Reliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation. We compare three segmentation strategies using images from Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory: (i) fixed color-based thresholding, (ii) supervised U-Nets trained from scratch, and (iii) pretrained vision transformers fine-tuned for binary segmentation. Models were evaluated on a held-out test set and a generalization set that comprised unseen species. On the held-out test set, thresholding, the best U-Net, and the best vision transformer achieved mean Dice scores of 58.3, 96.6, and 97.3, respectively. On the generalization set, the corresponding Dice scores were 56.5, 86.2, and 95.7. Thresholding remained effective on some datasets but failed when plant appearance changed. Supervised U-Net training resolved within-distribution errors but failed to generalize to novel species and backgrounds. Pretrained vision transformers consistently produced high-accuracy segmentations across the evaluated species, views, soil backgrounds, and tray types. These results benchmark the practical progression from fixed rules to task-specific supervision and pretrained visual representations for controlled-environment plant phenotyping.
Why it matches plant phenotyping methods植物フェノタイピングにおける画像セグメンテーション手法を比較・検証し、異なる種や撮像条件への汎化性能をベンチマークしているため、方法が研究の中心である。
abstractReliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation.
Abstract Tomato leaf diseases (TLDs) such as Early Blight (EB), Late Blight (LB), and Leaf Mold (LM) have a negative impact on crop yield and quality, result-ing in economic losses in agriculture. Traditional diagnosis methods depend on the visual recognition of a disease, which are time-consuming, subjective and may be difficult to reach in rural settings. Keeping these drawbacks in mind, the present work introduces a Transfer Learning model for tomato leaf disease classification based on EfficientNetB3 network. A pretrained Ef-ficientNetB3 network, trained on ImageNet, is used to obtain discriminative features like lesion boundaries, discoloration, fungal textures, and infection spots. Images are cropped to 224 × 224 pixels and split into training, validation and test set. The proposed architecture employs Global Average Pooling, a dense layer with ReLU activation, drop out regularization and Softmax classifier for classification of tomato leaf images into four classes: Early Blight, Late Blight, Leaf Mold and Healthy. Experimental results show the high classification accuracy and low training, validation and test-ing losses. Inter-class misclassifications of the confusion matrix show very few, which supports good generalization. Moreover, Grad-CAM visualiza-tions can generate interpretable heat maps that point to the regions of the image affected by the disease, and multi-class ROC analysis gives high AUC values, which means that it has excellent class separability. The proposed framework provides a precise, reliable, and interpretable approach for auto-mated tomato leaf disease diagnosis, contributing to precision agriculture by assisting in early detection and prompt management of tomato diseases.
Why it matches plant phenotyping methodsトマト葉画像から病害状態を推定する深層学習手法が研究の中心であり、Grad-CAMによる病変領域の解釈と性能評価も行っているため、植物表現型計測手法として採択。
abstractthe present work introduces a Transfer Learning model for tomato leaf disease classification based on EfficientNetB3 network
Reproduction assets foundThe paper's tomato leaf disease classification uses a publicly available Kaggle dataset (PlantVillage-derived tomato leaf images, 4000 images across 4 classes), explicitly declared in the Data Availability statement with a public URL. No author code, trained models, or other paper-specific assets are disclosed.Dataset · publicitted in accordance with the Journal policies.
Permission to use third-party material
Images or figures are never published previously and did not take from any
internet resources.
Data Availability
The dataset used in this study is publicly available from the PlantVillage
tomato leaf disease dataset on Kaggle’s following link:
https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf
Acknowledgements
The authors would like to thank SR University, Warangal, Telangana,
INDIA and Sharda University, Greater Noida, Uttar Pradesh, INDIA for
providing research facilities and computational resources to carry out this
work.Open asset ↗Kaggle · kaustubhb999/tomatoleafpdf-raw-page:20 lines:1-18Plant phenotyping relevance match · UnverifiedOpenAlex · checked 15 Sept 2026
Modern crop breeding demands precise organ-level analysis for trait quantification, making plant point cloud segmentation (PPCS) increasingly important. However, conventional deep learning approaches rely heavily on densely annotated datasets that are labor-intensive to acquire. Unified PPCS adaptation from distribution-shifted examples with minimal additional training remains challenging. To address this, we propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning to explicitly align features across spatial scales and an information-restricted decoding strategy that prevents reconstruction shortcuts and promotes robust adaptation. The resulting pre-training enables stable few-shot generalization across species and sensing conditions, while unified fine-tuning with inherited thresholds further reduces adaptation overhead. Under full supervision on Soybean3D, PlantC2USeg achieves the highest semantic IoU and instance mWCov among compared methods, at 91.91% and 94.62%. With 20 labeled samples, it leads both metrics at 89.78% and 90.27%; with only 10 samples, it retains the highest mWCov of 83.23% while achieving 83.19% IoU. Across HR3D, 10-shot transfer to tobacco, tomato, and sorghum averages 78.41% IoU and 79.42% mWCov, while 22-shot transfer to SYAU-Maize achieves the highest IoU and mRec at 92.75% and 93.51%. Furthermore, a leading category-averaged mIoU of 85.0% on ShapeNet Part demonstrates the framework's capability to handle diverse shape variations beyond agricultural domains. These results demonstrate that PlantC2USeg reduces overall adaptation effort under distribution shifts, enabling scalable plant phenotyping and transferable 3D representation learning beyond agriculture.
Why it matches plant phenotyping methods植物点群の器官レベル形質定量を目的とするセグメンテーション手法を開発し、複数データセット・作物・ショット条件で性能評価しているため、植物フェノタイピング手法が中心である。
abstractwe propose PlantC2USeg, a deep transfer learning framework featuring cross-scale consistency learning
This paper explores how deep learning methods can be used to monitor the health of crops and identify diseases, particularly for the apple crop. As the need for food security and sustainable farming methods increases, there is a strong demand for early detection of crop diseases. We have used a Convolutional Neural Network (CNN), based on the model of VGG16 architecture, since the model is known to be effective in image classification. The dataset contained 7771 training images for to enhance machines deep learning regarding plant diseases. Following that, validation image collection of 1747 images divided into four health conditions of the apple crops. In addition, the model was evaluated using 196 new images as a final test. To enhance the model capacity for recognizing diseases of real leaves rather than just memorize exact training pictures, data augmentation was used with ImageDataGenerator of TensorFlow. This means the training images were zoomed, rotated, and shifted to enable the machine detects more variations. Ten epochs of training were performed to measure the model accuracy. The results indicated that the model obtained significant improvement in training and validation accuracy from 56.43% to 78.12% and 92.94 to 96.93%, respectively. Most impressively, the final test dataset, which contained completely new images, scored an accuracy rate of 98%. The results indicate that in the architecture field the application of deep learning methodologies is effective, suggesting that automated detection of diseases by using sophisticated image analysis manages crop diseases identification efficiently. Combination of these methods successfully creates avenues for novel research to built real-time systems of crop disease monitoring, which help farmers increase their productions and farm their lands sustainably.
Why it matches plant phenotyping methodsリンゴ葉の画像から病害・健全状態をCNNで推定する画像ベース植物フェノタイピング手法であり、学習・検証・未知画像で性能評価を行っているため含める。
abstractWe have used a Convolutional Neural Network (CNN), based on the model of VGG16 architecture, since the model is known to be effective in image classification.
O cultivo de maçãs tem grande importância econômica no setor agropecuário brasileiro, especialmente na região Sul do país. No entanto, a produtividade dos pomares é frequentemente comprometida por doenças foliares que, se não tratadas, podem resultar em perdas substanciais. Nesse contexto, os avanços em técnicas de Aprendizado de Máquina têm possibilitado o desenvolvimento de soluções computacionais que auxiliam no diagnóstico agropecuário com maior precisão e agilidade. Este trabalho propõe uma abordagem baseada em Redes Neurais Convolucionais que utiliza aprendizado por transferência para detectar automaticamente sintomas de doenças em folhas de macieira. A metodologia desenvolvida inclui a segmentação e análise de regiões sintomáticas para reduzir o ruído proveniente de áreas saudáveis e direcionar o aprendizado do modelo para sinais relevantes. Um total de 32.382 manchas de sintomas foram extraídas de 1.995 imagens originais, abrangendo cinco classes de distúrbios foliares: glomerela, sarna, danos por herbicidas, deficiência de magnésio e deficiência de potássio. A rede MobileNetV2, treinada por meio de aprendizado por transferência, alcançou um F1-score de 0,926 e 93,8% de acurácia no conjunto de teste reservado. Os resultados indicam um bom desempenho no contexto avaliado, sugerindo o potencial da abordagem como ferramenta de apoio ao diagnóstico da saúde das plantas e à tomada de decisões em campo. Palavras-chave: aprendizado de máquina; visão computacional; doenças em plantas. Application of convolutional neural networks for disease detection in apple tree leaves ABSTRACT: Apple cultivation holds significant economic importance in the Brazilian agricultural sector, especially in the southern region of the country. However, orchard productivity is often compromised by foliar diseases, which, if left untreated, can lead to substantial losses. In this context, advances in Machine Learning techniques have enabled the development of computational solutions that support agricultural diagnostics with greater accuracy and agility. This work proposes an approach based on Convolutional Neural Networks that uses transfer learning to automatically detect disease symptoms in apple leaves. The developed methodology includes segmentation and analysis of symptomatic regions to reduce noise from healthy areas and focus the model’s learning on relevant signals. A total of 32,382 symptom patches were extracted from 1,995 original images, covering five foliar disorder classes: glomerella, scab, herbicide damage, magnesium deficiency, and potassium deficiency. The MobileNetV2, trained via transfer learning, achieved a F1-score of 0.926 and 93.8% accuracy on the held-out test set. The results indicate good performance in the evaluated setting, suggesting the approach’s potential as a tool to support plant-health diagnosis and field decision-making. Keywords: machine learning; computer vision; plant disease.
Why it matches plant phenotyping methods葉の病徴を画像から自動検出・分類するCNNと、症状領域のセグメンテーションを中心的に開発・評価しており、植物病害状態の画像ベース表現型計測に該当する。
abstractEste trabalho propõe uma abordagem baseada em Redes Neurais Convolucionais que utiliza aprendizado por transferência para detectar automaticamente sintomas de doenças em folhas de macieira.
India’s economy is heavily reliant on agriculture, with a diverse array of crops grown on vast tracts of land. Fruit cultivation, especially papaya, has become more popular in recent years because of its high nutritional and financial value. To increase yield, maximize resource use and lessen reliance on chemical pesticides, modern techniques like protected cultivation and hydroponics are being used more and more. Fruit crops grown in controlled or semi-controlled environments are still susceptible to nutrient imbalances despite these developments, which can have a substantial impact on plant health, fruit quality and overall productivity. Papaya leaf nutrient deficiencies frequently show up in the early stages of growth and can result in poor fruit development and decreased yield if they are not detected in time. To support early diagnosis and better crop management, the current study focuses on creating an effective method for identifying nutrient deficiencies in papaya leaves using a deep learning (DL) framework based on transfer learning (TL). In this nutrient and micronutrient deficiency study and field work observation during year 2024 to 2026 with different climate and weather conditions done in order to tackle a new but related classification task, in the context of plant health assessment, several well-established architectures including InceptionV3, VGG19, DenseNet and Xception have been widely explored for leaf image analysis. Studies commonly utilize publicly available datasets, such as papaya leaf image repositories hosted on platforms like IEEE DataPort, to fine-tune these models for efficient feature extraction and accurate identification of nutrient and micronutrient deficiency patterns. This body of work demonstrates the growing role of transferring convolutional neural network (CNN) models in advancing automated crop monitoring and decision support systems.
Why it matches plant phenotyping methodsパパイヤ葉画像から栄養・微量栄養素欠乏という植物状態を深層学習で識別する手法の開発が研究の中心であり、植物フェノタイピングに該当する。
abstractthe current study focuses on creating an effective method for identifying nutrient deficiencies in papaya leaves using a deep learning (DL) framework based on transfer learning (TL).
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Within the context of climate change, quinoa ( Chenopodium quinoa Willd.) is a climate-resilient crop with high nutritional value. The effects of deficit irrigation on quinoa growth and physiological performance under arid conditions remain insufficiently understood. This study evaluated ten quinoa genotypes (two commercial varieties and eight accessions) under two irrigation regimes to identify traits and spectral indices associated with water-stress tolerance. We combined manual phenotyping of agromorphological and physiological traits with multispectral and spectroradiometer measurements to calculate 35 vegetation indices across 13 and 5 dates, respectively. Deficit irrigation reduced plant height (18%), specific leaf area (8%), yield (43%), harvest index (26%), relative water content (7%), and dry matter accumulation (36%), while relative chlorophyll content (SPAD, Soil Plant Analysis Development) and stomatal density increased by 16% and 13%, respectively; accession ACC_23 exhibited the highest water-use efficiency (5.9 g kg -1 ). A univariate analysis of 35 vegetation indices across 13 dates showed that: Health Index(HIV), Normalized Green-Red Difference Index (NGRD), Red-Green Ratio (RG) and Plant Senescence Reflectance Index (PSRI), were the most sensitive, detecting significant differences between irrigation treatments in up to 32 of the 130 possible genotype-by-date comparisons. Integrating remote sensing into crop phenotyping represented a significant methodological improvement by enhancing phenotyping efficiency, improving detection of deficit irrigation effects, and facilitating identification of tolerant quinoa genotypes for arid production systems.
Why it matches plant phenotyping methodsリモートセンシングと多時点の植 phenotyping を統合し、35の植生指数の感度比較によって水ストレス関連形質を抽出する方法適用が、研究の主要な技術的要素として明示されています。
abstractWe combined manual phenotyping of agromorphological and physiological traits with multispectral and spectroradiometer measurements to calculate 35 vegetation indices across 13 and 5 dates, respectively.
Purpose Conventional plant disease detection is time-consuming and prone to human error. The purpose of this study is to propose an edge artificial intelligence (AI)-based deep learning framework for plant disease detection under real-field conditions. The model integrates convolutional neural networks (CNNs) with a Sliding Window Mean Absolute Deviation (SWMAD) preprocessing technique to address illumination variability and complex background conditions. Design/methodology/approach A dual-layer CNN model is developed for plant disease classification using HSV segmentation, flood-fill segmentation and SWMAD preprocessing to handle real-field variations. The model is trained on PlantVillage and real farm images and deployed via TensorFlow Lite for real-time offline detection. TensorFlow Lite is used to enable efficient on-device inference for deployment in resource-constrained environments. Findings Benchmark experiments conducted on the PlantVillage dataset achieved a classification accuracy of 99.91% under controlled conditions. On the hybrid dataset comprising PlantVillage and real-field images, the optimized CNN framework achieved a validation accuracy of 95.01% following extensive evaluation of optimizers, layer architectures and worker configurations. The integration of the proposed SWMAD preprocessing technique into the finalized architecture further improved the validation accuracy to 97.38%, demonstrating enhanced robustness and classification performance under practical agricultural conditions in the final deployed model. Originality/value The originality of this study lies in several novel contributions. First, we introduce an SWMAD-based preprocessing technique, which enhances local statistical variations in leaf images by capturing pixel-level deviations from neighborhood intensity means. Unlike, conventional preprocessing methods, SWMAD is specifically designed to handle real-field challenges such as illumination variation, noise and complex backgrounds. The improvement in validation accuracy demonstrates the effectiveness of the proposed approach in capturing more discriminative features compared to existing techniques, thereby improving overall model robustness and reliability in practical agricultural environments.
Why it matches plant phenotyping methods植物病害という植物状態を画像から推定する深層学習・前処理・エッジ展開手法が研究の中心であり、実環境での検証も行っているため。
abstractThe purpose of this study is to propose an edge artificial intelligence (AI)-based deep learning framework for plant disease detection under real-field conditions.
Common beanGrapevineLeafClassificationObject detectionStress / disease detectionDisease symptoms / severity
Plant leaf disease is a grave risk to crop suitability and agricultural sustainability, and therefore, the ability to make early and accurate diagnosis is a mandatory need in the contemporary precision farming system.In recent years, deep learning has gained significant attention for image-based plant disease detection.Despite its effectiveness, model performance can be influenced by factors such as redundant feature representations and sensitivity to hyperparameter selection.To address these challenges, this study proposes a nested hybrid optimization framework that combines the Cuckoo Search Algorithm (CSA) for channel selection with the Beluga Whale Optimization Mechanism (BWOM) for tuning the hyperparameters of a Convolutional Neural Network (CNN).The proposed approach is independently evaluated on bean and grape leaf datasets under consistent experimental conditions to assess its disease classification performance.In addition to strong predictive performance, the framework incorporates explainable AI (XAI) techniques, namely Gradient-weighted Class Activation Mapping (Grad-CAM) and Gradientweighted Class Activation Mapping Plus Plus (Grad-CAM++), to enhance model interpretability.These approaches highlight the most significant visual features influencing predictions, thereby providing valuable insights for agronomists and fostering trust in AI-based systems.Experimental results show that the proposed CSA-BWOM optimized CNN achieves classification accuracies of 99.61% and 99.38% on the bean and grape datasets, respectively, outperforming baseline CNN models and exhibiting competitive performance when compared to a few existing approaches.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類するCNN最適化・説明可能AI手法が研究の中心であり、植物病害状態の表現型推定に該当する。
titleExplainable AI-based CNN Optimization Model for Plant Leaf Disease Detection
Abstract One of the most important challenges faced by smallholder farmers in the agricultural industry is the lack of accurate, timely knowledge to predict and detect crop health issues. Crop productivity is often threatened not only by diseases but also by environmental and physiological stresses, which contribute to significant yield losses and negatively impact the national economy. Traditional detection methods are time-consuming, costly, and require expert knowledge, creating a need for automated and intelligent systems. This work proposes a dual-functional framework that combines crop disease and stress detection using advanced machine learning and deep learning techniques to accurately classify healthy and diseased leaves. This integrated system ensures early detection, reduces crop loss, improves productivity, and provides a scalable, farmer-friendly solution for sustainable agriculture.
Why it matches plant phenotyping methods葉画像から健康・病害状態を機械学習で分類する手法が研究の中心であり、植物の病害・ストレス状態を直接推定するため、植物フェノタイピング手法として採用。
abstractThis work proposes a dual-functional framework that combines crop disease and stress detection using advanced machine learning and deep learning techniques to accurately classify healthy and diseased leaves.
Food productivity, quantity and quality are at stake when plant diseases such as rice diseases undermine the food security. Rice leaf disease treatment necessitates accurate and timely diagnosing. This study describes a deep learning model for categorizing and forecasting rice plant diseases. Using the remora optimization algorithm (ROA) on a rice leaf dataset demonstrates its potential for plant disease classification. The ROA-DM method detects rice leaf diseases using the ROA algorithm, a deep maxout network (DMN), and a deep autoencoder (DAE). ROA is applied to the learning parameters of deep model in order to achieve better convergence and avoiding local minima, which usually happens with conventional gradient-based optimizers. Experiments show that the suggested framework is accurate and precise across illness categories. The confusion matrices display the training and validation accuracy, losses of this model. The performance of our optimal learning method with respect to other methods indicated its potential for identifying leaf diseases. The accuracy of the ROA-DM method is 98.5%.
Why it matches plant phenotyping methodsイネ葉の観察画像から病害状態を分類・検出する深層学習手法が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractThis study describes a deep learning model for categorizing and forecasting rice plant diseases.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicThe dataset collected from https://www.kaggle.com/datasets/emmarex/plantdisease (PlantVillage dataset) for algorithm testing in plant disease diagnosis 35 . The selected rice leaf disease samples from PlantVillage dataset consisting of 3050 colour leaf images across four classes.Open asset ↗Kaggle · emmarex/plantdiseaselines:85-97Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published30 Jun 2026Journal of Intelligent Decision Making and Information ScienceCited by 0 · OpenAlex ↗
This study presents a deep learning-based framework for automated tomato leaf disease detection using a transfer learning approach built on ResNet18 architecture. The system is designed to classify 10 disease categories using image inputs resized to 224×224 pixels, leveraging ImageNet pre-trained weights to enhance feature extraction. The dataset consists of approximately 18,345 training samples with a batch size of 16 and trained over 10 epochs using the Adam optimizer and CrossEntropy loss function. Experimental results demonstrate strong classification performance, achieving a peak validation accuracy of 98.2% at epoch 9, with validation loss reduced to 0.64 from an initial value of approximately 1.8. The model shows high confidence predictions, with over 90% of test samples falling within the 90–100% confidence range. Per-class F1-scores range between 0.82 and 0.95, indicating consistent performance across multiple disease categories. The confusion matrix reveals strong diagonal dominance, confirming correct classification for most classes; however, specific misclassification patterns were observed. For instance, Bacterial_spot and Early_blight exhibit mutual confusion, while Septoria_leaf_spot shows complete misclassification into Tomato_mold, indicating limitations in distinguishing visually similar disease patterns. A balanced test dataset with class distribution ranging between 9% and 11% ensures unbiased evaluation. Additionally, Grad-CAM visualization confirms that the model focuses on biologically relevant regions such as lesion areas and leaf textures, improving interpretability. Despite achieving high accuracy under controlled conditions, the model’s generalization to real-world environments remains a challenge. The study highlights the need for improved robustness against variations in lighting, background, and disease severity. Overall, the proposed system demonstrates strong potential for precision agriculture applications, particularly in mobile-based disease diagnosis systems for farmers.
Why it matches plant phenotyping methodsトマト葉の病徴を画像から分類する深層学習手法を開発・評価しており、植物の病害状態を直接推定する方法が研究の中心です。
abstractThis study presents a deep learning-based framework for automated tomato leaf disease detection using a transfer learning approach built on ResNet18 architecture.
Agriculture remains one of the most essential sectors for sustaining human life and economic stability. However, crop diseases continue to pose a serious threat to agricultural productivity, often leading to significant financial losses for farmers. Traditional disease identification methods rely heavily on manual inspection, which is time-consuming, requires expert knowledge, and is not always accurate. In this paper, a smart crop disease detection system is proposed using machine learning techniques. The system focuses on analyzing leaf images to identify visible symptoms of diseases at an early stage. Image preprocessing techniques are applied to enhance the quality of the input data, followed by feature extraction and classification using an efficient learning model. The proposed approach aims to reduce human effort while improving detection accuracy. The model is trained and tested on a dataset of crop leaf images and demonstrates promising performance in identifying multiple types of plant diseases. The results indicate that the system can serve as a supportive tool for farmers by providing quick and reliable predictions. This approach not only improves productivity but also contributes to sustainable agricultural practices. Future enhancements can further improve real-time detection and expand the system for a wider range of crops
Why it matches plant phenotyping methods葉画像から植物病害の可視症状を抽出・分類する機械学習手法が研究の中心であり、植物状態の表現型推定に該当する。
abstractThe system focuses on analyzing leaf images to identify visible symptoms of diseases at an early stage.
Xylem tissue enables efficient long-distance water transport but is a primary target for vascular pathogens. This study investigates how systemic invasion by Verticillium dahliae impairs the hydraulic function of pepper (Capsicum annuum) plants, focussing on xylem colonisation and its anatomical and physiological effects. Real-time sap flow was continuously monitored with custom-built ExoBeat sensors, while periodic stem water potential measurements allowed calculation of changes in stem hydraulic conductance as an additional indicator of xylem performance. Fungal colonisation was assessed by quantitative polymerase chain reaction, and vessel occlusions and embolised conduits were visualised using scanning electron microscopy and micro-computed tomography, complemented by direct hydraulic conductivity measurements. By 14 d post inoculation, V. dahliae had progressed from roots to aboveground tissues, coinciding with a marked decrease in sap flow, water potential, and soil-to-stem hydraulic conductance, alongside the onset of dwarfing. Direct fungal blockage and anatomical changes were the primary contributors to hydraulic dysfunction. Vessel occlusion by tyloses, gels, and air embolisms played a negligible role. This study reveals how V. dahliae progressively impairs pepper hydraulics through systemic xylem colonisation, highlighting the value of real-time sap flow monitoring. Our integrative, multidisciplinary approach offers a powerful framework to unravel the complexity of dynamic plant-fungal vascular interactions.
Why it matches plant phenotyping methodsカスタムセンサーによるリアルタイム・サップフロー測定を中心に、植物の水理機能・病原体による機能低下を定量化しており、単なる生物学的測定にとどまらない実質的なフェノタイピング手法の適用である。
abstractReal-time sap flow was continuously monitored with custom-built ExoBeat sensors
Guava cultivation is considerably influenced by foliar and fruit diseases whose overlapping symptoms and environmental variability make accurate field-level diagnosis challenging. Numerous studies have been conducted to find efficient methods of diagnosing plant diseases, but most focus on image-level classification and do not include lesion localization or pixel-level segmentation of the images within a single framework of analysis. This study proposes a comprehensive framework for utilizing automated image analysis to classify guava leaf and fruit diseases at the image level, locate lesions, and segment lesions at the pixel level from multiple images of the same type of disease collected from various growing conditions. The dataset was enriched through three augmentation strategies including standard preprocessing, structured augmentation, and GAN-based synthetic image generation, expanding the effective training data to approximately 7,000 images, while a 5-fold cross-validation strategy guided model selection and final performance was assessed on a held-out test set. The experimental evaluation of multiple state-of-the-art Convolutional Neural Networks (CNNs) for the classification of guava leaf and fruit diseases indicated that the model generated using the ResNet50+DenseNet121 model fusion achieved the highest classification accuracy of 98.20%. For lesion detection and segmentation, YOLOv8-seg outperformed Mask R-CNN, achieving mAP@0.5 of 0.907 and 0.889, and mAP@0.5:0.95 of 0.783 and 0.769 for detection and segmentation, respectively, with a balanced precision–recall profile. The techniques of Explainable AI (XAI) were used to increase the transparency of this model by identifying areas in the image that are significant to the actual lesion. The framework was further designed with practical web-based deployment in mind, evaluating both lightweight and high-capacity models to balance computational efficiency against predictive accuracy. From this research, it was concluded that using model fusion, data augmentation, and segmentation-aware lesion detection would provide a solution for managing guava diseases effectively.
Why it matches plant phenotyping methodsグアバの葉・果実における病斑の分類、位置特定、画素レベル分割を自動化する画像解析フレームワークを開発・評価しており、植物の病害状態の表現型取得が研究の中心である。
abstractThis study proposes a comprehensive framework for utilizing automated image analysis to classify guava leaf and fruit diseases at the image level, locate lesions, and segment lesions at the pixel level
Sapodilla (Manilkara zapota), or chickoo, is a key tropical fruit, very popular in India, Mexico, and Thailand, as it is nutritionally and economically valuable. Nonetheless, the production of sapodillas is often affected by several diseases, which reduce fruit quality and quantity. The dataset used in this paper is a sapodilla fruit image dataset, comprising 1,518 images, gathered in the field under the practicing conditions on 18 February 2025, 22 February 2025, in Rahu village, Pune district, Maharashtra, India, with the use of smartphone cameras. The data is sorted into four categories, namely: Anthracnose, Bacterial rot, Healthy, and Sap bleeding. The photographs were taken in different backgrounds and in different lighting conditions to represent real-life cultivation conditions. The data is expected to be useful in machine learning-based plant disease detection, classification, and analysis, and spur the creation of intelligent and sustainable agricultural systems.
Why it matches plant phenotyping methodsサポディラ果実の病害・健全状態を画像で記録したデータセット自体が中心で、植物病害の画像ベース表現型解析に利用できる。
titleA curated image dataset for sapodilla fruit (Manilkara zapota) disease and fruit quality analysis.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicData identification number: Version: V1, Doi: 10.17632/xbzd2fjd3p.1
Direct URL to data: https://data.mendeley.com/datasets/xbzd2fjd3p/1Open asset ↗10.17632/xbzd2fjd3p.1html-lines:1-114Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Quantitative phenotyping of pepper seedlings is important for greenhouse plug tray seedling cultivation, but it remains constrained by inefficient manual monitoring, complex greenhouse backgrounds, and growth-stage-dependent discrepancies between two-dimensional image traits and actual leaf biomass. In this study, a cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping. The framework integrated Visual Dynamic Momentum YOLO (VDM-YOLO) for individual seedling localization and growth-stage recognition, Variance Guided Strip Ghost Gated UNet (VSG-UNet) for lightweight, high-resolution leaf segmentation, and a stage-aware correction model for leaf dry biomass estimation. In performance evaluation, VDM-YOLO achieved a mean average precision at an intersection over union threshold of 0.5 (mAP0.5) of 89.27%, improving mAP0.5 by 1.82 percentage points over YOLOv12. VSG-UNet achieved a mean intersection over union (mIoU) of 83.9% and a Dice coefficient of 81.8%, while reducing floating point operations (FLOPs) and parameters by 44.2% and 61.2%, respectively, compared with U-Net. After stage-aware calibration, the coefficient of determination (R2) between segmented area and leaf dry weight increased from 0.764 to 0.813, and the root mean square error (RMSE) decreased from 0.0210 g to 0.0190 g. These results demonstrated that the proposed framework provided a proof of concept approach based on RGB images for the nondestructive assessment of leaf area and leaf dry biomass in pepper seedlings under restricted experimental conditions.
Why it matches plant phenotyping methodsRGB画像による葉の検出・セグメンテーションと、葉面積から葉乾燥バイオマスを推定する手法を開発・評価しており、植物表現型取得が研究の中心である。
abstracta cascaded vision framework with stage-specific morphological correction was developed for nondestructive seedling phenotyping.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
FlowerClassificationGrowth / development / phenology
Accurate recognition of flower growth stages is important for plant phenotyping but remains challenging due to subtle visual differences and limited labeled data. This study proposes a hybrid CNN/Transformer + GCN framework for fine-grained flower growth-stage classification. A new dataset, BD Flower Growth, is introduced with 3,889 original images from eight Bangladeshi flower species, categorized into three stages (early, mid, full), forming 24 classes. The dataset is divided into training and testing sets, with augmentation applied only to the training data. Deep backbone networks are used to extract feature maps, which are transformed into graph representations and refined using Graph Convolutional Networks (GCN). A systematic ablation study is conducted by varying GCN depth (3, 5 layers), node resolution ([Formula: see text], [Formula: see text]), and graph construction methods (4-neighbour, 8-neighbour, and KNN with [Formula: see text]). Experimental results show that performance depends strongly on both backbone and graph configuration. The best performance of 97% accuracy is achieved by EfficientNetV2, DenseNet201-based hybrid models, additionally Swin Transformer model shows the largest improvement, increasing from 84% to 97% after GCN integration. Across different settings, grid-based graphs (4- and 8-neighbour) consistently provide more stable and higher performance compared to KNN graphs, while moderate GCN depth (3-5 layers) offers the best balance accuracy. Cross-dataset evaluation on the Oxford 102 Flower dataset further demonstrates the generalization capability of the proposed approach. These findings highlight the effectiveness of hybrid graph-based learning and the importance of graph configuration in improving fine-grained classification.
Why it matches plant phenotyping methods花の生育段階という植物状態を画像から分類する手法の開発・比較検証が中心で、新規データセットとアブレーションおよびクロスデータセット評価も含むため。
abstractAccurate recognition of flower growth stages is important for plant phenotyping
Main conclusion A novel and efficient method was developed to accurately measure thickness in 3D of many cells from a confocal stack, as well as to track changes in cell thickness overtime. Plant cells and organs are three-dimensional objects with a certain thickness. Among basic geometric parameters (length, width, depth/thickness), cell thickness is less accurately and comprehensively measured, probably because it cannot be directly seen. The current methods of cell thickness quantification have some limitations, such as measuring only from a cross-section, not accounting for the directionality of biological thickness, or not offering a way to track changes in thickness of individual cells over time. This research is an attempt to bridge the gap, by making the quantification of thickness and tracking its changes in many cells easier and more accurate. We devised a novel method to efficiently measure average cell thickness in 3D from cells imaged with confocal microscopy, the most popular technique to image live samples over many days. The method, in combination with the popular software MorphoGraphX, also allows accurate and efficient tracking of changes in thickness between different time points. We tested the method on various organs of the model plant Arabidopsis thaliana such as the shoot apical meristem, the hypocotyl, the cotyledon, and the sepal. We demonstrated that this new method can reliably measure the thickness of hundreds of cells at once in a short amount of time to reveal new biological insights. We believe this would be a useful tool for plant researchers to accurately characterize this hidden morphological dimension.
Why it matches plant phenotyping methods植物細胞の3D厚みと経時変化を効率・高精度に測定する手法を開発し、複数器官で検証しているため、植物形態フェノタイピング手法が中心である。
abstractA novel and efficient method was developed to accurately measure thickness in 3D of many cells from a confocal stack, as well as to track changes in cell thickness overtime.
Despite the widespread use of image-only convolutional models for plant disease diagnosis to provide global food security, image variability at the field level, visually similar symptoms, and stress due to soil nutrients or moisture conditions, can cause loss of accuracy. This paper compares classical machine learning classification models to custom convolutional neural networks and pretrained transfer-learning models for multi-crop and multi-disease classification and also introduces a late-fusion multimodal decision support model that could integrate data about images, soil, and weather. Experiments were conducted on the PlantVillage dataset which had 54,305 RGB images belonging to 38 different crop-condition classes (43,456 training, 10,849 validation, and 10,849 test images) across 14 different crops. The accuracy, macro-precision, macro-recall and macro-F1 score were computed for the five classical classifiers (KNN, Random Forest, Extra Trees, SGD-linear SVM, and SVC-RBF using PCA-reduced features), three custom CNN variants, and four pretrained models (ResNet50, MobileNetV2, GoogleNet, and EfficientNetB7). Of the classical models, SVC with RBF kernel yielded the highest accuracy (83.58%) and MacroF1 (82.96%). In the case of the custom CNN models, the deeper they became and the more dropout the higher accuracy they gained, with CNN-V3 attaining 95.71% accuracy and 95.66% macro-F1. Transfer learning yielded the best results with MobileNetV2 (99.30% accuracy and macro-F1) outperforming ResNet50 (98.60% accuracy and macro-F1) and GoogleNet (97.83% accuracy and 97.46% macro-F1). The findings serve as the basis for the introduction of a multimodal system for soil forecasting integrating a MobileNetV2 image encoder, a residual MLP for soil features, and two dual LSTMs for 48-hour and 168-hour time-series of the weather. The interpretability, modularity and the sufficient resistance towards loss of sensor information for probability-level late fusion with 0.80, 0.10, 0.05 and 0.05 respectively make the framework appropriate for precision-agriculture advisory systems, until it is tested in the field.
Why it matches plant phenotyping methods植物画像から病害状態を推定する分類手法を複数比較し、マルチモーダル意思決定フレームワークを構築・評価しており、病害表現型の取得・推定が中心である。
abstractThis paper compares classical machine learning classification models to custom convolutional neural networks and pretrained transfer-learning models for multi-crop and multi-disease classification
Genome-wide association studies (GWAS) have advanced crop genetics by the detection of loci controlling complex traits; however, their power is often constrained by the quality and the throughput of phenotypic data. In this study, we integrated hyperspectral and genomics data to investigate the genetic architecture of spectral signatures associated with yield components in wheat. A diverse panel of 341 soft wheat lines was evaluated over three years, and hyperspectral data were collected using a UAV-mounted sensor. Among 273 spectral bands, those most strongly correlated with grain yield (GY), thousand-grain weight (TGW), and grains per unit area (GN) were selected. Principal component analysis was used for dimensionality reduction, and the first principal component (PC1), here defined as the hyperspectral phenome, accounted for 78.9%-97.1% of overall variance. The GWAS using both manual phenotypes and hyperspectral phenomes identified 31 significant marker-trait associations (MTAs), including several pleiotropic loci shared across traits and data types. A notable SNP on chromosome 1A, associated with all three hyperspectral phenomes, was located within a gene specifying a chlorophyll a-b binding protein, a key component of photosynthesis and stress response. Additional MTAs were linked to genes involved in cytochrome P450 metabolism and LRR proteins, highlighting their roles in yield and environmental response. Overall, this study shows that hyperspectral imaging serves as a valuable, high-throughput secondary correlated trait for uncovering novel loci and dissecting the genetic basis of complex yield traits in wheat.
Why it matches plant phenotyping methods小麦の収量関連形質を推定するUAV搭載ハイパースペクトル計測と、スペクトルデータからフェノームを抽出する解析が研究の中心であり、GWASへの実質的な応用として記述されている。
abstracthyperspectral data were collected using a UAV-mounted sensor
Crop diseases pose a significant threat to global food security, often resulting in substantial yield losses and economic instability for farmers. Traditional methods of disease identification, which rely on manual visual inspection, are labor-intensive, subjective, and frequently prone to error. While Convolutional Neural Networks (CNNs) have established a baseline for automated detection, they occasionally struggle with capturing global context within complex leaf patterns. This paper presents a robust image-based classifier utilizing Vision Transformers (ViT) to identify crop diseases from leaf images. Leveraging the self-attention mechanism, the proposed model effectively captures long-range dependencies in image data. The system is trained and validated on the PlantVillage dataset using transfer learning techniques. Experimental results demonstrate that the Vision Transformer architecture achieves a classification accuracy of 98.4%, outperforming traditional CNN architectures such as ResNet50 and VGG16. These findings suggest that transformer-based models offer a promising avenue for precision agriculture, enabling early intervention and reduced pesticide usage.
Why it matches plant phenotyping methods葉画像から作物病害を分類するVision Transformer手法の開発・検証が中心で、植物の病害状態を直接推定しているため。
abstractThis paper presents a robust image-based classifier utilizing Vision Transformers (ViT) to identify crop diseases from leaf images.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · checked 5 Sept 2026
ABSTRACT Southern leaf blight (SLB) is a foliar disease of maize (Zea mays L.) caused by the necrotrophic fungal pathogen Cochliobolus heterostrophus. Genetic resistance is the most effective control method for SLB. Developing disease resistant maize lines requires field trials during which disease phenotypes must be visually assessed. Remote sensing using drones is an emerging technology that can be leveraged for high-throughput phenotyping of disease severity that is otherwise labor-intensive and subjective. This project used a deep learning approach to estimate SLB disease severity of single-row maize plots from drone imagery. Over 26,000 plot-level images produced from flights conducted across three growing seasons were labeled with in-field visual scores taken contemporaneously by expert raters. Variation in environmental conditions contributed to a labeled image dataset that reflects the complexity of agronomic field experiments. We assessed the ability of nine deep learning models from three architectural families to estimate disease severity. The best-performing model, EVA-02-B, achieved strong cross year generalization (R 2 = 0.697). Error analysis found that performance was more strongly associated with seasonal disease progression and flight-score time offset than with image-level noise. UAV-based deep learning estimated SLB severity with comparable precision to expert raters. This study lays the groundwork for integrating automated phenotypes into genetic studies of disease resistance. PLAIN LANGUAGE SUMMARY Southern leaf blight (SLB) of maize is a disease that causes yield loss worldwide and developing resistant varieties offers the best hope for controlling the disease. Studying SLB resistance requires plant pathologists to visually score severity in the field, a labor-intensive method that requires expertise. To address these challenges, we asked whether SLB severity scoring could be automated using drone images and artificial intelligence (AI). We trained AI models using three years of image and score data then compared the results to visual scores taken by five plant pathologists. The best performing AI model showed a similar level of consistency to the experts and proved capable of scoring severity despite unpredictable and uncontrollable conditions that affect field imaging experiments such as weeds or shadows. These findings provide a validated method that improves the efficiency of maize disease research, a critical area of study for agricultural sustainability and productivity.
Why it matches plant phenotyping methodsドローン画像と深層学習により、トウモロコシの葉病害重症度という植物状態を推定し、複数年データで性能と汎化性を評価した手法研究である。
abstractRemote sensing using drones is an emerging technology that can be leveraged for high-throughput phenotyping of disease severity
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · Crossref · checked 5 Sept 2026
1 Abstract Non-structural carbohydrates (NSCs) are central to plant carbon allocation and physiological regulation, yet their quantification typically relies on destructive biochemical assays that lack spatial resolution. Here, we developed a shortwave infrared (SWIR) hyperspectral imaging workflow for non-destructive estimation and spatial reconstruction of starch-associated variation in strawberry leaves. The workflow combined automated hyperspectral segmentation, spectral preprocessing, Partial Least Squares Regression (PLSR), and constrained wavelength selection. Sample-level spectra extracted from 114 strawberry leaf samples grown across three different metabolic conditions were paired with destructive starch measurements and used to train models across the 900–1750 nm spectral range. A constrained greedy band-selection strategy revealed that predictive performance approached a plateau at approximately 12 wavelengths, indicating substantial spectral redundancy within the full hyperspectral dataset. The final reduced-band model achieved a cross-validated coefficient of determination (R 2 ) of 0.771 ± 0.066 and a root mean squared error (RMSE) of 0.743 ± 0.098 mg g −1 fresh weight using repeated stratified 5-fold cross-validation. Pixel-wise application of the final model generated spatial starch-associated maps that preserved pronounced intra-leaf heterogeneity, including vein-associated spatial structure. These results demonstrate that starch-associated spectral information can be reconstructed from a constrained reduced-band SWIR framework while retaining sufficient predictive performance for spatial mapping. The identified wavelength reduction supports the feasibility of deployable multispectral systems for non-destructive carbohydrate sensing in plant phenotyping applications.
Why it matches plant phenotyping methods植物葉のデンプン状態を非破壊推定・空間再構成するSWIR画像計測とケモメトリック解析ワークフローを開発・検証しており、フェノタイピング手法が中心です。
abstractHere, we developed a shortwave infrared (SWIR) hyperspectral imaging workflow for non-destructive estimation and spatial reconstruction of starch-associated variation in strawberry leaves.
Abstract Potato quality detection is a critical step that determines their market value. However, manual sorting suffers from low efficiency, high cost, and a high misjudgment rate. Therefore, the rapid and accurate classification of defective potatoes is of great economic significance for reducing industrial losses. In this study, a lightweight convolutional neural network (WavebandCNN) was constructed combined with hyperspectral imaging (HSI) technology to achieve rapid and accurate classification of four categories of potatoes: healthy, greening, skin damage, and dry rot. First, hyperspectral images of 400 potato samples were collected and calibrated, and regions of interest (ROI) were extracted to construct a spectral dataset. The performance of the lightweight convolutional neural network was evaluated using raw spectra and five preprocessed spectra, respectively, and compared with three traditional machine learning models: Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). Meanwhile, the successive projections algorithm (SPA) was employed to select characteristic wavelengths for data dimensionality reduction. The results show that WavebandCNN achieved the highest classification accuracy of 93.11% with raw spectra, significantly outperforming all comparative models. After screening 20 characteristic wavelengths via SPA, the classification accuracy was improved to 95.98%, while the training time and data redundancy were greatly reduced. This study confirms that the combination of hyperspectral imaging technology and the WavebandCNN model enables accurate identification of potato defects, providing a new approach for the online detection and practical application of potato defects.
Why it matches plant phenotyping methodsジャガイモの欠損・病変状態をハイパースペクトル画像とCNNで直接分類する手法を構築・比較・評価しており、植物状態の取得・推定が研究の中心である。
abstracta lightweight convolutional neural network (WavebandCNN) was constructed combined with hyperspectral imaging (HSI) technology to achieve rapid and accurate classification of four categories of potatoes: healthy, greening, skin damage, and dry rot.
Abstract Occlusion is a major factor limiting accurate three-dimensional (3D) wheat phenotyping. In natural growth conditions, overlapping spikes, leaves, and stems often make only partial target regions visible in single-view images, hindering complete and reliable 3D reconstruction. To address this problem, this study proposes an amodal completion-driven framework for single-view 3D reconstruction of occluded wheat. The framework first uses visible prompts to recover the complete appearance and structural cues of occluded targets, and then feeds the completed images into single-view 3D reconstruction models to generate complete 3D structures. To support model training and evaluation, we construct the MMWO (Multi-view Multi-instance Wheat Occlusion) dataset from MMW by synthesizing diverse occlusion samples through organ-level cutouts, random geometric transformations, and region-constrained pasting, with annotations including visible masks, occlusion masks, and complete target images. Six representative reconstruction methods, including Direct3D, Real3D, SF3D, Spar3D, TRELLIS.2, and Hunyuan3D, are systematically evaluated. Hunyuan3D achieves the best geometric performance, with the lowest mean CD-L 1 and CD-L 2 values of 0.1286 and 0.0536, and the highest mean F-score of 0.5668. SF3D achieves the best rendering quality in terms of PSNR, SSIM, and LPIPS. In addition, Pix2Gestalt completion reduces the estimation errors of spike length, width, and area from 9.31%, 10.89%, and 32.23% to 4.64%, 9.70%, and 9.45%, respectively. These results demonstrate that amodal completion can effectively alleviate occlusion-induced information loss and provide more complete structural priors for single-view 3D wheat reconstruction. This study offers a feasible solution for robust 3D wheat phenotyping under occlusion and provides a systematic reference for applying general-purpose 3D generative models to agricultural phenotyping.
Why it matches plant phenotyping methods遮蔽下小麦の単視点3D再構成とアモーダル補完を開発し、データセット構築、複数手法の系統評価、器官形質推定誤差の検証まで行っており、植物フェノタイピング手法が中心である。
abstractthis study proposes an amodal completion-driven framework for single-view 3D reconstruction of occluded wheat
Plant leaf diseases must be detected and treated early to improve crop yield and reduce agricultural losses. However, pixel-level representations and the inability to be read limit the applicability of existing deep learning approaches to the agricultural sector. A graph neural network termed the Attention-Enhanced Graph Neural Network (AE-GNN) may explain and diagnose multi-plant leaf disease. The proposed framework models leaf pictures as a graph with nodes representing discriminative leaf areas and edges representing their spatial connection. Before creating the global context vector and classification, graph features are aggregated, and an attention weighting method is applied to refocus on disease-relevant nodes obscured by less informative background characteristics. Final disease prediction uses a multilayer perceptron classifier. A curated dataset of half-spinach and curry leaf pictures is used to assess the proposed method for fifteen illnesses and their healthy classifications. Grad-CAM-based explainable AI methods make the model predictions' most important areas clearer. The dataset and source code from this work are available on GitHub for reproducibility and openness. Experimental results reveal that the proposed AE-GNN outperforms convolutional neural networks and graph-based models in classification. Graph-structured learning, attention enhancement, and explainability create a robust and interpretable framework for multi-plant leaf disease diagnosis.
Why it matches plant phenotyping methods葉画像から植物病害状態を分類・診断する画像解析手法を提案し、既存モデルとの比較評価と説明可能性解析を行っているため、植物フェノタイピング手法が中心である。
abstractA graph neural network termed the Attention-Enhanced Graph Neural Network (AE-GNN) may explain and diagnose multi-plant leaf disease.
Reproduction assets foundThe paper's Data availability section explicitly links a public GitHub repository containing the paper's spinach/curry leaf fungal disease image dataset used for the AE-GNN phenotyping/classification analysis.Dataset · publicData availability
The dataset is available at the link below. https://github.com/MeganathanE1990/FINAL-DISEASE-DATA-SET/tree/mainOpen asset ↗MeganathanE1990/FINAL-DISEASE-DATA-SETlines:413-463Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Abstract Agriculture is a highly dynamic area that sustains global food security, and crop health plays a critical role in obtaining agricultural output. Peanuts, commonly known as groundnuts, hold a significant value due to their nutritional importance and economic benefits in many regions. However, it faces numerous challenges due to its vulnerability to a range of diseases that have a severe impact on both quality and yield. Disease detection methods based on traditional techniques were time-consuming, vulnerable to human mistakes and Labor-intensive. To handle these issues, we suggest a cutting-edge technique for the detection of peanut diseases using deep learning models. In this research work, we initially proposed some pre-trained deep learning models such as EfficientNet-B0, EfficientNet-B4, and ConvNeXt-Base, but none of them produced state-of-the-art results. To address this challenge, we leveraged the ResNet-50 Architecture using transfer learning enriched with the combination of advanced methodologies such as Data augmentation, OneCycleLR Learning rate scheduler, and weighted loss. This approach dramatically boosted the performance across various metrics, demonstrating the strength of transfer learning to handle imbalanced data and refine generalization. Deep learning models were trained with 1720 publicly available images of the dataset. The dataset includes both healthy and diseased images of groundnut leaves, including Alternaria leaf spot, Rosette, Rust and Leaf spot (early and late). The dataset was partitioned into 80% training images, 10% test images, and 10% value accuracy images. Our proposed methodology outperformed on the same dataset and gave better results than the older ones on the same dataset. The earlier same dataset had an accuracy rate of 96.51%. Our experiments showed that the suggested technique achieved a 97.28% accuracy rate and outperformed the existing state-of-the-art models. Results from these experiments demonstrate the merit of the proposed model for application in real-world agricultural problems, establishing a new baseline for detecting groundnut leaf diseases and establishing the feasibility of AI-based solutions for enhancing transferable sustainable agricultural practices.
Why it matches plant phenotyping methods落花生葉の病徴を画像から分類する深層学習手法を開発・評価しており、植物の病害状態推定が研究の中心であるため含める。
abstractwe suggest a cutting-edge technique for the detection of peanut diseases using deep learning models.
Published1 Jun 20262026 International Conference on Data Science for Cyber-Physical Systems Resilience using Advanced Applications (ICDCA)Cited by 0 · OpenAlex ↗
Agriculture is an important sector for food production and economic growth. Plant diseases reduce crop quality and productivity, causing financial loss to farmers. This project proposes a Real-Time Plant Disease Detection System using Deep Learning techniques. Users can upload plant leaf images through a website, and the system analyzes the image using CNN and MobileNetV2 models to detect whether the leaf is healthy or diseased. The system provides fast and accurate disease prediction along with remedy suggestions for farmers. Keywords: Deep Learning, CNN, MobileNetV2, Plant Disease Detection, Machine Learning, Smart Agriculture.
Why it matches plant phenotyping methods葉画像から健康・罹病状態をCNN/MobileNetV2で推定する手法が研究の中心であり、植物病害状態の画像ベース表現型推定に該当する。
abstractThis project proposes a Real-Time Plant Disease Detection System using Deep Learning techniques.
Chili peppers (Capsicum annuum L.) are a strategic horticultural commodity in Indonesia, but their productivity is often hampered by pathogen infections that cause leaf diseases such as anthracnose, leaf spot, and yellow virus. Early detection by farmers is still dominated by subjective visual observation and prone to misdiagnosis due to the similarity of symptoms between diseases. Although Deep Learning technology through Convolutional Neural Networks (CNN) offers an automated solution, implementation in real-world conditions still faces significant challenges such as lighting variations, complex backgrounds, and limited local datasets. This often leads to a drastic decrease in model performance compared to testing in a controlled environment. To address these issues, this study proposes an optimization of the transfer learning strategy on the MobileNetV2 architecture by integrating progressive layer-wise fine-tuning and adaptive data augmentation techniques. The fine-tuning method is carried out gradually on the pre-trained model layers, while adaptive augmentation dynamically manipulates images based on environmental characteristics to improve model robustness. The results of this study, which include multi-class classification on cross-location image data, are projected to be able to boost the accuracy and generalization ability of the model in heterogeneous field conditions. Practically, this research provides a framework for a more precise and robust disease detection system to accelerate the implementation of precision agriculture in the future.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類するCNN手法の改良が研究の中心であり、病害状態の表現型推定に該当する。転移学習のファインチューニングと適応的画像拡張、異なる圃場条件での頑健性評価を扱っている。
abstractThe results of this study, which include multi-class classification on cross-location image data, are projected to be able to boost the accuracy and generalization ability of the model in heterogeneous field conditions.
Reproduction assets foundThe paper states its chili leaf image dataset was supplemented with data from a supporting repository, cited as a public Mendeley Data deposit (reference [2]). This is a public plant-image dataset directly used for the paper's disease-classification phenotyping. No authors' analysis code or trained model checkpoint is,Dataset · public[2] F. Wajidi and N. Arifin, “Deteksi Penyakit Daun Cabai Menggunakan Kombinasi GLCM dan HSV dengan
Klasifikasi SVM,” vol. 11, no. 02, 2025. [Online]. Available:
https://data.mendeley.com/datasets/w9mr3vf56s/1Open asset ↗w9mr3vf56s/1pdf-page:9 lines:1-56Code / dataset availability confirmedOpenAlex · arXiv · checked 15 Sept 2026
Accurate estimation of wheat spike volume is important for yield component analysis and stress resilience assessment, yet field-based measurement remains challenging. Active 3D sensing methods such as Light Detection and Ranging (LiDAR) or time-of-flight (ToF) are sensitive to plant motion or poorly suited to outdoor conditions, while 3D reconstructions are computationally expensive. Direct 2D image processing would offer computational advantages, but image-based models lack explicit geometric information. We therefore propose a hybrid 2D-3D approach with knowledge distillation during training while enabling efficient image-only inference. First, we train a rigid-invariant point cloud network using distance-based histogram features to obtain pose-robust geometric representations. We then combine the 3D model with a proposed multi-view image-based regulated Transformer (RT) in an ensemble architecture. Finally, we distill the ensemble knowledge into a purely image-based student model using either feature-based or label-based distillation. The two distilled RTs reduce the mean absolute error (MAE) from 654.31 mm$^3$ of the non-distilled RT to 639.93 mm$^3$ and 644.62 mm$^3$, and increase correlation from 0.76 to 0.77 and 0.82, respectively. At the same time, inference time is reduced from 160 ms to 1.4 ms per spike. Distillation further mitigates volume-dependent bias and reshapes the latent representation of the image model toward a geometry-aware shape. Our results demonstrate that 3D-informed training of a 2D Transformer allows for scalable and efficient spike volume estimation for high-throughput field phenotyping.
Why it matches plant phenotyping methods小麦穂の体積を画像・3D再構成・知識蒸留で推定する手法の開発と性能評価が中心であり、高スループット植物フェノタイピングへの応用も明示されている。
abstractWe therefore propose a hybrid 2D-3D approach with knowledge distillation during training while enabling efficient image-only inference.
Reproduction assets foundThe paper explicitly states that links to its wheat spike dataset (multi-view images and 3D scans) and its analysis code are available via the authors' project webpage, which is an allowed URL. Other URLs (pyrender, CORDIS projects) are generic libraries or unrelated funding projects, not paper-specific assets.Dataset · publictance of around 2.5 m with a ground sampling distance of 0.3 mm (Fig. S1 a). The tagged and imaged spikes (Fig. S1 b) were sampled and ground truth volumes were acquired with a 3D light scanner (Shining 3D Einscan-SE V2, SHINING3D, Hangzhou, China) following the protocol of [ 76 ] . Links to the dataset and code can be found at https://oliviazum.github.io/3DKD-wheat/ . Detailed information about the dataset can be found in Sec. A .
3.3 Data Pre-Processing
Field images contained approximately 300-500 spikes per genotype within a plot of about 1.5 m 2 m^{2} . To reduce background inference, spike detection was first performed, and all subsequent processing was restricted to the detected regioOpen asset ↗lines:91-104Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
To achieve efficient crop management, exact plant disease detection in leaves is required. This study proposes DeMoHybridNet (Bottleneck Reduction Fusion) for the automated classification of Corn, Apple, Citrus, and Mango crop diseases. Input images are processed through augmentation and resizing, and then features are learned using DenseNet-201 and MobileNetV2. Global Average Pooling is applied, which produces condensed features. The features are then compressed using bottleneck layers of 512 features. The features are concatenated and classified by Random Forest (RF) classifier. To further improve the performance, a hybrid meta-heuristic method called IGWO-DOA (Improved Grey Wolf Optimization-Dingo Optimization Algorithm) is used to optimize the hyperparameters of the model for better convergence and generalization. The proposed optimized model gives the classification accuracy is 98.56% for Corn, 98.99% for Apple, 97.83% for Citrus and 99.35% for Mango leaf dataset. Statistical analysis confirms its robustness and reliability, demonstrating its effectiveness for precision agriculture applications.
Why it matches plant phenotyping methods葉画像から植物の病害状態を自動分類する深層学習・特徴抽出・分類ワークフローが研究の中心であり、植物病害表現型の画像ベース推定手法に該当する。
abstractThis study proposes DeMoHybridNet (Bottleneck Reduction Fusion) for the automated classification of Corn, Apple, Citrus, and Mango crop diseases.
Abstract Timely and accurate plant disease detection is important for enhancing agricultural productivity and promoting sustainability. The study introduces Multimodal Adaptive Fuzzy-based Deep Neural Network (MAF-DNN) for classification of plant diseases. The proposed method combines fuzzy logic with multimodal data fusion to effectively address the complex interactions and uncertainties in agricultural datasets. The MAF-DNN employs a robust adaptive fuzzy framework with dynamic rule optimization and integrates Hyperspectral Imaging Data (HID) with RGB imaging data to acquire detailed spectral information and high-resolution visual cues for disease classification. The multimodal fusion enhances the model’s ability to capture intricate patterns that relate to plant health, improving the accuracy of disease classification. The experimental results showed that the MAF-DNN outperforms traditional models by achieving an accuracy of 97.8%, precision of 96.5%, recall of 98.2%, and F1-score of 97.3%. Additionally, the adaptive design reduces computational overhead, increases efficiency, and improves scalability for large-scale agricultural applications. The MAF-DNN represents a significant advancement in plant disease classification and provides a robust and efficient solution for precision agriculture.
Why it matches plant phenotyping methods植物病徴を画像から分類するマルチモーダル画像・深層学習手法の開発と性能評価が中心であり、植物の病害状態を直接推定するため。
abstractThe study introduces Multimodal Adaptive Fuzzy-based Deep Neural Network (MAF-DNN) for classification of plant diseases.
Reproduction assets foundThe paper uses two public Kaggle plant disease image datasets (New Plant Diseases Dataset and CCMT Plant Disease Dataset) as its phenotyping inputs and states that the authors' custom MAF-DNN code is publicly available on GitHub, with all three URLs given in the article and matching allowed URLs.Code · publicThe custom code used to develop and evaluate the proposed Multimodal Adaptive Fuzzy Deep Neural Network (MAF-DNN) framework is publicly available at: https://github.com/skbsangeetha/MAF-DNN-Plant-disease-classificationOpen asset ↗skbsangeetha/MAF-DNN-Plant-disease-classificationhtml-lines:102-118Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published13 May 2026Indonesian Journal of Electronics, Electromedical Engineering, and Medical InformaticsCited by 0 · OpenAlex ↗
Rice diseases such as leaf blight, blast, and brown spot remain major constraints on food security and rural livelihoods across Southeast Asia, causing significant yield losses each year. In Indonesia, particularly in Lamongan, East Java, these pathogens threaten smallholder productivity and disrupt national rice supply chains. This study aims to enhance automated rice disease detection under real agricultural conditions by integrating image preprocessing techniques with a deep learning-based detection framework. The main contribution lies in developing a hybrid pipeline that combines RGB-to-grayscale conversion and contrast stretching prior to model training, effectively mitigating low-contrast conditions and noise commonly found in field-acquired image datasets. The enhanced images are subsequently processed using the Faster Region-Based Convolutional Neural Network (Faster R-CNN) with a ResNet-50 backbone to localize and classify disease symptoms. Experiments conducted on a dataset of 1,500 annotated rice leaf images achieved high detection performance, with accuracies of 97.37% for leaf blight, 94.12% for blast, and 95.24% for brown spot. Compared with the baseline Faster R-CNN model, the proposed approach improved classification accuracy from 0.8906 to 0.9297, reduced false negatives from 0.439 to 0.1998, increased foreground classification accuracy from 0.55 to 0.78, and descreased total loss from 0.839 to 0.6493. These results demonstrate that integrating RGB-to-grayscale conversion and contrast stretching significantly enhances feature representation, leading to improved detection accuracy, reduced error rates, and more stable training behavior. Overall, the proposed framework provides a robust and reliable approach for rice disease identification and offers strong potential for practical deployment in precision agriculture systems.
Why it matches plant phenotyping methodsイネ葉の病徴を画像から検出・分類する画像前処理とFaster R-CNNの統合手法を開発し、性能比較・検証しているため、植物表現型取得が中心である。
abstractThe main contribution lies in developing a hybrid pipeline that combines RGB-to-grayscale conversion and contrast stretching prior to model training
Given the global importance of wheat cultivation in the agricultural landscape, the practicality of the tetrazolium test in post-harvest management of seed lots, and the significant increase in the use of technologies in agriculture, this work aimed to evaluate predictive models for high-efficiency phenotyping and classification of the viability of different commercial wheat cultivars using the tetrazolium test. The predictive models proved accurate in estimating the viability of the 50 seed lots, reaching over 90% viable seeds, depending on the wheat cultivar. The recommended tetrazolium salt solution concentrations were 0.125% for the BRS 264 cultivar, 0.1% for MGS Brilhante and BRS 404, and 0.075% for TBIO DUQUE and BRS 394, with a pre-conditioning period of 9 h, regardless of the cultivar. Correlations between the percentage of viable seeds obtained by the tetrazolium test and physiological vigor variables were statistically significant, serving to validate each chosen predictive model, as well as to rank the seed lots by cultivar. Through computational phenotyping of over 10,000 seed images, and subsequently, individual digital analyses of the respective embryonic tissues, the cultivars BRS 264, TBIO DUQUE, and BRS 404 were classified into four viability classes, and MGS Brilhante and BRS 394 into three classes. Therefore, predictive models, specific to each cultivar, associated with the tetrazolium test and image analysis resources, represent significant advances for decision-making regarding the implementation or post-harvest management of wheat crops, especially cultivars planted under different climates and regions.
Why it matches plant phenotyping methods小麦種子画像とテトラゾリウム試験を用いて、生存性を推定・分類する予測モデルを開発し、相関で検証しており、植物表現型取得・抽出法が研究の中心である。
abstractthis work aimed to evaluate predictive models for high-efficiency phenotyping and classification of the viability of different commercial wheat cultivars using the tetrazolium test.
In this paper, we introduce two-way weighted feature pyramid and convolutional block attention mechanism based on the single-stage target detection framework to enhance multi-scale feature fusion and highlight the lesion-related response. The experiment adopted the configuration of batch size of 8 and a total of 50 rounds of training, and carried out training and evaluation on the data division containing 1136 training images and 211 validation images. The validation set contained 769 labeled instances and covered more than ten types of pests and diseases. During the training process, the loss of bounding box, classification and distribution focus decreased overall, while the accuracy rate, recall rate and mAP index of validation set increased or fluctuated with the training progress. Ablation experiments show that adding attention module and feature pyramid structure to the baseline model can bring accuracy benefit, and the combination of the two can achieve better detection performance. At the same time, the number of parameters and calculation overhead increase, and the inference speed decrease slightly. The results show that the proposed improvement is beneficial to disease localization and identification in complex background and small target scenarios, and can provide a reference for visual monitoring in smart agriculture.
Why it matches plant phenotyping methods植物葉の病斑を画像から検出・局在化し、改良YOLOv8の性能を学習・検証しているため、植物病害状態の画像ベース表現型推定法が中心です。
abstractwe introduce two-way weighted feature pyramid and convolutional block attention mechanism based on the single-stage target detection framework to enhance multi-scale feature fusion and highlight the lesion-related response.
Field / plotLeafStress / disease detectionDisease symptoms / severity
Mustard [Brassica juncea (L.) Czern.] is an essential crop in agriculture, but its yield is often restricted by different kind of diseases, affecting both farmers and the edible oil industry. Recent advancements in artificial intelligence have transformed plant disease detection by enabling precise identification of various diseases. However, their detection and management become more challenging when crops are affected by multiple co-occurring diseases. To address this challenge, present study was carried out to implement deep learning algorithm for precise detection of co-occurring disease in mustard crop. A dataset consisting of 329 diseased leaf images of mustard crop with co-occurring symptoms of Alternaria blight and white rust diseases were collected during the 2023–2024 from the experimental fields of ICAR-Indian Agricultural Research Institute, New Delhi. Dataset processed through annotation and augmentation to boost detection accuracy of the network. A YOLO-based detection model (YOLOv11 and its variants) was trainedand validated. Their performance was evaluated using the test dataset. Among the YOLOv11 variants, YOLOv11-x showed the highest performance by achieving mAP @50 score of 96.2% with average F1-score of 93.8% on validation data, performing 4.8% relatively better than the least complex model (YOLOv11-n), highlighting its superior detection capability. Furthermore, YOLOv11-x also surpassed previous YOLO models (YOLOv8, YOLOv9, and YOLOv10) in detection accuracy. The experimental results demonstrated the effectiveness of YOLOv11 for co-occurring disease detection in mustard crops.
Why it matches plant phenotyping methodsマスタード葉の共発生病害という植物状態を画像から検出するYOLOモデルを開発・検証しており、表現型取得手法が中心的です。
abstractpresent study was carried out to implement deep learning algorithm for precise detection of co-occurring disease in mustard crop.
Field / plotClassificationStress / disease detectionDisease symptoms / severity
Plant disease diagnosis in field settings is challenged by subtle symptomology, high inter-class visual similarity, and class imbalance, making automated detection particularly difficult. While deep learning models achieve high accuracy, traditional architectures impose prohibitive computational costs that hinder deployment on resource-constrained hardware. This paper proposes a novel Reduced Order Modelling (ROM) framework integrating a YOLOv8m backbone for spatially sensitive feature extraction, PCA-based compression to isolate the most discriminative features, and classical classification. A treatment-based label engineering approach was applied to consolidate the PlantWildV2 dataset from 115 to 11 agronomically relevant classes. Experimental results showed that a highly compressed feature space acts as a natural regularizer, with accuracy peaking at 100 principal components and declining beyond that threshold. The tuned SVC classifier achieved a test accuracy of 87.52% and a macro F1-score of 0.882, outperforming all other classifiers evaluated. The proposed ROM framework surpassed EfficientNet-B0 in accuracy (87.52% vs. 82.50%) while reducing training time from 5.8 hours on GPU to 30.8 seconds on CPU, a 670-fold efficiency gain, demonstrating the viability of Reduced Order Modelling for plant disease detection on low-resource hardware.
Why it matches plant phenotyping methods植物画像から病害状態を推定する分類手法の開発が研究の中心であり、圧縮特徴抽出・分類器・計算効率を評価しているため、植物フェノタイピング手法として採用。
abstractThis paper proposes a novel Reduced Order Modelling (ROM) framework integrating a YOLOv8m backbone for spatially sensitive feature extraction, PCA-based compression to isolate the most discriminative features, and classical classification.
Early diagnosis of plant leaf diseases plays an important role in protecting crop yields and supporting sustainable agriculture. This paper proposes an improved DeepFusionNet model optimized through a hybrid Flower Pollination Algorithm and Butterfly Optimization Algorithm, balancing global exploration with local refinement for faster and more stable convergence. The model combines DenseNet201 and MobileNetV2 by compressing their final convolutional feature maps with 1×1 convolutions and fusing them along the channel dimension to form a compact and discriminative representation. This fused representation is then classified using a Random Forest classifier. This framework consistently achieves high accuracy on all eight datasets, with performance ranging between 97.07% and 99.66%. Extensive experiments are performed that include statistical validation, convergence studies, and reliability tests to prove the robustness of the approach. Furthermore, to make it practically useful, the whole system is embedded into a mobile application capable of real-time disease detection and providing actionable recommendations to farmers for the effective treatment and prevention of diseases.
Why it matches plant phenotyping methods植物葉の病徴を画像から診断する深層学習手法の開発・検証が中心であり、植物の病害状態を直接推定する画像ベース表現型解析に該当する。
abstractThis paper proposes an improved DeepFusionNet model optimized through a hybrid Flower Pollination Algorithm and Butterfly Optimization Algorithm
Sugarcane is a high-value industrial crop vital for sugar and biofuel production, yet increasingly constrained by climate variability, biotic and abiotic stresses, soil degradation, and inefficient input use. Traditional breeding and crop management approaches are often slow, labour-intensive, and less precise, emphasizing the need for digital transformation in sugarcane agriculture. AI now offers powerful tools to accelerate genetic improvement, enhance stress resilience, and optimize resource-use efficiency. This review synthesizes recent advances in AI applications across the sugarcane improvement pipeline, including high-throughput phenotyping, genomic prediction, digital crop monitoring, and AI-driven decision-support systems. ML and DL models enable automated, accurate prediction of key traits such as biomass, canopy temperature, nitrogen status, and sugar recovery using UAV, satellite, and proximal sensing data. AI-powered genomic selection approaches leveraging convolutional networks, transformers, and attention mechanisms improve prediction accuracy for yield, ratooning ability, and stress tolerance by integrating SNPs, pedigree, and multi-environment datasets. Emerging innovations such as digital twins, multimodal data fusion, reinforcement learning-based irrigation scheduling, and climate-smart advisory models further strengthen real-time crop intelligence. The integration of blockchain-enabled breeding databases, FAIR data standards, and interoperable analytics pipelines supports scalable and collaborative research. Literature analysis reveals 15-30% gains in selection efficiency, >90% accuracy in disease detection, and phenotyping cost reductions of up to 70%. Key challenges remain, including scarce annotated datasets, genotype × environment complexity, model interpretability, and adoption barriers for smallholders. A future roadmap is proposed featuring multimodal foundation models, edge-AI deployment, and explainable breeder dashboards. AI is redefining sugarcane research from reactive to predictive, enabling climate-resilient, sustainable, and profitable production systems.
Why it matches plant phenotyping methodsサトウキビ育種におけるAI応用の総説であり、高スループット表現型解析、UAV・衛星・近接センシングによる形質推定を主要な対象として扱っているため、フェノタイピング手法レビューとして適格。
abstractThis review synthesizes recent advances in AI applications across the sugarcane improvement pipeline, including high-throughput phenotyping, genomic prediction, digital crop monitoring, and AI-driven decision-support systems.
This paper addresses the problem of automated segmentation of plant green biomass in field crop images aimed at improving the accuracy of crop and weed identification. To construct a training dataset for neural network models, an automatic annotation algorithm is proposed, enabling the generation of polygonal object masks without human intervention. The method is based on adaptive analysis of color characteristics of plant fragments with iterative narrowing of the hue range in the HSV color space, combined with an integral quality metric that accounts for the dynamics of contour area and shape. The proposed method achieved an IoU of 93.22% and a DSC of 96.30%, demonstrating a high level of agreement between automatic and manual annotations. The generated masks are used to train segmentation models of the YOLO11-seg family. Models of different scales (n, s, m, l, x) were trained and evaluated using standard metrics, including Intersection over Union (IoU), mAP@0.5, mAP@0.5–0.95, F1-score, and Precision–Recall (PR) curves. Experimental results demonstrate that models trained on automatically generated annotations achieve stable segmentation performance of plant green biomass. The best results were obtained with the YOLO11m-seg model, achieving an F1-score of 0. 772. The results confirm the effectiveness of the proposed approach and demonstrate acceptable segmentation quality, supported by both quantitative metrics and visual analysis. The developed automatic annotation algorithm can be used to expand training datasets in computer vision tasks for agricultural applications.
Why it matches plant phenotyping methods植物の緑色バイオマスを画像から自動抽出するポリゴン注釈法を開発し、手動注釈との一致度で検証しているため、植物表現型取得・抽出法が中心である。
abstractan automatic annotation algorithm is proposed, enabling the generation of polygonal object masks without human intervention
Reproduction assets foundThe authors publicly released the paper-specific generated dataset of polygonal segmentation annotations (masks and supporting materials) on Hugging Face. CVAT is only a generic annotation tool, and no author analysis code or trained model checkpoints are explicitly deposited.Dataset · publicThe generated dataset with polygonal segmentation annotations of crop and weed plants, produced using the proposed algorithm and based on the LincolnBeet Dataset, is publicly available on Hugging Face at: https://huggingface.co/datasets/ivliev123/polygonal_marking_plant_objectsOpen asset ↗Hugging Face · ivliev123/polygonal_marking_plant_objectshtml-lines:438-462Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Introduction Early detection of plant diseases is essential for maintaining crop health and ensuring sustainable agricultural productivity. Guava fruit and leaf diseases, if not identified at an early stage, can lead to significant yield losses. Recent advances in deep learning offer promising solutions; however, challenges remain in achieving both high accuracy and model interpretability for practical agricultural deployment. Methods This study proposes an explainable deep learning-based framework for the classification of guava fruit and leaf diseases. A real-world dataset consisting of 527 annotated images across five classes-Disease Free, Phytophthora, Red Rust, Scab, and Styler and Root Rot-was utilized. Six hybrid model architectures were developed by integrating transfer learning backbones (VGG16, MobileNetV2, InceptionV3, and ResNet50) with custom convolutional neural network (CNN) classifiers. Model performance was evaluated using accuracy, precision, recall, F1-score, and class-wise metrics. To enhance transparency, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize disease-relevant regions. Results Among all evaluated models, the proposed VGG16 + MobileNetV2 hybrid architecture achieved the best performance, attaining an accuracy of 96%, an F1-score of 0.96, and strong generalization across all disease classes. Comparative analyses using confusion matrices, ROC-AUC curves, precision-recall curves, and radar plots confirmed the superior and consistent performance of the proposed model over other hybrid configurations. Discussion The results demonstrate that combining deep feature extractors with lightweight architectures enhances both classification accuracy and computational efficiency. The integration of Grad-CAM provides meaningful visual explanations, increasing trust and interpretability in AI-assisted disease diagnosis. This framework shows strong potential for deployment in real-time smart farming systems and mobile-based diagnostic applications, particularly in resource-constrained agricultural environments.
Why it matches plant phenotyping methodsグアバの葉・果実画像から病害状態を推定する深層学習手法が研究の中心であり、複数モデルの比較評価とGrad-CAMによる説明可能性検証も行っているため、植物フェノタイピング方法論として採用する。
abstractThis study proposes an explainable deep learning-based framework for the classification of guava fruit and leaf diseases.
Reproduction assets foundThe paper's plant image dataset (527 annotated guava fruit/leaf disease images) is a public Kaggle deposit explicitly cited by the authors with a URL, making it a paper-specific, publicly actionable asset. No author analysis code or trained model checkpoints are stated as publicly available; the data availability only指Dataset · publicKaggle ). Available online at: https://www.kaggle.com/datasets/noamaanabdulazeem/guava-dataset (Accessed January 10, 2024 ).Open asset ↗Kagglelines:550-617Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
ABSTRACT Smart agriculture based on the use of Artificial Intelligence for crop disease detection to ensure food security. Fungal disease is one of the major causes that affects the quality of the vegetables. Convolutional neural networks (CNNs) and vision transformers (ViTs) enable the detection of crop diseases at an early stage, allowing farmers to take preventive measures and minimize further losses. The proposed method introduces an ensemble of Custom CNN to understand multilevel local features and Pretrained ViT to capture global dependencies as well as contextual information from the dataset. An interactive cross attention module (ICAM) facilitates bidirectional information exchange between CNN and transformer token representations, while an attention guided gated fusion (AGGF) mechanism adaptively combines complementary features. The Indian Crop Visual Disease Dataset (ICVDD‐5) has been developed in a real field for the proposed work with the help of domain experts. The dataset contains 880 diverse images depicting both healthy and diseased specimens of five vegetable crops. The crops selected for this research initiative include Brinjal, Cabbage, Chili, Okra, and Tomato. These five crops are examined for about 21 distinct disease classes. Comprehensive ablation studies are conducted to prove the contributions of each architectural component, including CNN‐only, ICAM‐disabled, and AGGF‐disabled configurations. Experimental results demonstrate that the proposed ICAG‐Net achieves a test accuracy of approximately 70%–73% with improved macro‐F1 score compared to baseline CNN models under identical training settings. The novelty of this work lies in an extensible solution for real world crop disease diagnosis systems and offers insights into hybrid CNN–transformer architectures for small scale agricultural datasets.
Why it matches plant phenotyping methodsCNN・Transformerによる植物病害症状の画像検出手法を開発し、実圃場画像データセットの構築、アブレーション、ベースライン比較で性能検証しているため、植物フェノタイピング手法が中心である。
abstractThe proposed method introduces an ensemble of Custom CNN to understand multilevel local features and Pretrained ViT to capture global dependencies as well as contextual information from the dataset.
Abstract Fungal diseases in crops represent a severe agricultural threat requiring fast and accurate automated diagnosis. This study presents an enhanced deep learning system that employs a Hybrid Convolutional Neural Network (Hybrid CNN) for classifying crop leaf images as Healthy or Infected, implemented in MATLAB. Unlike single-branch CNN architectures, the proposed HybridLeafNet combines two parallel convolutional branches operating simultaneously with different receptive field sizes — a 3×3 branch capturing fine-grained local texture patterns and a 5×5 branch capturing broader spatial disease features — whose outputs are concatenated and processed through deeper fully connected layers. The system retains the original preprocessing pipeline including resizing to 256×256, per-channel median filtering, and contrast enhancement. Training is conducted using the Adam optimizer over 100 epochs with shuffling at every epoch to prevent overfitting and improve generalization. The model additionally integrates audio feedback, playing a distinct audio cue upon classification to support non-visual user interaction. Performance evaluation employs a comprehensive set of metrics including accuracy, precision, recall, F1-score, specificity, and AUC derived from the confusion matrix. The multi-scale feature fusion strategy of HybridLeafNet significantly improves discriminative capability over single-path CNNs, yielding higher accuracy in distinguishing subtle fungal infection patterns across diverse crop leaf images. Keywords: Hybrid CNN, Fungal Disease Detection, Multi-Scale Feature Extraction, Crop Classification, Deep Learning.
Why it matches plant phenotyping methods作物葉画像から感染状態を推定する画像ベース植物フェノタイピング手法を開発・評価しており、分類モデルが研究の中心である。
abstractThis study presents an enhanced deep learning system that employs a Hybrid Convolutional Neural Network (Hybrid CNN) for classifying crop leaf images as Healthy or Infected
Recent advancements in domain-specific classification methods have demonstrated the remarkable performance of deep learning in comparison to traditional machine learning techniques. This study develops a computationally efficient Convolutional Neural Network (CNN) model tailored for citrus plant disease classification, achieving performance comparable to that of the pretrained InceptionV3 model. A custom five-layer CNN model is constructed to classify citrus plant diseases into healthy and diseased categories using images collected from citrus orchards in Northen India. The model has been further validated using images sourced from GitHub and the Kaggle database. The proposed method surpasses classical machine learning approaches in accuracy and computational efficiency, achieving classification accuracies of 92.59%. The training time of the proposed CNN AgriVision-L5 is reduced by 50%, respectively, compared to the InceptionV3 model, demonstrating their computational efficiency. The proposed methodology offers significant advancements in plant disease management and sustainable agriculture, aligning with Sustainable Development Goals like SDG2, SDG9, and SDG12.
Why it matches plant phenotyping methods柑橘病害を画像から分類するCNNを開発し、外部画像で検証しており、植物の病害状態を推定する方法が研究の中心です。
abstractThis study develops a computationally efficient Convolutional Neural Network (CNN) model tailored for citrus plant disease classification
Abstract- Plant diseases pose a serious threat to global food security by reducing crop yield and quality. To improve detection, a multi-modal diagnostic framework is proposed that combines Vision Transformers (ViTs) for image-based disease classification with Natural Language Processing (NLP) for symptom description and treatment recommendations. The system supports multilingual interaction and generates automatic disease reports, making it accessible to diverse farming communities. By integrating ViT and NLP, the model offers higher diagnostic accuracy and interpretable, farmer-friendly support. Designed for real-world use, it can be deployed on mobile and IoT platforms, enabling smart, interactive decision-making in precision agriculture. Keywords: Plant Disease Detection, Vision Transformers, NLP, Multi-Modal Learning, Precision Agriculture.
Why it matches plant phenotyping methods植物画像から病害を分類するマルチモーダル診断手法が研究の中心であり、植物の病害状態を直接推定するため、フェノタイピング手法として採用する。
abstracta multi-modal diagnostic framework is proposed that combines Vision Transformers (ViTs) for image-based disease classification
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Introduction Reliable identification of plant diseases from leaf images is essential for effective crop monitoring and the prevention of yield deterioration. With the growing adoption of deep learning in agricultural applications, convolutional neural network–based classifiers have demonstrated notable success in visual plant disease recognition. Methods In this study, we propose PlantPathNet , a purpose-built deep learning architecture for plant disease classification. Input images are transformed from the RGB to the HSV color space to enhance the representation of disease-related visual features. A novel Cross-layer Feature Integration Module (CFIM) is introduced to effectively aggregate discriminative features across multiple network depths. Additionally, an efficient channel attention mechanism based on ECANet is incorporated to emphasize disease-relevant representations. The model is optimized using a composite loss function combining modified softmax loss and center loss to address class imbalance and improve feature separability. Results Extensive experiments conducted on the PlantVillage dataset demonstrate that PlantPathNet outperforms several state-of-the-art models, including ResNet-50, Inception-V3, DenseNet121, VGG16, and Vision Transformer-based approaches. The proposed model achieves an overall accuracy of 99.57%, precision of 99.52%, recall of 99.54%, F1-score of 99.53%, and an AUROC of 99.84%. Discussion The results indicate that the integration of HSV-based preprocessing, CFIM, and channel attention significantly enhances classification performance. The proposed framework provides a robust and efficient solution for automated plant disease diagnosis and has strong potential for real-world agricultural applications.
Why it matches plant phenotyping methods葉画像から植物病害状態を推定する深層学習手法を新規開発し、既存モデルとの比較検証も行っているため、植物フェノタイピング手法が中心である。
abstractwe propose PlantPathNet , a purpose-built deep learning architecture for plant disease classification.
Climate change, particularly increasing frequency and intensity of spring frost events, poses a serious threat to viticulture by reducing yield and product quality. This study proposes an image processing and machine learning-based framework for early, rapid, and accurate segmentation of frost damage in vineyards using YOLOv11s enhanced with Atrous Spatial Pyramid Pooling (ASPP). A unique dataset called FGVL dataset from Sultana seedless grape vineyards in Manisa, Türkiye, following a severe frost event in April 2025. FGVL includes 418 frost-damaged grapes, 510 frost-damaged leaves, 395 healthy grapes, and 698 healthy leaves, all manually annotated by experts under natural field conditions. By integrating ASPP into YOLOv11s, proposed model improved multi-scale contextual feature extraction and achieved mAP@50 of 0.7686, demonstrating stronger performance in instance segmentation of small, overlapping, and visually similar grapevine organs. In addition, Dynamic Confidence Thresholding (DCT) strategy was introduced to improve prediction reliability in dense and visually complex vineyard scenes. Despite challenges such as background clutter, object overlap, and small target structures, model maintained stable performance with low computational demand, requiring only 6.45 GB of GPU memory. Proposed framework offers an accurate, efficient, and practically deployable early recognition system for frost damage assessment in viticulture.
Why it matches plant phenotyping methodsブドウの器官における霜害状態を画像からセグメンテーションする手法を開発・評価しており、植物の病害・障害状態の取得が研究の中心である。
abstractThis study proposes an image processing and machine learning-based framework for early, rapid, and accurate segmentation of frost damage in vineyards using YOLOv11s enhanced with Atrous Spatial Pyramid Pooling (ASPP).
Reproduction assets foundThe paper's Data availability statement explicitly shares the FGVL frost-damage dataset and source code in the corresponding author's public GitHub repository, matching an allowed URL.Code · publicSource code and dataset are publicly shared in GitHub repository of corresponding author. GitHub repo: https://github.com/kaanarikk/Grape-Instance-Segmentation-For-ViticultureOpen asset ↗https://github.com/kaanarikk/Grape-Instance-Segmentation-For-Viticulturelines:230-236Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Plant diseases pose significant challenges to global agricultural productivity, requiring early and accurate detection to mitigate their impact. This study introduces a Vision Transformer (ViT)-based framework for classifying apple leaf diseases, utilizing a novel multi-patch selection approach to strike a balance between feature extraction and computational efficiency. Leaf images were preprocessed to ensure compatibility with the ViT framework and divided into patches of varying sizes (32 × 32, 16 × 16, and 8 × 8), enabling the model to capture both local and global features for classifying four categories: Apple Scab, Black Rot, Cedar Rust, and Healthy Leaves. The proposed Plant Leaf Disease Vision Transformer (PLD-ViT) framework achieves superior classification performance with 97.76% validation accuracy, 95.34% precision, 95.11% recall, and 95.06% F1-score using 16 × 16 patch configuration, significantly outperforming ResNet-50 (96.75% validation accuracy, 95.11% precision, 93.42% recall, 95.31% F1-score) and Swin Transformer (96.79% validation accuracy, 95.76% precision, 95.94% recall, 95.89% F1-score) while maintaining computational efficiency (1.0× GFLOPs vs 3.8× and 4.5× respectively). The model robustly classifies distinct categories but faces challenges distinguishing visually similar groups, such as Cedar Rust and Healthy Leaves. Despite its strengths, the model has limitations, including its reliance on controlled datasets and the computational demands associated with smaller patch sizes. This ViT-based framework offers a practical and scalable solution for precision agriculture, laying the groundwork for accessible tools that support sustainable farming practices and promote global food security.
Why it matches plant phenotyping methods植物葉の病害状態を画像から分類するViTベース手法を開発し、複数モデルとの性能比較・検証を行っており、病害表現型の取得・推定が研究の中心である。
abstractThis study introduces a Vision Transformer (ViT)-based framework for classifying apple leaf diseases, utilizing a novel multi-patch selection approach
Determining the optimal harvest time is among the most critical economic decisions for peanut ( Arachis hypogaea L.) growers, directly influencing yield, quality, and market value. Unlike many other crops, peanuts are indeterminate, continuing to flower and produce pods throughout their life cycle. As a result, pod development and maturation are asynchronous, making harvest timing particularly challenging. Conventional maturity estimation techniques, including the hull scrape method, pod blasting, and visual maturity profiling, are invasive, labor-intensive, time-consuming, and spatially limited. Moreover, differences in cultivar maturity rates and agroclimatic conditions exacerbate inconsistencies in maturity prediction. These challenges highlight the urgent need for scalable, objective, and data-driven methods to support growers in achieving optimal harvest outcomes. This review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation. It aims to identify the limitations of conventional techniques and explore the integration of advanced sensing technologies, artificial intelligence (AI), and geospatial analytics to enhance precision and scalability in peanut maturity assessment and harvest decision-making. This review examines traditional destructive techniques such as the hull scrape method and pod blasting, followed by emerging non-invasive methods employing proximal and remote sensing platforms. Applications of vegetation indices, multispectral and hyperspectral imaging, and AI-based data analytics are discussed in the context of maturity prediction. Additionally, the potential of multimodal remote sensing data fusion and digital frameworks integrating spatial big data analytics, centralized data management, and cloud-based graphical interfaces is explored as a pathway toward end-to-end decision-support systems. Recent advances in non-invasive sensing and AI-assisted modeling have demonstrated significant improvements in scalability, precision, and automation compared with traditional manual approaches. However, their effectiveness remains constrained by the limited inclusion of agroclimatic, phenological, and cultivar-specific variables. Furthermore, the translation of model outputs into actionable, field-level harvest decisions is still underdeveloped, underscoring the need for integrated, user-centric digital infrastructure. Achieving a robust and transferable digital peanut maturity estimation system will require comprehensive ground-truth data across cultivars, regions, and growing seasons. Multidisciplinary collaborations among agronomists, data scientists, growers, and technology providers will be essential for developing practical, field-ready solutions. Integrating AI, multimodal sensing, and geospatial analytics holds immense potential to transform peanut maturity estimation. Such innovations promise to enhance harvest precision, economic returns, and sustainability while reducing manual effort and uncertainty, ultimately improving the efficiency and quality of life for peanut producers worldwide.
Why it matches plant phenotyping methodsピーナッツ莢の成熟度という植物状態を対象に、従来法と非侵襲センシング、画像解析、AIによる推定手法を体系的にレビューしており、フェノタイピング手法が中心である。
abstractThis review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation.
Abstract. The rapid advancement of smart agriculture has created a need for efficient and real-time monitoring systems to improve crop productivity and sustainability. This project presents a sensor- enabled portable device designed to monitor soil and plant health using Internet of Things and Machine Learning techniques. The system integrates sensors such as soil moisture and temperature sensors with a microcontroller to collect environmental data continuously. The collected data is processed and displayed on a user-friendly web dashboard, enabling farmers to make informed decisions regarding irrigation and crop management. Additionally, a Convolutional Neural Network (CNN) model is implemented for plant disease detection using leaf images, achieving high accuracy. The device is designed to be low-cost, portable, and easy to use, making it suitable for small and medium-scale farmers. Experimental results demonstrate reliable performance in monitoring soil conditions and detecting plant diseases. The proposed system contributes to precision agriculture by reducing resource wastage, improving crop health, and enhancing overall agricultural efficiency. Keywords: Plant Health, Machine Learning, Precision Agriculture, Plant Disease Detection, Smart Farming
Why it matches plant phenotyping methods葉画像による植物病害検出をCNNで実装した携帯型センシングシステムが研究の中心であり、植物状態の取得・判定手法を含むため。
abstractThis project presents a sensor- enabled portable device designed to monitor soil and plant health using Internet of Things and Machine Learning techniques.
Background: This review study examines the transformative potential of machine learning (ML) methods for real-time and continuous evaluation of legume crop development. It provides a structured and comprehensive synthesis of current ML applications, highlighting their potential to improve legume crop management in terms of accuracy, efficiency, scalability and sustainability. Unlike existing reviews, this study specifically emphasizes real-time monitoring frameworks that integrate multi-source data (satellite, UAV, IoT and sensors) for legume crops. Methods: Various machine learning methods, including supervised, unsupervised and deep learning paradigms, are reviewed with respect to their applications in crop health prediction, disease detection and yield estimation. The review further analyzes the integration of ML models with Internet of Things (IoT), edge computing and sensor-based systems to address challenges related to data quality, model interpretability, computational efficiency and real-time decision-making. Result: While challenges remain, such as data heterogeneity, limited model generalization and the integration of ML with traditional agronomic practices, recent technological advancements demonstrate promising solutions. Key trends include the development of robust and transferable models, improved human–machine interfaces and decision-support tools for farmers. These advances have the potential to enhance precision, resilience and sustainability in legume crop monitoring, thereby contributing to global food security and climate-smart agriculture.
Why it matches plant phenotyping methodsマメ科作物の生育・健康・病害・収量を対象に、機械学習と衛星・UAV・IoT・センサーを統合したモニタリング手法をレビューしており、植物形質・状態の取得および推定方法が中心である。
abstractThis review study examines the transformative potential of machine learning (ML) methods for real-time and continuous evaluation of legume crop development.
Abstract This paper presents a deep learning model to detect cotton plant pests and classify diseases, which must overcome limited datasets, class imbalance, and feature redundancy. At the preprocessing phase, the Gaussian blur filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to sharpen images by improving their clarity and contrast. To increase and diversify the data, Spa-GAN-based data augmentation is used to produce realistic synthetic samples. To obtain an accurate Region of Interest (RoI), an Attention-Guided Multi-Scale Residual U-Net (AGMS-UNet) is considered to segment local and global structural information. The proposed framework makes three major contributions: (i) a new attention-based feature extractor, TriAttnNet , that incorporates spatial, channel, and contextual attention to represent diseases on a fine-grained level; (ii) a new optimization strategy, Hybrid Mongoose Ray Chaotic Optimization (HMRCO), which includes chaotic strategies to better tune the parameters and explore the feature space; and (iii) classification layer with focal loss for final decision. Experimental analyses prove that the suggested method is much more effective than the current state-of-the-art models, providing a powerful and understandable solution to precision agriculture and sustainable cotton crop health monitoring. Experimental results show that TriAttnNet achieves 98.66% accuracy, 98.71% recall, and 98.81% F1-score, which is better than the state-of-the-art algorithms, such as EfficientNetB1-CBAM (96.38%) and BERT-ResNet-PSO (95.69%). The proposed system is computationally feasible and interpretable, and it is interpretable to provide a practical solution to precision agriculture and sustainable monitoring of the health of cotton crops.
Why it matches plant phenotyping methods綿植物の病害を画像から検出・分類する深層学習手法が研究の中心であり、植物の病害状態を直接推定して性能比較・検証しているため。
abstractThis paper presents a deep learning model to detect cotton plant pests and classify diseases
Reproduction assets foundThe paper's plant image input is the public Kaggle Cotton Plant Disease Dataset, explicitly cited with URL. Authors' code/models are only available upon request, so no public code asset qualifies.Dataset · publicThe dataset of this study is taken from the publicly available Kaggle repository, Cotton Plant Disease
Dataset [25].Open asset ↗Kagglepdf-page:6 lines:1-48Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published28 Mar 2026International Journal of Engineering & Extended Technologies ResearchCited by 5 · OpenAlex ↗
Indeed, precise and timely detection of diseases in plants is one of the most vital elements in maximizing crops to uphold global food security. Traditional methods are often time-consuming, subjective, and sometimes require expert knowledge. This project involves the use of a Deep Learning framework for automatic Field Plant Disease Detection and Classification, making use of the advanced YOLOv11 object detection model. Namely, YOLOv11 is utilized because of its superior balance of detection speed and accuracy in comparison with earlier models. This makes it ideal for real-time applications on the field. The plant image dataset is proposed to be collected, preprocessed, and annotated, involving different crops and common diseases in a large dataset. The YOLOv11 architecture is trained to simultaneously locate the disease regions (bounding boxes) on leaves, stems, or fruits and classify the specific type of disease. This may involve techniques for improving model robustness, such as data augmentation and transfer learning, which should enable better generalization across diverse environmental conditions. Such performances will then be checked using metrics such as Mean Average Precision and the speed of inferences: Frames Per Second. The system will be reliable, efficient, and scalable for farmers and agricultural experts. Implementation challenges include model size optimization for mobile deployment and continuous retraining on new disease strains, but the integration of YOLOv11 has great potential to revolutionize precision agriculture and smart farming by providing the ability for instantaneous disease management.
Why it matches plant phenotyping methods植物器官上の病変領域と病害種を画像から自動抽出・分類するYOLOv11手法の開発と性能評価が中心であり、植物病害状態のフェノタイピングに該当する。
abstractThis project involves the use of a Deep Learning framework for automatic Field Plant Disease Detection and Classification, making use of the advanced YOLOv11 object detection model.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
Bacterial grain rot (BGR), caused by Burkholderia glumae, is a major disease that reduces the yield of rice (Oryza sativa L.), thereby threatening food security. Conventional phenotypic analysis methods face limitations in objectively evaluating disease resistance and understanding the genetic basis. In this study, we integrated image-based phenotypic analysis with QTL mapping to screen for QTLs and candidate genes associated with B. glumae resistance. B. glumae was inoculated into 189 recombinant inbred lines (RILs) derived from Kele (resistant) and IS592BB (susceptible), followed by visualization and quantitative analysis using DAB staining. Phenotypic parameters, including the field resistance score, ratio of diseased spikelets (%), DAB staining intensity, and ratio of diseased area (%), were measured and used for QTL mapping. On chromosome 1, within Chr01_24592710-Chr01_37274755, four QTLs-qFRS1 [LOD: 5.98, phenotype variation explained (PVE): 15.41%], qRDS1 (LOD: 5.29, PVE: 18.56%), qQDS1 (LOD: 9.58, PVE: 22.02%), and qRDA1 (LOD: 8.44, PVE: 31.51%)-were identified as overlapping. After fine-mapping we narrow down Chr01_33472174-Chr01_33838140 and a total of 16 candidate genes were screened this region. Among which OsBGq1 was found to encode a nucleotide-binding LRR receptor (NLR) domain. OsBGq1 expression increased significantly upon B. glumae infection. Additionally, RILs Kele type of Chr01_33472174-Chr01_33838140 presented increased ROS-scavenging enzyme activity and phytoalexin accumulation upon B. glumae infection, contributing to increased resistance. The integration of DAB-based quantitative phenotyping with QTL mapping is proposed to provide a more objective indicator for identifying genes associated with resistance to BGR.
Why it matches plant phenotyping methodsイネ病害抵抗性の遺伝解析が主目的だが、DAB染色を用いた画像ベースの病徴定量化を主要な手法として統合し、客観的な抵抗性指標として提案しているため、表現型取得法の実質的応用に該当する。
abstractwe integrated image-based phenotypic analysis with QTL mapping to screen for QTLs and candidate genes associated with B. glumae resistance.
Identifying the detection of plant diseases remains a chronic menace in contemporary farm settings, with farmers unable to manage the economic downturns caused by the lack of resources and long periods of waiting to get expert agronomic advice. Current diagnostic methods are highly biased towards in depth visual examination by trained staff as well as laboratory pathology analysis thus posing a bottleneck in terms of lengthy turnaround times, high cost and impractical situation in real agricultural practice. This paper outlines a smartphone-based, bilingual diagnostic tool, which combines the concept of computational simplified deep learning systems with user-friendly interface structure and speech functionality. The developed tool uses a Convolutional Neural Network redesigned as a TensorFlow Lite system, which allows conducting analysis computations on a handheld device without the constant need to have an internet connection. The images of the leaves that are taken with the cameras of mobile devices are processed and evaluated with the taxonomic indicators to determine the indicators of plant wellness or identify particular forms of illness. The tool inserts crop-targeted classification systems and alters the classification outcome, involved on the basis of the specified botanical specimens. With reference to the accessibility requirements, the instrument has a dual-language feature, which can operate in English and Tamil, in addition to speech synthesis features, which audio-visually details the diagnostic conclusions to the end users. The architecture has been modified to maintain the stability of operations and consistency of the user experience over repeated interactions by including verification processes, historical analysis archiving, and capabilities of preserving data in disconnected modes. The tool separates the impermissible and appropriate photographic contributions, a non-infected situation on the plants, and pathology, consequently minimizing the instances of erroneous evaluation. Combining image-based analytical algorithms, cross-language inter-user interaction, as well as audio-based assists to make decisions, this mobile tool will be a grounded and farmer-centered technological solution. The model with a validation accuracy of 93.04 in the training phase and the deployment model with a validation accuracy of 92.27 and a mean inference time of 28.28 m/s validates the use of the model in real-time smartphone-based agriculture. The deployment strategy attests to the feasibility of deploying the state-of-the-art agricultural diagnostic equipment on cost-efficient mobile devices, progressing fast disease-detection schedules, minimizing the undue use of chemicals, and enhancing agricultural practices that are sustainable to the environment.
Why it matches plant phenotyping methods葉画像から植物の健全性・病害状態を推定するスマートフォン画像解析システムを開発し、精度と推論時間を検証しており、植物フェノタイピング手法が中心である。
abstractThe developed tool uses a Convolutional Neural Network redesigned as a TensorFlow Lite system, which allows conducting analysis computations on a handheld device without the constant need to have an internet connection.
In precision agriculture, crop disease detection can be a highly valuable undertaking in which scalable and correct solutions may save considerable amounts of money and loss of yield. This paper introduces a comparative analysis of state-of-the-art deep learning models with special attention to EfficientNetB3 hybrids, which are trained on a balanced subsample of the PlantVillage dataset with 33 classes based on nine crops. To overcome the shortcomings of the previous studies, which used unbalanced sample, a leakage-free balancing approach was used, resulting in 13,200 training and 3,300 validation samples. Custom head transfer learning was used where it was tested using two strategies; FreezeUnfreeze fine-tuning, and Singlephase training. MobileNetV2, InceptionV3, DenseNet121, GhostNet, in addition to other baseline CNNs, were compared to baseline Convolutional Neural Networks (CNNs). The findings indicate that EfficientNetB3 hybrids are superior with an accuracy of ≥99.5% and 99.9% Area Under the Curve (AUC) and specificity than the previous CNN-based systems. The paper logically defines a performance ladder between model options and real-life deployment demands, such as lightweight mobile applications to precision agriculture systems, and points out future trends in the field-based validation.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習モデルの比較・改良が研究の中心であり、植物病害表現型の取得・推定手法に該当する。
abstractThis paper introduces a comparative analysis of state-of-the-art deep learning models with special attention to EfficientNetB3 hybrids
Seed selection constitutes the initial and one of the most critical steps in agricultural productivity. The identification of high-quality seeds is a labor-intensive and costly process that requires considerable expertise. Within the scope of smart farming applications, this study proposes a deep learning–based model designed to automate the seed selection process by accurately predicting seed germination capacity from seed images. The proposed model determines whether a seed will germinate using RGB images and morphological traits automatically extracted from these images. The dataset used in this study comprises a total of 3,645 images belonging to three different seed types. For each seed type (okra, eggplant, and tomato), 405 seed images were acquired from three distinct imaging sources (digital microscope, camera, and scanner), labeled, and subsequently sown in seed trays. The germination status of each sown seed was systematically monitored and matched with its corresponding image data. The dataset was partitioned into 80% training and 20% testing subsets. Following 5-fold stratified cross-validation, the proposed model achieved an average weighted F1-score of 0.95 on the training set and 0.93 on the testing set for germination capacity prediction. The performance of the proposed model was further compared with widely used deep convolutional neural network architectures, including VGG19, ResNet50, and EfficientNetB5. Comparative results demonstrate that the proposed model provides competitive and robust performance for seed germination prediction. Overall, the findings indicate that the proposed approach can effectively be utilized for automated seed germination prediction. Future research should evaluate the generalizability of the model by conducting performance assessments on additional seed types.
Why it matches plant phenotyping methodsRGB画像から種子の形態形質を自動抽出し、発芽状態を予測する深層学習手法が研究の中心であるため、植物フェノタイピング手法として含める。
abstractthis study proposes a deep learning–based model designed to automate the seed selection process by accurately predicting seed germination capacity from seed images.
Rapid and accurate identification of DUS (Distinctness, Uniformity, and Stability) test traits in lettuce leaves is essential for advancing multi-omics-driven intelligent breeding. It also plays a critical role in germplasm protection and enhancing agricultural competitiveness. However, the phenotypic traits of lettuce leaves are highly diverse and complex due to both genotypic variation and environmental influences, posing significant challenges for precise DUS trait quantification. To address these challenges, we propose a high-precision phenotypic trait extraction pipeline and introduce an interpretable phenotypic fingerprinting framework for lettuce subgroup identification. First, a lightweight semantic segmentation network guided by group attention is developed to extract leaf components. Then, shape, color, and texture traits are comprehensively quantified. Following UPOV (International Union for the Protection of New Varieties of Plants) guidelines, we establish quantitative methods for seven DUS test traits: leaf shape, leaf tip shape, leaf margin shape, leaf vein shape, color hue, brightness, and anthocyanin coloration. Finally, PCA (Principal component analysis) was used to select 13 key traits, capturing over 95.82% of the total variance, for constructing "phenotypic ID" of lettuce varieties. Experiments conducted on 709 lettuce leaf image datasets showed that the accuracy of subgroup identification based on phenotypic fingerprints reached 98.59%. This study offers a scalable approach for automated DUS test trait evaluation and intelligent crop variety identification, providing a novel paradigm with strong potential for application in precision breeding and germplasm resource management.
Why it matches plant phenotyping methodsレタス葉画像からDUS形質を抽出・定量化する画像解析パイプラインを開発し、709画像で評価しており、植物フェノタイピング手法が研究の中心である。
abstractwe propose a high-precision phenotypic trait extraction pipeline and introduce an interpretable phenotypic fingerprinting framework for lettuce subgroup identification.
Reproduction assets foundThe article provides a public GitHub repository containing the authors' source code for the lettuce phenotypic fingerprint pipeline. The 709-image dataset and annotations are only available upon request, so they do not qualify as public assets.Code · publicThe data used to support the findings of this study are available upon request from the corresponding author, and the source code is accessible at https://github.com/qiuguangjie87/PP_Phenotypic_Fingerprint .Open asset ↗PP_Phenotypic_Fingerprintlines:263-278Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
This study addresses the challenge of automated high-throughput phenotyping of wheat spike characteristics using modern computer vision and deep learning methods. Accurate estimation of spikelet number is a key indicator of plant productivity, yet traditional manual counting approaches are labor-intensive, slow, and difficult to scale to large breeding datasets. To overcome these limitations, we propose a spikelet detection strategy based on simplified point annotations, where an expert marks only the centers of spikelets rather than drawing detailed segmentation masks or bounding boxes. This significantly reduces annotation time and lowers the overall cost of preparing training datasets for machine learning models. To determine the most effective way of utilizing such simplified annotations, three computational methods were explored: segmentation of binary masks using a U-Net architecture, density regression based on two-dimensional Gaussian distributions optimized via Kullback-Leibler divergence, and detection of fixed-size bounding regions using the YOLOv8 object detection framework. The models were evaluated on dedicated test datasets using both quantitative metrics (MAE, MAPE) and spatial localization metrics (Precision, Recall, F1 score). The results demonstrate that U-Net-based approaches provide consistently high accuracy in spikelet localization and counting while maintaining robustness to annotation imperfections. In contrast, the YOLOv8-based method showed reduced performance, likely due to the geometric mismatch between fixed-size boxes and the natural elongated shape of spikelets. Overall, the proposed methodology highlights the effectiveness of combining minimalistic point-level annotation with advanced segmentation models for automating phenotyping workflows. This approach has the potential to accelerate breeding programs, enhance the efficiency of large-scale phenotypic data collection, and support further development of robust computer-vision tools for plant science applications.
Why it matches plant phenotyping methodsコムギの穂の小穂数をRGB画像から自動推定する画像解析・深層学習手法を開発し、複数モデルを定量評価しており、フェノタイピング手法が研究の中心である。
abstractThis study addresses the challenge of automated high-throughput phenotyping of wheat spike characteristics using modern computer vision and deep learning methods.
Crop diseases represent one of the most significant threats to global food security and agricultural sustainability, causing substantial reductions in both yield quantity and produce quality. The timely and accurate identification of plant pathogens remains critically important for modern farming operations, yet conventional detection approaches continue to rely heavily on visual scouting by agricultural experts, a process that proves both time-intensive and economically burdensome, particularly across extensive cultivation areas. This research presents an intelligent crop disease detection system that synergistically combines the representational power of residual neural networks with the optimization capabilities of extreme gradient boosting. The proposed methodology initially applies comprehensive preprocessing procedures including normalization and data augmentation to enhance image quality and expand dataset diversity. Subsequently, the ResNet50 architecture serves as a deep feature extractor, capturing nuanced disease indicators such as chromatic aberrations, necrotic lesions, and textural anomalies from leaf imagery. These extracted high-dimensional features are then fed into an XGBoost classifier, which performs optimized multiclass disease categorization through its ensemble of decision trees. This hybrid configuration demonstrates superior classification accuracy while simultaneously mitigating overfitting concerns and exhibiting enhanced generalization across varying agricultural conditions. The framework effectively discriminates between healthy foliage and multiple disease states, thereby facilitating integration into real-time agricultural monitoring infrastructures. The experimental evaluation confirms that this approach enables early pathogen detection, supports informed decision-making for intervention strategies, and ultimately contributes to reduced crop losses, minimized pesticide utilization, and the advancement of sustainable precision farming methodologies in contemporary agriculture.
Why it matches plant phenotyping methods葉画像から病徴を抽出し、ResNet50とXGBoostで植物の健全・病害状態を分類する手法が研究の中心であり、評価も実施している。
abstractThis research presents an intelligent crop disease detection system that synergistically combines the representational power of residual neural networks with the optimization capabilities of extreme gradient boosting.
Accurate acquisition of phenotypic characteristics in protected crops is a crucial prerequisite for intelligent control and digital breeding in greenhouses. To accurately assess the phenotypic traits of protected lettuce, a specialized in situ phenotypic detection method has been developed. The Multimodal Features and Attention Mechanism for Phenotype Detection Model (MFAMNet) was developed for protected lettuce, employing a segmented multi-source image dataset for synchronous regression testing. The results revealed that the predicted values generated by MFAMNet exhibited a strong correlation with the measured values, achieving coefficients of determination of 0.96, 0.92, 0.95, 0.94, and 0.95 for plant height, crown width, leaf area, fresh weight, and dry weight, respectively. Ablation tests demonstrated that the deep learning detection framework based on multi-modal feature fusion significantly outperformed single-feature detection models, highlighting the advantages of integrating diverse data modalities. In addition, the multi-modal feature attention mechanism (MMF) facilitates both inter-modality and intra-modality interactions by capturing the global correlations between modalities and employing dynamic sparse spatial attention. The effectiveness of MMF has been validated through comparative experiments, demonstrating its suitability for the phenotypic detection of artificially cultivated lettuce. In summary, the method proposed in this study facilitates real-time monitoring of facility crops, enabling precise control of environmental parameters in protected agriculture and optimizing resource allocation. This approach contributes to the development of a comprehensive intelligent agriculture system and establishes a foundation for unmanned farms.
Why it matches plant phenotyping methodsレタスの草丈、株幅、葉面積、 fresh weight、dry weightを推定するマルチモーダル画像ベース手法を開発し、実測値との比較およびアブレーション・比較実験で検証しており、フェノタイピング手法が研究の中心である。
abstracta specialized in situ phenotypic detection method has been developed
The movement, distribution, and interactions of organelles are cell-type specific, responding to fluctuating metabolic and environmental cues and governing the efficiency of plant physiology and stress response. The directional motility of various plant organelles is predominantly driven by the actomyosin system, yet the distinct functionality of these organelles across plant tissues presupposes organelle-specific regulation of motility, which requires the detection of subtle shifts in dynamics. Meanwhile, studies that comprehensively characterize and directly compare the simultaneous movement of multiple types of organelles within the same cell are limited. Here, we visualized peroxisomes, mitochondria, chloroplasts, Golgi bodies, and actin filaments simultaneously in tobacco (Nicotiana tabacum) to evaluate organelle organization and motility within the context of one another. Quantitative analysis of multiple motility factors enabled us to identify peroxisome motility in tobacco mesophyll as distinct from other organelles. Further analysis in Arabidopsis (Arabidopsis thaliana) revealed that both mitochondria and peroxisomes are slower in mesophyll cells compared to epidermis in normal growth conditions, but their motility patterns are unique from one another across leaf tissue after plants experienced conditions that induce photorespiration, a metabolic pathway requiring the concerted action of chloroplasts, peroxisomes, and mitochondria. Our quantitative analysis of thousands of organelles across species, cell type, and physiological conditions unveils distinct modulation of motility according to organelle identity and function. The extensive combinatorial characterizations of plant organelle movement provide a fundamental resource for the future discovery of molecular mechanisms driving the movement and distribution of diverse organelles.
Why it matches plant phenotyping methods複数オルガネラを同時可視化し、運動性を定量抽出する画像解析ワークフローが研究の中心で、植物細胞の生理状態を表す測定法として実質的に適用されている。
abstractHere, we visualized peroxisomes, mitochondria, chloroplasts, Golgi bodies, and actin filaments simultaneously in tobacco (Nicotiana tabacum) to evaluate organelle organization and motility within the context of one another.
Maize is susceptible to various diseases throughout its growth cycle, which can significantly reduce yields. The accurate identification of maize diseases with similar symptomatic manifestations is particularly challenging under field conditions due to heterogeneous lighting and variable weather conditions. This paper proposes a novel detection model named SCFM-DETR, which is based on an improved Real-Time DEtection TRansformer (RT-DETR) to achieve robust identification of maize diseases in complex environments. SimAM-StarNet is employed as the backbone for feature extraction in this model, reducing the number of parameters and improving multiscale feature fusion, thereby diminishing the impact of background noise. Furthermore, the original RepC3 module is replaced with a newly designed CGLU-FasterBlock-MANet (CFM) module, which enhances adaptive feature fusion for finer discriminative capability. The experimental results demonstrate that the SCFM-DETR model achieves an average precision of 96.7% and a recall of 95.8% on a maize disease dataset, exceeding the corresponding metrics of the baseline RT-DETR-R18 model by 3.1% and 6.0%. Additionally, the model reduces the number of parameters and computational load by 47% and 49%, respectively, making it highly suitable for deployment in computationally limited agricultural settings. This work offers a high-accuracy, lightweight framework that facilitates intelligent crop disease monitoring and supports the advancement of smart agriculture.
Why it matches plant phenotyping methodsトウモロコシの病徴を画像から検出するモデルを開発・評価しており、植物の病害状態を推定する画像ベースの表現型計測手法が中心である。
abstractThe experimental results demonstrate that the SCFM-DETR model achieves an average precision of 96.7% and a recall of 95.8% on a maize disease dataset
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 5 Sept 2026
Despite their relevance to postharvest engineering and cultivar improvement, the genotype- and environment-dependent variation of the physical and geometrical traits of onion bulb remains poorly characterized in the Republic of Korea. The study evaluated these traits in six commercial onion cultivars grown across two distinct production regions (Muan and Changnyeong), using a randomized complete block design with three replications. A standardized phenotyping workflow combined with image acquisition and imageJ-based trait extraction was employed to measure linear dimensions, including polar and equatorial diameters, neck and bulb thickness. Linear mixed models were used to partition genotype (G), location (L), and G x L interaction effects. Most traits exhibited significant G, L, and G×L effects, indicating strong environmental sensitivity alongside genetic control Combined heritability estimates were high for bulb thickness (0.83), bulb weight (0.66), and diameter- and area-related traits (0.54–0.68), while broad-sense heritability across locations was consistently high (0.71–0.99), particularly for single bulb weight and size traits. Spring Breeze, Katamaru, and Healthy Q consistently produced larger bulbs, while Cheonjujeok and Eomji Nara exhibited smaller bulb dimensions. Trait responses varied markedly between environments, with changes ranging from reduction of approximately 80% to increases exceeding 160%, highlighting pronounced genotype × environment interactions. Hierarchical cluster heatmap analysis revealed strong associations among bulb size–related traits and distinct genotype groupings, with clear location-dependent differences in trait expression between Muan and Changnyeong. These findings demonstrate the utility of image-based phenotyping for robust environment-aware assessment of onion bulb geometry and provides a quantitative basis for region-specific cultivar selection, postharvest system design, and future multi-site breeding evaluations.
Why it matches plant phenotyping methods画像取得とImageJによる形質抽出を組み合わせた標準化フェノタイピングワークフローが、タマネギ球の形態形質測定の中心的手法として明示されているため。
abstractA standardized phenotyping workflow combined with image acquisition and imageJ-based trait extraction was employed to measure linear dimensions
Accurate measurement of posture traits, such as curvature and droop, can provide critical insight into the structural phenotype and stress response of tall grasses, including key perennial bioenergy crops. These posture traits vary across genotypes and growth stages and can influence both productivity and harvestability. This study builds on previous efforts to quantify whole-plant posture, extending the analysis to incorporate deep learning and multi-view UAV imagery. High-resolution oblique, sideways, and nadir images were collected over experimental plots comprising multiple grass genotypes with diverse morphologies. A deep learning framework, incorporating instance segmentation models, was developed to classify plants based on posture metrics extracted from multiple viewing angles. By training on oblique and nadir views together, this work explores the degree to which plant posture can be inferred from each perspective, helping evaluate the contribution of each data acquisition approach and exploring the possibility of combined data acquisitions. Validation against manually annotated datasets evaluates the ability of the approach to differentiate posture traits at high resolution, enabling non-destructive, plant-specific phenotyping at scale. The work supports longitudinal monitoring of canopy structure and facilitates the integration of posture descriptors into breeding programs. It also provides a framework for future fusion with LiDAR and Structure-from-Motion (SfM) data to enhance 3D modeling of genotype-specific canopy architectures in switchgrass or other tall grasses.
Why it matches plant phenotyping methods深層学習と多視点UAV画像から植物姿勢形質を抽出・分類する手法を開発し、手動アノテーションで検証しているため、植物フェノタイピング手法が中心である。
abstractA deep learning framework, incorporating instance segmentation models, was developed to classify plants based on posture metrics extracted from multiple viewing angles.
Introduction: Achieving sustainable growth in agricultural productivity is crucial for addressing various challenges confronting food systems globally. One of the key aspects is effectively identifying and addressing diseases that can adversely affect crop quality and yield. Methods: This research study proposes the use of Wireless Multimedia Sensor Network (WMSN) in conjunction with deep transfer learning model for disease detection in horticulture crops. The proposed system utilizes the image data of horticulture crops obtained using WMSN for performing a comparative assessment of several pre-trained deep learning models, encompassing VGG, ResNet, MobileNet, Inception, Xception, DenseNet, and EfficientNet, to ascertain their effectiveness in identifying diseases across a range of horticultural plants. The models undergo fine-tuning using transfer learning technique and are assessed on different measures, such as accuracy, precision, recall, F1 score, and the number of epochs needed for convergence using the image data obtained from WMSN. Results and Discussion: Among the compared models, EfficientNetB3 appears as the best performing model, surpassing others in all evaluation metrics while also exhibiting low parameters and a compact size. Notably, EfficientNetB3 achieves a testing accuracy of 93.69% and a training accuracy of 98.85% after only 21 epochs of training. In contrast, DenseNet201, DenseNet169, and EfficientNetB0 demonstrate performance close to the best-performing models, but they have higher parameters or sizes. On the contrary, ResNet50, InceptionV3, and Xception exhibit poorer performance, presumably due to their substantial size in relation to the dataset. Conclusion: This analysis provides valuable insights for optimizing the top-performing models for disease classification across various plant species. Moreover, the fine-tuned EfficientNetB3 model shows potential for integration with mobile devices, facilitating real-time disease classification.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習手法を提案し、複数モデルを比較評価しているため、病害フェノタイピング手法が中心です。
abstractThis research study proposes the use of Wireless Multimedia Sensor Network (WMSN) in conjunction with deep transfer learning model for disease detection in horticulture crops.
BACKGROUND: Phenotypic diversity arises from the process of development and is shaped by genomic variation in plants. However, the genetic basis of growth dynamics remains poorly understood in maize. RESULTS: Here, we analyze 679 maize inbred lines derived from a synthetic CUBIC population with approximately 2.8 million SNPs, leveraging high-throughput phenotyping to capture 1,002,240 RGB images across 18 growth stages. We quantify 67 image-based traits (i-traits), revealing distinct dynamic patterns throughout development. Genome-wide association studies identify 857 quantitative trait loci (QTLs) influencing growth variation, with 88.6% classified as period-specific dynamic QTLs exhibiting modest effects, and 11.4% as conservative QTLs with sustained effects. Notably, 1.5% of cryptic pleiotropic QTLs spanning different growth stages suggest genetic relocations during development. These QTLs enhance heritability estimates for mature traits by an average of 6.2%. We further characterize the novel function of key genes linked with these QTLs, including BRD1 with the pleiotropic effects on plant height and perimeter of convex hull and ZmGalOx1 with the broad-spectrum regulation of plant architecture. Developmental rewiring of epistatic networks shapes maize growth, underscoring the vitality of temporal genetic regulation. Trajectory modeling of i-traits across periods decodes the growth variation patterns, supporting the ontogenic hypothesis driven predictive breeding strategies. CONCLUSION: The findings elucidate the genetic architecture underlying growth dynamics from a spatial-temporal perspective, offering novel insights for maize improvement.
Why it matches plant phenotyping methods大規模RGB画像から67の画像形質を抽出し、発育段階ごとのトレイト動態を解析する高スループット植物表現型解析が研究の中核であるため、方法応用として収録する。
abstractleveraging high-throughput phenotyping to capture 1,002,240 RGB images across 18 growth stages
Reproduction assets foundThe paper's own phenotyping assets are publicly available: selected RGB plant images on Zenodo (record 18150504), and the image-analysis/i-trait extraction pipeline code on GitHub with a Zenodo mirror (record 18151471). The NCBI BioProject and MaizeGDB are prior-study/generic resources, not paper-specific.Code · publicThe image analysis and i-trait extraction pipeline and codes followed the previous procedure [ 18 ] without any modifications and has been publicly released at Github [ 49 ] and Zenodo [ 50 ] platform, all code in the repository are released under the MIT License.Open asset ↗GitHublines:195-202Code · publichas been publicly released at Github [ 49 ] and Zenodo [ 50 ] platform, all code in the repository are released under the MIT License.Open asset ↗Zenodolines:195-202Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · checked 5 Sept 2026
Pigeon pea ( Cajanus cajan [L.] Millsp.) remains an underutilized legume in most African countries despite its potential to promote climate-resilient farming, diversify food sources, and enhance nutrition. Limited understanding of its indigenous diversity and farmer trait preferences hampers wider adoption, especially in the West African region. Between February and May 2025, a germplasm exploration was conducted across 18 Nigerian states, supplemented by accessions from the International Institute of Tropical Agriculture (IITA) genebank, Ghana, the Republic of Benin, and The Gambia, totaling 273 accessions. Ethnobotanical surveys documented farmer preferences, cultural uses, and local nomenclature, while seed morphometric traits were assessed using Videometerlab4 multispectral imaging. Farmer surveys revealed that cooking time (58.3%), commercial value (27.0%), and maturity cycle (14.7%) were key preferred traits. Gender and age influenced preferences; women and older farmers prioritized cooking time, whereas men and younger farmers emphasized the maturity cycle. Vernacular names (e.g., Otili, Fiofio, Waken Gwari ) reflected deep cultural ties and cross-border exchange in Ogun State and the Republic of Benin, highlighting transboundary diversity. Morphometric analysis showed moderate variation in seed size, shape, and color. Seed area (14.2–46.0 mm2), compactness (0.590–0.998), and eccentricity (0–0.808) distinguished rounded from elongated seeds, while CIELab_A values (− 0.04 to 29.98) captured color differences. The first two PCA axes explained 67.1% of the total variation, and cluster analysis grouped accessions into four morphotypes. By combining genetic, morphometric, and farmer preference data, this study offers a strong basis for conserving and developing climate-resilient, fast-cooking, and market-preferred cultivars for sub-Saharan Africa.
Why it matches plant phenotyping methodsVideometerlab4マルチスペクトル画像を用いた種子形態形質の取得と解析が研究の主要な構成要素であり、複数の形態・色指標と形態型分類を実施しているため、フェノタイピング手法の実質的な適用に該当する。
titleGermplasm exploration and digital phenotyping reveal indigenous diversity and farmer preferences in pigeon pea (Cajanus cajan (L.) Millsp.) for climate-smart breeding
In response to the demand for real-time monitoring of the nitrogen nutritional status of peanut populations, this paper proposes a real-time monitoring system for the nitrogen nutritional status of peanut populations based on the YOLOv11 framework and spectral attention module. Traditional nitrogen detection methods have problems such as low efficiency and difficulty in achieving population-scale monitoring, while crop phenotyping technology based on computer vision faces challenges such as small leaf targets, severe occlusion, easy confusion of nitrogen deficiency symptoms, and difficulty in deploying deep learning models on mobile terminals. This study improves the YOLOv11 model, introduces the ASF (Attentional Scale Fusion) module and the DySample dynamic upsampling mechanism, enhances the model’s perception and feature expression capabilities for multi-scale targets, and effectively improves the monitoring accuracy and robustness of the nitrogen nutritional status of peanut populations. Experimental results show that the ADS-YOLO model performs well in evaluation indicators such as accuracy, recall, and mean average precision (mAP), providing technical support for precision fertilization of peanuts.
Why it matches plant phenotyping methodsピーナッツ集団の窒素栄養状態という植物状態を画像から推定するYOLOモデルを開発・評価しており、表現型取得・抽出手法が研究の中心である。
abstractthis paper proposes a real-time monitoring system for the nitrogen nutritional status of peanut populations based on the YOLOv11 framework and spectral attention module.
The growing influence of plant diseases on agricultural productivity becomes a major threat to the food security of the world. Traditional methods of identifying plant diseases of leaves are time consuming, prone to mistakes and overwhelmingly dependent on the knowledge of experts to make a decision. In this project, an Attention-Augmented Multi-Scale Convolutional Neural Network (CNN) deep learning-based method for automated detection of plant diseases is proposed. The model combines multi-scale feature extraction with channel and spatial attention, which can better learn discriminative feature representations from leaf images. Multi-scale convolutions are adopted which learn both the small-scale and large-scale disease patterns, and the Squeeze-and-Excitation (SENet) and the Convolutional Block Attention Module (CBAM) are taken into account which make the network only pay attention to the leaf regions via the veins, edges, and infected spots, and decrease the background noise interference. Images are preprocessed with the background removal and augmentation techniques to improve generalization. A notable fact is that performance of the proposed architecture outperforms the traditional CNN models in terms of significant enhancements in classification accuracy and classification robustness. The implementation for the system is TensorFlow & Keras AI framework using GPU accelerated Colab environments for fast convergence of the system. Using the help of a Streamlit-based web app for real-time prediction of diseases, users can upload leaf images and can get the instant diagnosis. The presented end-to-end system shows how attention-augmented networks play a major role in aiding early disease detection in precision agriculture for sustainable crop management and mitigation of economic losses.
Why it matches plant phenotyping methods葉画像から植物病害状態を検出・分類するCNN手法の開発が研究の中心であり、植物表現型（病害状態）の画像ベース推定に該当する。
abstractan Attention-Augmented Multi-Scale Convolutional Neural Network (CNN) deep learning-based method for automated detection of plant diseases is proposed.
[Objective]Maize leaf dry biomass is a key trait that reflects plant morphology, growth vigor, and physiological processes including photosynthetic production. Its dynamic changes can effectively characterize the growth status of maize. Accurate estimation of maize leaf dry biomass is crucial for accurately predicting maize yield and informing production management decisions. Extensive research on crop dry biomass estimation indicates that 3D point cloud data characterizing crop morphological structure, along with features derived therefrom, exhibit an extremely high correlation with crop dry biomass. However, traditional dry biomass prediction studies focus primarily on the population canopy scale, and lack effective prediction methods for dry biomass at the plant and organ scales. Research on non-destructive measurement methods for maize leaf dry biomass, based on 3D point clouds and machine learning, the demand is conducted to address for rapid acquisition of organ-level dry biomass information in maize cultivation and management research.[Methods]Maize leaf point cloud data were acquired using three techniques: Multi-view stereo (MVS), LiDAR scanning, and 3D digitalization (DT). The leaf point clouds underwent preprocessing steps that included plant segmentation, denoising, mesh refinement, and uniform subsampling. Subsequently, morphological traits were extracted from the processed data, including leaf length, leaf area, bounding box dimensions, and the number of points contained within the leaf point clouds. Three machine learning methods: random forest (RF), gradient boosting regression tree (GBRT), and support vector regression (SVR), as well as two deep learning methods: convolutional neural network (CNN) and fully connected neural network (FCNN), were employed for predicting maize leaf dry weight. A point cloud-based maize leaf dry biomass prediction model was subsequently developed. This study utilized the mean squared error reduction method inherent to RF and the cumulative improvement method based on decision tree splits in GBRT to rank and visualize feature importance for optimal models. The resulting rankings were then visualized. Simultaneously, Pearson correlation analysis was used to analyze the correlations of the features from the fused dataset (integrating data from the three devices) as well as those from the DT data with maize leaf dry biomass.[Results and Discussions]The results demonstrated that, among the dry biomass prediction models developed in this study, the model based on Laser point cloud data and the FCNN method achieved the highest accuracy, with a mean absolute error (MAE) of 0.08 g, a mean absolute percentage error (MAPE) of 4.60%, a root mean square error (RMSE) of 0.10 g, and a coefficient of determination (R2) of 0.98. In the correlation analysis, the leaf area exhibited the strongest correlation with dry biomass (r = 0.92), followed by the number of points (r = 0.88), leaf width (r = 0.86), and leaf length (r = 0.77). In the feature importance ranking, the leaf area trait consistently ranked within the top two positions, whereas the number of points ranked among the top three in most cases. However, features such as the height of the leaf base above the ground, the horizontal distances from the leaf tip and apex to the stem, and the azimuth angle demonstrated low correlations with dry biomass and low feature importance.[Conclusions]Among all the maize leaf features investigated in this study, size-related traits (such as leaf area, point count, leaf length, and leaf width) had the greatest impact on the accuracy of dry biomass estimation. The utilization of high-resolution 3D point clouds of maize leaves, combined with machine learning methods, enabled a high-accuracy estimation of leaf dry weight and provided a novel approach for the non-destructive measurement of dry biomass in crop organs.
Why it matches plant phenotyping methods3D点群取得・前処理・形態形質抽出と機械学習を組み合わせ、トウモロコシ葉の器官レベル乾物重を非破壊推定する手法を開発・評価しており、表現型取得と推定が研究の中心である。
abstractMaize leaf point cloud data were acquired using three techniques: Multi-view stereo (MVS), LiDAR scanning, and 3D digitalization (DT).
Wheat breeding strategies, focused on the creation of varieties with high yield potential under optimized, intensive fertilization, have resulted in a loss of genetic diversity and reduced the ability of these varieties to perform well in low-input farming systems. Recent advances in plant phenotyping have opened new possibilities for the in-depth characterization of old and neglected wheat varieties considering their value for cultivation under stress-prone conditions. The aim of this paper was to assess the environmental sustainability of old wheat varieties that were grown in South East Europe before and at the beginning of the Green Revolution. The 30 wheat varieties were grown under rain-fed conditions during the 2024/25 growing season in experimental trials at Rimski Šančevi, Serbia. Field evaluation was conducted at three growth stages using 15 traits associated with yield and resilience to abiotic stresses with two non-destructive phenotyping devices - the Literal sensor (Hiphen) and the DUALEX optical leaf clip meter (Metos). After harvest, thousand grain weight and grain size were assessed using the MARViN (MARViTECH), while basic technological parameters were obtained by the GrainSense Analyzer (Oulu). ANOVA revealed statistically significant differences among the analysed genotypes for the studied traits, while the re-evaluation of old varieties under contemporary climate conditions, applying high-throughput phenotyping instruments, enabled elucidation of their value and potential role in wheat production under climate change.
Why it matches plant phenotyping methods複数の非破壊センサーと高スループット機器を用いて、品種の収量・ストレス関連形質を体系的に取得する方法適用が研究の主要部分である。
abstractField evaluation was conducted at three growth stages using 15 traits associated with yield and resilience to abiotic stresses with two non-destructive phenotyping devices - the Literal sensor (Hiphen) and the DUALEX optical leaf clip meter (Metos).
Abstract The research develop an accurate and efficient method for detecting multiple corn leaf diseases to support sustainable agricultural practices in Soppeng Regency, Indonesia. The goal is to design a Convolutional Neural Network (CNN) model capable of classifying corn leaf diseases, including rust, blight, and gray leaf spot, using high-resolution image data. The research employed a balanced dataset sourced from open-access repositories, followed by preprocessing, data augmentation, and CNN model optimization. The model’s performance was evaluated using accuracy, precision, recall, and F1-score to ensure comprehensive assessment. Experimental results show that the proposed CNN achieved high accuracy across all disease classes, with strong per-class metrics, indicating robust performance in distinguishing visually similar symptoms. The classification results with the Convolutional Neural Network algorithm have 95% training data accuracy and 93% test data accuracy in detecting leaf diseases in corn plants. The findings contribute to agricultural technology by offering a scalable and field-deployable disease detection system that can be integrated into mobile or edge-based platforms. Limitations include reliance on publicly available datasets, which may not fully capture the variability of local field conditions. The research concludes that the proposed CNN model can significantly enhance early disease detection, reduce dependency on manual inspections, and support precision agriculture. Future research should focus on expanding the dataset with locally captured images, incorporating real-time image acquisition, and optimizing the model for deployment in low-resource environments to improve adaptability and reliability.
Why it matches plant phenotyping methodsトウモロコシ葉の病害症状を画像から分類するCNN手法の開発・性能評価が中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として含める。
abstractThe goal is to design a Convolutional Neural Network (CNN) model capable of classifying corn leaf diseases, including rust, blight, and gray leaf spot, using high-resolution image data.
Reproduction assets foundThe paper's phenotyping analysis is based entirely on a public Kaggle corn leaf disease image dataset, explicitly cited with URL and access date in the Data Availability statement and Methods. No author code or trained model is shared.Dataset · publicrch and innovation in the field of agricultural technology and artificial intelligence
Data Availability
The data used in this study comes from a publicly available and curated image repository. The dataset was obtained from the “Corn or Maize Leaf Disease Dataset” . The data source can be seen in the Kaggle – https://www.kaggle.com/smaranjitghose/corn-or-maize-leaf-disease-dataset
References
Rozi F, et al. Indonesian market demand patterns for food commodity sources of carbohydrates in facing the global food crisis. Heliyon. 2023;9(6):e16809. 10.1016/j.heliyon.2023.e16809 .
Yu B-G, Chen X-X, Zhou C-X, Ding T-B, Wang Z-H, Zou C-Q. Nutritional composition of maize grain assoOpen asset ↗Kaggle · smaranjitghose/corn-or-maize-leaf-disease-datasetlines:224-246Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Hyperspectral technology is used to monitor the SPAD (Soil and Plant Analysis Development) of maize, which is of great significance for regulating maize growth, optimizing nutrient management and improving yield formation. However, too much spectral information of hyperspectral data has resulted in the parameters redundancy and the complex structure of model. To solve this problem, a spectral vegetation indices (VIs) and wavelet features (WF) fusion method using squeeze-and-excitation network (SENet-SVWF) was proposed in this study. The partial least squares regression (PLSR), support vector regression (SVR), random forest regression (RFR), extreme gradient boosting (XGBoost) and long short-term memory (LSTM) predictors and five pretreatment methods were used in predicting SPAD value of maize, and the best pretreatment method and predictor were determined. VIs and wavelet transform (WT) were used to analyze the spectral data after the best pretreatment. Pearson correlation analysis and peak extraction method were used to determine the combination of VIs and WF. The SENet was introduced to fuse the selected VIs and WF, and the corresponding weights of different spectral features were optimized. The results showed that the multivariate scattering correction (MSC) was identified as the best pretreatment method, and SVR and RFR predictors performed best. The model established using SE-VIs-WF spectral features combined with RFR has the highest accuracy. The R 2 of the test set at V6, V8, V12 and R1 were 0.570, 0.760, 0.824 and 0.742, the root mean squared error (RMSE) were 1.199, 1.786, 1.994 and 3.118, respectively. Compared with the spectral data after MSC pretreatment, the R 2 of the model test set increased by 6.742%, 13.264%, 20.644% and 8.480%, and the number of model input features decreased by 541, 539, 539 and 541. The method proposed would achieve accurate prediction of SPAD value of maize and provide new ideas for crop nutrition information estimation.
Why it matches plant phenotyping methodsトウモロコシ葉のSPAD値という植物生理形質を、ハイパースペクトル特徴量と深層学習で推定する手法を開発・評価しており、表現型取得・抽出が中心である。
abstractTo solve this problem, a spectral vegetation indices (VIs) and wavelet features (WF) fusion method using squeeze-and-excitation network (SENet-SVWF) was proposed in this study.
Automated extraction of individual plant branches from time-series imagery is essential for high-throughput phenotyping, yet it remains computationally challenging due to non-rigid growth dynamics and severe identity fragmentation within entangled canopies. To overcome these stage-dependent ambiguities, we propose ST-DETrack, a spatiotemporal-fusion dual-decoder network designed to preserve branch identity from budding to flowering. Our architecture integrates a spatial decoder, which leverages geometric priors such as position and angle for early-stage tracking, with a temporal decoder that exploits motion consistency to resolve late-stage occlusions. Crucially, an adaptive gating mechanism dynamically shifts reliance between these spatial and temporal cues, while a biological constraint based on negative gravitropism mitigates vertical growth ambiguities. Validated on a Brassica napus dataset, ST-DETrack achieves a Branch Matching Accuracy (BMA) of 93.6%, significantly outperforming spatial and temporal baselines by 28.9 and 3.3 percentage points, respectively. These results demonstrate the method's robustness in maintaining long-term identity consistency amidst complex, dynamic plant architectures.
Why it matches plant phenotyping methods植物画像から個体枝を追跡・抽出する手法を開発し、アブラナ dataset で性能検証しているため、植物表現型取得の中心的研究である。
abstractAutomated extraction of individual plant branches from time-series imagery is essential for high-throughput phenotyping
Field / plotLeafStress / disease detectionDisease symptoms / severity
This work proposes an AI-powered agricultural decision-support system to overcome the limitations of traditional advisory mechanisms that often fail either in their diagnostic acumen or contextual awareness. In this respect, the proposed approach integrates a hybrid convolutional neural network-Swin Transformer architecture for plant disease detection with a multilingual conversational module powered by Google Gemini. The hybrid visual framework merges convolutional feature extraction with shifted-window selfattention, thus accurately identifying subtle and globally distributed disease patterns within natural farm images. The conversational module interprets farmer queries across regional languages, assuring reliable intent understanding and domainspecific response generation. Real-time meteorological data from the OpenWeatherMap API have been integrated to align diagnoses with localized environmental risks, rendering more actionable recommendations. The empirical investigation shows that the system has outperformed traditional CNN-based architectures on accuracy, precision, recall, and robustness metrics. Collectively, the framework offers a scalable, contextaware, and multilingual solution for enhanced crop health management under precision agriculture.
Why it matches plant phenotyping methods植物の自然画像から病害パターンを検出・分類する画像解析手法が中核であり、植物病害状態のフェノタイピングに該当する。対話型農業支援や気象情報も含むが、病害検出モデルの技術評価が明示されている。
abstractThe empirical investigation shows that the system has outperformed traditional CNN-based architectures on accuracy, precision, recall, and robustness metrics.
Field / plotMultimodalLeafClassificationStress / disease detectionDisease symptoms / severity
Plant leaf diseases significantly affect crop yield and quality, posing a major challenge to global agriculture. Conventional detection methods based on manual inspection or image-only deep learning often overlook critical environmental factors influencing disease development. This paper proposes an Edge-Aware Multi-Modal Attention Network (EMAN) that integrates IoT sensor data with high-resolution leaf images to detect and assess disease severity accurately in real time. EMAN fuses visual leaf features with environmental measurements, including temperature, humidity, soil moisture, and light intensity. Dynamic Dilated Residual Blocks (DDRB) extract multi-scale image features to identify small lesions, discolorations, and subtle disease indicators. A dual attention mechanism emphasizes disease-prone regions (spatial attention) and relevant environmental factors (sensor attention), enhancing predictive performance. The architecture supports edge-cloud hybrid inference, enabling lightweight edge models to provide instant alerts to farmers, while cloud analytics refine predictions and monitor temporal disease trends. Experiments on combined Plant Village and on-field datasets demonstrate that EMAN outperforms conventional CNN-based methods in both disease classification and severity estimation, achieving robust multi-modal fusion and real-time edge inference. The proposed system provides a scalable solution for precision agriculture, promoting proactive crop management, minimizing economic losses, and supporting sustainable farming practices.
Why it matches plant phenotyping methods葉画像とIoTセンサーを統合し、植物病害の検出・重症度推定手法を開発・評価しており、植物状態の取得が研究の中心である。
abstractThis paper proposes an Edge-Aware Multi-Modal Attention Network (EMAN) that integrates IoT sensor data with high-resolution leaf images to detect and assess disease severity accurately in real time.
Why it matches plant phenotyping methodsジャガイモ塊茎の病斑・生理障害を画像から検出する深層学習モデルを開発・比較し、精度を検証しているため、植物フェノタイピング手法が中心です。
abstractwe propose YOLOv8-ST, an enhanced deep learning model that incorporates the Swin Transformer and Triplet Attention modules to effectively distinguish between these visually similar tuber blemishes.
Addressing the challenging issue of complex background interference in plant disease identification, recent research employs diverse deep learning (DL) methodologies on both publicly available and customized datasets. This study introduces a two-step DL approach for plant disease classification. Initially, an enhanced convolutional neural network (CNN) is developed through a comparative analysis of prominent CNN architectures, including customized and cascaded versions of select DL models, achieving an accuracy of 93.3%. To further enhance accuracy, segmentation architectures such as DeepLabV3+, UNet, Iterative UNet, and UNet with Atrous Spatial Pyramid Pooling (ASPP) are integrated before customized CNN architectures. These segmentation algorithms effectively isolate the diseased portions of leaf images. Notably, the UNet with ASPP architecture demonstrates reduced time complexity, minimizing the number of features to be trained, and significantly improves accuracy to 99.8%, outperforming other predefined architectures. The models are trained on a plant village dataset, detecting 10 different diseases across various plant species, including tomato, corn, and potato.
Why it matches plant phenotyping methods葉画像から病変部位を分離し、植物の病害状態を分類する画像解析手法が研究の中心であるため、植物フェノタイピング手法として含める。
abstractThis study introduces a two-step DL approach for plant disease classification.
Agriculture contributes enormously to global food security, but crop diseases result in huge yield losses every year, compromising food production globally. Conventional disease identification practices depend mostly on visual inspection by agricultural specialists, which is time-consuming, subjective, and not accessible to small farmers. Deep Learning (DL) has come forward as a revolutionary technology to implement automated plant disease detection with the promise of quick, precise, and scalable applications. This work introduces an end-to-end deep learning-based plant disease detection and classification system using Convolutional Neural Networks (CNNs). The system applies transfer learning using pre-trained networks like VGG16, ResNet50, and MobileNetV2 with a high accuracy and efficiency in computations. The system takes leaf images using smartphones or Internet of Things (IoT)-based cameras, performs processing using a trained CNN model, and makes real-time diagnosis along with treatment suggestions. Experimental outcomes show classification accuracy of over 95% for various crop species like tomato, potato, apple, and corn. Combining this technology with IoT devices and mobile applications facilitates farmers to make prompt decisions based on accurate information, saving losses on crops and ensuring eco-friendly farming. This work contributes to precision agriculture by narrowing the gap between cutting-edge AI technologies and effective farming requirements
Why it matches plant phenotyping methods植物の葉画像から病害状態をCNNで検出・分類する手法が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThis work introduces an end-to-end deep learning-based plant disease detection and classification system using Convolutional Neural Networks (CNNs).
Cotton, as a globally important economic crop, requires early and accurate disease detection to ensure stable yield and promote sustainable development. However, due to the small size of certain leaf lesions, traditional detection methods often suffer from missed or false detections. To address this issue, we propose an improved YOLOv8-based model, CM-YOLO, aimed at enhancing the detection performance for small cotton leaf disease targets. Specifically, the SS2D module from VMamba is introduced into the backbone network to achieve comprehensive feature extraction through multi-directional scanning. Furthermore, the MSDA module is embedded prior to the SPPF module to reduce performance degradation caused by redundant computations and to enhance the model's focus on critical small targets. Finally, the original bounding box loss function is replaced with DIoU, enabling precise localization of small targets by optimizing anchor center point distances and accelerating model convergence. Experimental results demonstrate that CM-YOLO achieves superior performance in cotton leaf disease detection, with an mAP50 of 0.933 and a recall of 0.891. Compared with state-of-the-art methods, YOLOv8n and YOLOv11n achieve mAP50 values of 0.874 and 0.930, respectively, both lower than CM-YOLO, thereby validating the effectiveness of the proposed method. Additionally, generalization experiments indicate that the model maintains high detection accuracy and robustness across different plant datasets, highlighting its strong applicability in complex scenarios and providing a valuable reference for intelligent agricultural disease detection research.
Why it matches plant phenotyping methods綿花葉の病斑という植物の病害状態を画像から検出・局在化するYOLOベース手法を開発し、性能比較と汎化実験で検証しており、フェノタイピング手法が中心である。
abstractwe propose an improved YOLOv8-based model, CM-YOLO, aimed at enhancing the detection performance for small cotton leaf disease targets.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
Abstract Agricultural production is still quite susceptible to plant diseases, despite the fact that it is essential to both economic growth and food security. Yellow rust can lower wheat yields by 20–30%, red rust by 5–10%, and anthracnose by up to 60% in crops including cotton and mango. For losses to be minimized, early and precise detection is therefore crucial. Preprocessing, segmentation, feature extraction, and classification are all included in this study’s machine learning-based framework for detecting various crop leaf diseases. To test the model, 9,111 carefully chosen images that were balanced through augmentation were employed. The novelty of this work lies in combining bilateral filtering and GraphCut segmentation with texture-based feature extraction and a systematic comparison of multiclass SVM kernels across a multi-crop dataset. Experimental results using stratified 5-fold cross-validation show that the linear kernel SVM achieved the best performance, with 99.0% accuracy, 98.6% precision, 98.7% recall, and 98.6% F1-score–outperforming earlier SVM-based approaches. These findings demonstrate the effectiveness of kernel selection and preprocessing in enhancing disease classification and provide a strong basis for future comparisons with deep learning methods to build scalable and reliable plant disease detection systems.
Why it matches plant phenotyping methods植物葉の画像から病徴・病害状態を推定する画像解析手法が研究の中心であり、前処理、セグメンテーション、特徴抽出、SVM分類の比較と検証を行っているため含める。
abstractPreprocessing, segmentation, feature extraction, and classification are all included in this study’s machine learning-based framework for detecting various crop leaf diseases.
Double haploid (DH) technology can significantly shorten the breeding cycle and improve the breeding efficiency, and it is favored by breeders. The metrics for evaluating the effect of haploid genome doubling mainly include anther emergence and ear seed setting. The evaluation of fertility restoration ability is mainly conducted through visual inspection at present, which is time-consuming, and easy to be affected by fatigue, resulting in errors and inconsistencies. Therefore, it is urgent to develop efficient and accurate evaluation technology to reduce the field work burden of researchers. In this work, we propose a grading evaluation model (Maize-IRNet) of haploid anther emergence and ear seed setting based on Inception-ResNet. Firstly, the modules of Stem and Inception-ResNet are utilized for image feature extraction and multi-scale feature learning. Then, the Reduction module is used for spatial downsampling and feature compression, and the global attention mechanism (GAM) is used to enhance the recognition of key regions of the image. The experimental results show that the Maize-IRNet's classification accuracy of haploid ear seed setting and anther emergence is 84.2 % and 84.0 %, which is higher than six baseline methods (VGG11_bn, ResNet50, ResNet101, ViT-Base-16, gMLP, MLP-Mixer). In order to facilitate the practical application for breeding researchers, we have developed a mobile application that integrates the Maize-IRNet model. This study helps to achieve high-throughput collection of fertility restoration phenotypes, improves the evaluation efficiency of fertility restoration, reduces breeding costs, and provides technical support for the promotion of engineering breeding of DH technology.
Why it matches plant phenotyping methodsトウモロコシの葯出現と穂の種子着生という生殖形質を画像から自動評価する深層学習モデルを開発・比較し、モバイルアプリにも実装しており、表現型取得法が中心である。
abstractTherefore, it is urgent to develop efficient and accurate evaluation technology to reduce the field work burden of researchers.
Reproduction assets foundThe paper's data availability statement explicitly provides the maize haploid fertility image dataset (1897 ear images, 6443 tassel images), the Maize-IRNet source code, and the Android APK, all hosted on the authors' public GitHub repository.Dataset · publicThe maize haploid fertility image dataset collected by smartphones is available at https://github.com/wyzwyz666/maize-haploid-fertility/blob/main/datasetOpen asset ↗wyzwyz666/maize-haploid-fertilitylines:506-531Code · publicThe source code: https://github.com/wyzwyz666/maize-haploid-fertility/blob/main/sourcecodeOpen asset ↗wyzwyz666/maize-haploid-fertilitylines:506-531Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In the arid cultivation region of Xinjiang, China, shrinkage disease severely compromises the quality, yield, and market value of jujube. Published research has achieved high accuracy in detecting larger lesions using RGB imaging and hyperspectral imaging (HSI). However, these methods lack sensitivity in detecting early and subtle symptoms of disease. In this study, a multi-source data fusion strategy combining RGB imaging and HSI was proposed for non-destructive and high-precision detection of early-stage jujube shrinkage disease. Firstly, a total of 317 fruits of the 'Junzao' cultivar were collected during multiple stages of natural infection, covering early-stage shrinkage disease detection across different growth stages, including both green and mature red fruits. Secondly, morphological features were extracted from RGB images in multiple dimensions, while a three-stage feature selection strategy combining Principal Component Analysis (PCA), the Successive Projections Algorithm (SPA), and the Genetic Algorithm (GA) was implemented to identify four key wavelengths from HSI. Thirdly, a hybrid convolutional neural network-multilayer perceptron (CNN-MLP) architecture was constructed, with dynamic feature weighting employed to achieve effective multimodal fusion and optimize detection performance. Experimental results demonstrated that compared to the MLP and CNN models, the proposed method achieved approximately 8.0% and 5.4% improvements in accuracy and 38.6% and 32.4% improvements in F1 scores, respectively. It offers a robust and scalable solution for early disease detection and postharvest quality assessment in jujube production.
Why it matches plant phenotyping methodsRGB画像・HSIから果実の病斑形態と分光特徴を抽出し、マルチモーダル深層学習で植物病害状態を検出する手法の開発・性能評価が中心であるため。
abstracta multi-source data fusion strategy combining RGB imaging and HSI was proposed for non-destructive and high-precision detection of early-stage jujube shrinkage disease.
Reproduction assets foundThe paper's Data Availability Statement points to a public GitHub repository containing the study's dataset (RGB images and hyperspectral data of jujube fruits). No separate analysis code availability is stated, but the deposited dataset is a paper-specific, publicly actionable asset.Dataset · publicThe data from this study are publicly available. The dataset is available at https://github.com/2484733079/Early-detection-of-Jujube-Shrinkage-Disease-by-Multi-source-Data-on-Multi-task-Deep-Network.git (accessed on 13 October 2025).Open asset ↗2484733079/Early-detection-of-Jujube-Shrinkage-Disease-by-Multi-source-Data-on-Multi-task-Deep-Networklines:365-367Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Nov 2025Computers and Electronics in Agriculture.
Vision Transformers (ViTs) have recently demonstrated promising achievements in various computer vision tasks. However, designing a ViT model architecture requires high-level domain expertise, which can be challenging for new researchers to solve real-life problems, such as those in agricultural imaging. Agricultural datasets often include region-specific patterns influenced by factors such as soil metrics, weather conditions, crop imagery, and spectral signatures, making the design of the manual ViT model a time-consuming and expertise-driven process. To address these limitations, this study proposes a Neural Architecture Search (NAS) leveraging Differential Evolution (DE) algorithm which automates the process of fine-tuning hyperparameters, reducing the reliance on manual intervention and enabling the creation of highly optimized ViT models. The proposed approach is trained and tested on agricultural images dataset of tomato leaves, consisting of ten classes. The experimental results demonstrate the effectiveness of DE-based optimized ViT models by showcasing their ability to handle the unique complexities of agricultural datasets while achieving superior accuracy and reliability in classification tasks.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から分類するVision Transformerのアーキテクチャ探索手法を開発・評価しており、植物病害表現型の取得・推定が中心である。
abstractthis study proposes a Neural Architecture Search (NAS) leveraging Differential Evolution (DE) algorithm which automates the process of fine-tuning hyperparameters
Anthracnose, caused by Colletotrichum gloeosporioides, poses a significant threat to blueberries, necessitating a deeper understanding of the genetic mechanisms underlying resistance to develop efficient breeding strategies. Here, we conducted a genome-wide association study on 355 advanced selections of southern highbush blueberry from the University of Florida Blueberry Breeding and Genomics Program. Visual scores and image analyses were used for assessing disease severity. The population was genotyped using Capture-Seq, detecting 38,379 single nucleotide polymorphisms. The study revealed a moderate narrow-sense heritability estimate (∼0.5) for anthracnose resistance in blueberries. Minor additive loci contributing to anthracnose resistance were identified on chromosomes 2, 3, 5, 6, 9, 10, and 12, using 2 different phenotyping approaches. Visual and image-based phenotyping captured complementary aspects of anthracnose resistance, identifying distinct, non-overlapping SNP associations. Candidate gene mining flanking significant associations unveiled key defense-related proteins, such as serine/threonine protein kinases, pentatricopeptide repeat-containing proteins, E3 ubiquitin ligases that have been well-known for their roles in plant defense signaling pathways. Our findings highlight the complex and quantitative resistance mechanism for anthracnose in blueberry, providing insights for breeding strategies and sustainable disease management.
Why it matches plant phenotyping methodsブルーベリーの炭疽病抵抗性を対象に、視覚評価と画像解析による病害重症度推定を2つの表現型評価法として比較・適用し、相補的な抵抗性情報を抽出しているため、画像ベース表現型取得が研究の実質的要素です。
abstractVisual scores and image analyses were used for assessing disease severity.
Wheat protein content is a major determinant of its usage and value. Current methods require wet labs that may be difficult to access and are not real-time. To overcome this, Hyperspectral imaging (HSI) has been reported for estimating the protein content of wheat seeds with the advantage that it is real-time, does not require wet labs, and has high accuracy. However, these models have been developed and validated for a small range of protein content, and without considering cultivation regions. This paper reports the extension of the use of HSI for protein estimation for a wider range of protein content and for wheat cultivated in different regions. Hyperspectral images of 621 wheat samples from five regions in India were acquired in the 900-1700 nm wavelength range. The reference protein content of each sample was determined using the Kjeldahl method, with values ranging from 9.5 to 17.25%. Mean spectra were extracted from the hyperspectral images to develop deep learning and conventional machine learning methods, which were validated through 5-fold cross-validation. The experiments showed that the one-dimensional convolutional neural networks (1D-CNN) performed the best, with the coefficient of determination (R²) of 0.9972, root mean square error (RMSE) of 0.0771, and the ratio of performance to deviation (RPD) of 18.81 for the prediction set. This shows that a 1D-CNN model trained using mean spectra can accurately estimate the wheat protein content. This has the advantage of not requiring a wet lab, and being potentially real-time, which could benefit the farmers, traders, and food industry.
Why it matches plant phenotyping methods小麦種子のタンパク質含量という植物形質を、ハイパースペクトル画像と1D-CNNで推定する手法の拡張・検証が中心であり、交差検証による性能評価も実施している。
abstractThis paper reports the extension of the use of HSI for protein estimation for a wider range of protein content and for wheat cultivated in different regions.
Accurate and early detection of plant leaf diseases is crucial for ensuring crop health and improving agricultural productivity. This work proposes a hybrid deep learning model that combines ResNet18, Inception blocks, and fully connected Capsule layers to classify leaf images of apple, grape, and corn plants into healthy or diseased categories. ResNet18 is used as the backbone for deep feature extraction, while Inception modules enhance the network’s ability to capture multi-scale patterns. Capsule layers are employed at the final stage to retain spatial relationships and pose information, improving the model's ability to recognize complex disease features. The model is trained and evaluated using images from the PlantVillage dataset, with separate configurations for each crop. The proposed model achieved validation accuracies of 99.84% for apple, 100% for grape, and 97.27% for corn. Performance is further assessed using precision, recall, and F1-score, and compared against a baseline ResNet18 model. The results demonstrate that the proposed architecture significantly improves classification accuracy and feature understanding, making it a strong candidate for real-world agricultural disease monitoring systems.
Why it matches plant phenotyping methods植物葉画像から健全・病害状態を推定する画像ベースの深層学習手法を開発・評価しており、病害表現型の抽出が研究の中心である。
abstractThis work proposes a hybrid deep learning model that combines ResNet18, Inception blocks, and fully connected Capsule layers to classify leaf images of apple, grape, and corn plants into healthy or diseased categories.
Plant leaf disease classification presents significant challenges due to the extensive variation in disease symptoms and the diverse morphological characteristics of plant leaves. These variations complicate model training and hinder classification accuracy. This study proposes a hybrid deep learning (DL) model that combines SE-Residual blocks for feature enhancement, capsule networks (CN) for preserving spatial relationships, BiLSTM for processing sequential data, and attention mechanisms (AM) for feature prioritization, aiming to improve classification performance. SE-Residual blocks enhance feature extraction while minimizing information loss, and CN capture spatial relationships with reduced dependency on large datasets. BiLSTM processes sequential data, supported by AM to focus on critical features. The proposed model was trained and evaluated using the corn leaf disease dataset (CLDD) and the rice leaf disease dataset (RLDD). Its performance was compared with existing state-of-the-art models. The experimental results demonstrate that the proposed model achieved the highest training accuracy of 99.88% for CLDD and classification accuracies of 99.29% for blight, 100% for common rust, 100% for leaf spot, and 100% for healthy samples. Additionally, it achieved the highest training accuracy of 100% for RLDD and classification accuracies of 78.95% for bacterial leaf blight, 81.58% for brown spot, 89.77% for healthy, 77.27% for leaf blight, 100% for leaf scald, and 97.73% for narrow brown spot. These results highlight the effectiveness of the proposed model in achieving high accuracy for plant leaf disease classification.
Why it matches plant phenotyping methods植物葉の病害状態を画像から分類する深層学習手法を開発し、複数データセットで評価・比較しており、病害表現型の取得・推定が中心である。
titleA hybrid deep learning approach integrating capsule networks and BiLSTM for plant leaf disease classification
Rapid detection of quarantine diseases in apples is essential for import-export control but remains difficult because routine inspections rely on manual visual checks that limit automation at port scale. A fast, non-destructive system suitable for deployment at customs is therefore needed. In this study, three common apple quarantine pathogens were targeted using hyperspectral images acquired by a close-range hyperspectral camera and analyzed with a convolutional neural network (CNN). Symptoms of these diseases often appear similar in RGB images, making reliable differentiation difficult. Reflectance from 400 to 1000 nm was recorded to provide richer spectral detail for separating subtle disease signatures. To quantify stage-dependent differences, average reflectance curves were extracted for apples infected by each pathogen at early, middle, and late lesion stages. A CNN tailored to hyperspectral inputs, termed HSC-Resnet, was designed with an increased number of convolutional channels to accommodate the broad spectral dimension and with channel and spatial attention integrated to highlight informative bands and regions. HSC-Resnet achieved a precision of 95.51%, indicating strong potential for fast, accurate, and non-destructive detection of apple quarantine diseases in import-export management.
Why it matches plant phenotyping methodsリンゴ病害の症状をハイパースペクトル画像とCNNで検出・識別する方法が研究の中心であり、植物の病害状態を直接推定している。
abstracta convolutional neural network (CNN)
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 6 Sept 2026
Introduction: With the advancement of imaging technologies, the efficiency of acquiring plant phenotypic information has significantly improved. The integration of deep learning has further enhanced the automatic recognition of plant structures and the accuracy of phenotypic parameter extraction. To enable efficient monitoring of tomato water stress, this study developed a deep learning-based framework for phenotypic trait extraction and parameter computation, applied to tomato images collected under varying water stress conditions. Methods: Based on the You Only Look Once version 11 nano (YOLOv11n) object detection model, adaptive kernel convolution (AKConv) was integrated into the backbone's C3 module with kernel size 2 convolution (C3k2), and a recalibration feature pyramid detection head based on the P2 layer was designed. Results and discussion: Results showed that the improved model achieved a 4.1% increase in recall, a 2.7% increase in mAP50, and a 5.4% increase in mAP50-95 for tomato phenotype recognition. Using the bounding box information extracted by the model, key phenotype parameters were further calculated through geometric analysis. The average relative error for plant height was 6.9%, and the error in petiole count was 10.12%, indicating good applicability and accuracy for non-destructive crop phenotype analysis. Based on these extracted traits, multiple sets of weighted combinations were constructed as input features for classification. Seven classification algorithms-Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbors, Naive Bayes, and Gradient Boosting-were used to differentiate tomato plants under different water stress conditions. The results showed that Random Forest consistently performed the best across all combinations, with the highest classification accuracy reaching 98%. This integrated approach provides a novel approach and technical support for the early identification of water stress and the advancement of precision irrigation.
Why it matches plant phenotyping methodsトマト画像から植物高や葉柄数などの表現型形質を抽出・計算する深層学習フレームワークを開発し、精度評価も行っており、表現型取得手法が研究の中心である。
abstractthis study developed a deep learning-based framework for phenotypic trait extraction and parameter computation
Banana / plantainField / plotLiDAR / point cloudFruit2D/3D reconstructionSegmentation
Accurate 3D reconstruction provides essential spatial information for orchard robots and serves as a critical foundation for crop phenotypic analysis. However, most existing studies have focused on industrial scenarios and are typically conducted in interference-free indoor environments. In this study, we propose a novel 3D reconstruction method called BBNeuS, which achieves accurate reconstruction of banana bunches in real-world orchard conditions. To accurately separate banana bunches from orchards, this study proposes a multi-view extraction framework (MVExt), which alleviates occlusion and interference caused by the complex banana orchard environment by combining multiple views and point cloud projection. BBNeuS combines Signed Distance Field (SDF) supervision with bias consistency, which not only reduces deviations in volumetric rendering but also alleviates viewpoint discrepancies caused by unstable lighting conditions. We conducted segmentation experiments across various scenarios, with all evaluation metrics showing improvement, achieving up to a 12 % increase. In reconstruction experiments, the evaluation scores for PSNR, SSIM, and LPIPS reached 21.17, 0.89, and 0.27, respectively, representing improvements of 21.4 %, 20.3 %, and 20.6 % compared to baseline methods. The MAE metric was well balanced. These results demonstrate that BBNeuS can accurately extract banana-related information and significantly enhance the reconstruction of banana bunches. This research provides valuable insights for 3D phenotypic analysis of banana bunches and holds great significance for the development of intelligent banana orchards.
Why it matches plant phenotyping methodsバナナ房のセグメンテーションと3D再構成手法を開発・評価し、3D表現型解析への応用を明示しているため、植物表現型取得手法が中心である。
abstractwe propose a novel 3D reconstruction method called BBNeuS, which achieves accurate reconstruction of banana bunches in real-world orchard conditions.
Accurate and automated detection of wheat spikes is essential for high-throughput phenotyping and yield prediction, yet traditional manual counting is labor-intensive and error-prone. This study compared two deep learning models, U-Net and FasterViT, for wheat spike segmentation using pseudo-RGB images derived from hyperspectral data (400–1000 nm). A dataset of 400 wheat plants was collected at physiological maturity and annotated pseudo-RGB images were used for model training and testing. U-Net achieved a pixel accuracy of 0.893, a recall of 0.834, and a Dice score of 0.761. FasterViT outperformed U-Net with a pixel accuracy of 0.922, Intersection over Union (IoU) of 0.836, and a Dice score of 0.860, demonstrating better generalization and sharper segmentation of spikes. In terms of computational efficiency, U-Net required 2.5 seconds per image, whereas FasterViT required 6.85 seconds per image, reflecting a trade-off between speed and accuracy. Although the controlled dataset size was limited, the findings highlight the feasibility of low-resolution hyperspectral imagery for spike trait analysis. Future extensions could focus on field-based validation and integration into yield prediction pipelines to advance scalable precision agriculture.
Why it matches plant phenotyping methods小麦穂のセグメンテーション手法を比較・評価し、穂形質解析を目的とするため、植物フェノタイピング手法が中心である。
titleEvaluation of Deep Learning Models for Wheat Spike Segmentation Using Hyperspectral-derived Pseudo- RGB Images
In the Gross Domestic Product (GDP), agriculture production plays very crucial role and is a growth engine of a nation. Various countries are using advance technology like Artificial Intelligence (AI), Machine Learning (ML) and Internet of Things (IoT) within the agriculture sector which is referred as precision agriculture. Precision agriculture is a concept which involves all above technologies for increasing overall productivity of agriculture and to reduce time. Precise agriculture consists many domains which can be accomplished using AI and IoT. Plant leaf disease identification and crop recommendation are the two important domains of precise agriculture which uses AI and IoT technologies. Deep Learning (DL) on the other hand has the capacity for processing image data in proper way by extracting features. This research work ML and DL respectively for crop recommendation and plant leaf disease identification. Two separate ML models were developed by utilizing data obtained from kaggle. In order to utilize strength of multiple ML and DI techniques, a hybrid approach has been proposed in which two ML techniques: Support Vector Machine (SVM) and Artificial Neural Network (ANN) are combined together for crop recommendation. Results revels that hybrid of ANN and SVM achieved highest$\text{accuracy}=97.50 \%,\ \text{sensitivity}=97.61 \%$and$\text{specificity}=99.88 \%$as compared to individual technique. A hybrid of Convolutional Neural Network (CNN), VGG16 and EfficientNetV2S are combined for plant leaf disease identification resulting in$\text{accuracy}=97.33 \%,\ sensitivity =96.87 \%$and$\text{specificity} = 98.84 \%$.
Why it matches plant phenotyping methods葉画像から植物病害を識別する深層学習手法の開発と性能評価が研究の主要な貢献であり、植物の病害状態を直接推定しているため含める。作物推薦部分は対象外だが、病害識別手法だけで基準を満たす。
abstractA hybrid of Convolutional Neural Network (CNN), VGG16 and EfficientNetV2S are combined for plant leaf disease identification resulting in$\text{accuracy}=97.33 \%,\ sensitivity =96.87 \%$and$\text{specificity} = 98.84 \%$.
Strawberry (Fragaria x ananassa) cultivation plays an important role in local economies, especially in agrotourism regions like Bandung, Indonesia. Traditional disease identification methods, which rely on manual visual inspection by experts, are time-consuming, inconsistent, and infeasible for large-scale applications due to their subjective nature. To address these challenges, this study investigates the use of machine learning and computer vision models to automate and improve the accuracy of strawberry disease classification. We conducted a comparative analysis of nine machine learning models: DenseNet121, InceptionResNetV2, InceptionV3, MobileNetV2, ResNet50V2, VGG16, VGG19, YOLOv8n, and YOLOv11n. The dataset used in this study consists of 877 labeled images representing healthy and infected strawberry plants, collected from online sources (Kaggle, Roboflow) and field images. The data was preprocessed and split into training (70%), validation (20%), and testing (10%) subsets. Among all models, YOLOv8n and YOLOv11n achieved the highest classification accuracy of 94%, while also demonstrating fast inference speeds and relatively small model sizes. These results highlight their potential suitability for real-time disease detection in agricultural settings. The outcomes of this study aim to support the development of accessible, automated tools for strawberry disease diagnosis, particularly benefiting local farmers in agrotourism-based regions like Bandung.
Why it matches plant phenotyping methodsイチゴ植物の病害状態を画像から分類・推定する深層学習手法が研究の中心であり、植物病害表現型の取得・自動化に該当する。
abstractthis study investigates the use of machine learning and computer vision models to automate and improve the accuracy of strawberry disease classification.
Tomato plants, a globally significant horticultural crop, are frequently threatened by a range of diseases that compromise yield and quality. Traditional disease detection methods based on manual inspection by experts are often labour-intensive, time-consuming, and susceptible to human error. This study presents a machine learning-based approach that leverages Convolutional Neural Networks (CNNs) to automate the identification and classification of common tomato diseases using leaf images. A comprehensive dataset, including both healthy and diseased leaf images, was collected, pre-processed, and augmented to enhance model performance under various environmental conditions. A custom-designed CNN model was then trained and evaluated using standard metrics such as accuracy, precision, recall, and F1-score. The model demonstrated high classification accuracy and robustness across multiple disease categories including early blight, late blight, and bacterial spot. Furthermore, the system was deployed as a user-friendly web and mobile application interface, allowing real-time diagnosis in the field. This enables farmers especially in resource-constrained settings to identify and respond to infections early, thereby reducing yield losses and limiting excessive pesticide use. The project underscores the potential of AI-driven solutions in modernizing agricultural practices and promoting sustainable crop management. Recommendations are made for future work to improve model adaptability, extend its disease coverage, and integrate environmental sensor data for multimodal analysis.
Why it matches plant phenotyping methodsトマト葉画像から病害状態を分類するCNN手法を開発・評価しており、植物の病徴・病害状態の取得が研究の中心であるため。
abstractThis study presents a machine learning-based approach that leverages Convolutional Neural Networks (CNNs) to automate the identification and classification of common tomato diseases using leaf images.
Wheat diseases have severely threatened global food security, making prompt and accurate detection methods crucial for disease control. However, large-scale detection methods face challenges such as low accuracy, labor-intensive labeling processes, and limited applicability across different wheat diseases. This study proposes a novel method using an Unsupervised Domain Adaptation (UDA) for semantic segmentation, termed DATS-ASSFormer, to detect wheat rust, wheat scab, and wheat yellow dwarf from UAV-based multispectral images. The proposed method employs Domain Adaptation via Teacher-Student networks (DATS) to generate pseudo-labels for unlabeled data in the target domain, and Adaptive Semantic Segmentation Former (ASSFormer) to precisely segment diseased areas, thus minimizing the dependency on laborious manual labeling. To support the development and evaluation of the model, the Northwest A&F University-Wheat Disease Remote Sensing Dataset (NWAFU-WDRSD) was developed, encompassing 8,628 images of the three predominant wheat diseases. Extensive testing confirmed that the DATS-ASSFormer model outperformed existing models in six domain adaptation tasks, achieving average Oracle (supervised training within the target domain) and UDA mIoU scores of 85.80 % and 65.96 %, respectively. These results significantly enhance detection accuracy and robustness across various diseases in real-world agricultural settings. The efficacy of DATS-ASSFormer highlights its potential for practical applications in precision agriculture, offering a scalable and efficient solution for large-scale wheat disease detection and management. The project is accessible at https://github.com/YcZhangSing/DATS-ASSFormer.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から小麦病害領域を抽出するセマンティックセグメンテーション手法を開発・評価し、専用データセットも構築しているため、植物病害表現型の取得が中心である。
abstractThis study proposes a novel method using an Unsupervised Domain Adaptation (UDA) for semantic segmentation, termed DATS-ASSFormer, to detect wheat rust, wheat scab, and wheat yellow dwarf from UAV-based multispectral images.
Global climate change-induced environmental stress poses critical challenges to the stable development of economic crops such as citrus. High temperatures (HTs) at anthesis may cause poor pollination and excessive flower/fruit drop, seriously affecting fruit yield and quality. To comprehensively analyze the developmental dynamics and morphological responses of citrus to HT stress at anthesis, methods for precise whole-flower phenotypic extraction and stamen state classification were developed. A citrus flower automatic segmentation and phenotypic quantitative model (CF-ASPM) that combines the pre-trained Segment Anything Model (SAM) with a lightweight classification module was constructed to accurately identify and quantify key citrus flower structures. Phenotypic parameter extraction correlation coefficients were 0.90–0.98. A few-shot stamen classification method was also designed using a pre-segmentation strategy and differential features, and its classification accuracy was 96.39%. Experiments with Ehime mandarin were conducted to analyze dynamic citrus floral organ changes at different temperatures and the underlying physiological mechanisms. The results showed that citrus exhibits a distinct reproductive priority strategy under HTs. Floral organ growth is inhibited, blooming is accelerated, and an asynchronous compensation mechanism occurs between male and female organs. HTs accelerated flower aging and caused developmental imbalances in the ovary and nectar disc. This may lead to increased flower and fruit drop and altered fruit shape. This study revealed the reproductive priority strategy and growth imbalance of citrus floral organs under HTs using the CF-ASPM model. It provides important data for further exploring the molecular mechanisms and management strategies of HT stress.
Why it matches plant phenotyping methods柑橘花器官の自動セグメンテーション、形質抽出、雄蕊状態分類法を開発し、精度検証したことが研究の中心であるため。
abstractmethods for precise whole-flower phenotypic extraction and stamen state classification were developed.
FlowerClassificationObject detectionGrowth / development / phenology
As an ornamental plant, Alstroemeria Genus Morado holds great significance in precision agriculture for the automatic detection and classification of its flower maturity. However, due to its diverse morphologies, complex growth environments, and factors such as occlusion and lighting changes, related tasks face numerous challenges, and research in this area is relatively scarce. This study proposes a deep - learning - based object detection framework, the Morado Flower Detection Network (MFDN), which consists of two parts: a backbone network and a head network. Novel modules such as C3k2_PPA are introduced. Through multi - branch fusion and the attention mechanism, the ability to detect small targets is enhanced. The head network uses the CARAFE module for upsampling, combines features through Concat, accelerates processing with the optimized C2f module, and finally achieves precise detection and classification through the Detect module. In the comparative experiment on the morado_5may dataset, MFDN performs outstandingly in indicators such as Precision, Recall, and F1 - score. The mean Average Precision (mAP) of MFDN is 1.3% - 5.8% higher than that of YOLO - series models. It has strong generalization ability and is expected to contribute to improving the efficiency and automation level of agricultural production.
Why it matches plant phenotyping methodsアルストロメリア花の成熟度を画像から検出・分類する深層学習手法を開発し、データセット上で比較評価しており、植物表現型取得が中心である。
abstractThis study proposes a deep - learning - based object detection framework, the Morado Flower Detection Network (MFDN)
Reproduction assets foundThe paper's core phenotyping measurements (flower maturity detection/classification) are performed on the publicly released morado_5may dataset of 414 annotated Alstroemeria Morado flower images (5,439 bounding-box labels, raw/ripe classes), which the authors state is publicly available on Kaggle. The YOLOv5/ultralytcsDataset · publicLentsch T. (2021). Available online at: https://www.kaggle.com/datasets/teddevrieslentsch/morado-5may (Accessed July 20, 2021)Open asset ↗Kaggle · teddevrieslentsch/morado-5mayhtml-lines:544-586Dataset · publicthis study selected the publicly available morado_5may dataset (Lentsch, 2021) for experimentsOpen asset ↗morado_5mayhtml-lines:97-149Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Sept 2025Computers and Electronics in Agriculture.
Deep learning (DL) models have shown exceptional accuracy in plant disease identification, yet their practical utility for farmers remains limited due to a lack of professional and actionable guidance. To bridge this gap, we developed CDIP-ChatGLM3, an innovative framework that synergizes a state-of-the-art DL-based computer vision model with a fine-tuned large language model (LLM), designed specifically for Crop Disease Identification and Prescription (CDIP). EfficientNet-B2, evaluated among 10 DL models across 48 diseases and 13 crops, achieved top performance with 97.97 % ± 0.16 % accuracy at a 95 % confidence level. Building on this, we fine-tuned the widely used ChatGLM3-6B LLM using Low-Rank Adaptation (LoRA) and Freeze-tuning, optimizing its ability to deliver precise disease management prescriptions. We compared two training strategies—multi-task learning (MTL) and Dual-stage Mixed Fine-Tuning (DMT)—using a different combination of domain-specific and general datasets. Freeze-tuning with DMT led to substantial performance gains, achieving a 33.16 % improvement in BLEU-4 and a 27.04 % increase in the Average ROUGE F-score, surpassing the original model and state-of-the-art competitors such as Qwen-max, Llama-3.1-405B-Instruct, and GPT-4o. The dual-model architecture of CDIP-ChatGLM3 leverages the complementary strengths of computer vision for image-based disease detection and LLMs for contextualized, domain-specific text generation, offering unmatched specialization, interpretability, and scalability. Unlike resource-intensive multimodal models that blend modalities, our dual-model approach maintains efficiency while achieving superior performance in both disease identification and actionable prescription generation.
Why it matches plant phenotyping methods植物病害画像から病害状態を推定するコンピュータビジョン手法の開発・比較検証が中心であり、処方生成も含む実用的なソフトウェア枠組みである。
abstractEfficientNet-B2, evaluated among 10 DL models across 48 diseases and 13 crops, achieved top performance with 97.97 % ± 0.16 % accuracy at a 95 % confidence level.
Background Accurate sorghum spike detection is critical for monitoring growth conditions, accurately predicting yield, and ensuring food security. Deep learning models have improved the accuracy of spike detection thanks to advances in artificial intelligence. However, the dense distribution of sorghum spikes, variable sizes and complex background information in UAV images make detection and counting difficult. Methods We propose a multiscale and oriented sorghum spike detection and counting model in UAV images (MOSSNet). The model creates a Deformable Convolution Spatial Attention (DCSA) module to improve the network's ability to capture small sorghum spike features. It also integrated Circular Smooth Labels (CSL) to effectively represent morphological features. The model also employs a Wise IoU-based localization loss function to improve network loss. Results Results show that MOSSNet accurately counts sorghum spike under field conditions, achieving mAP of 90.3%. MOSSNet shows excellent performance in predicting spike orientation, with RMSEa and MAEa of 14.6 and 12.5 respectively, outperforming other directional detection algorithms. Compared to general object detection algorithms which output horizonal detection boxes, MOSSNet also demonstrates high efficiency in counting sorghum spikes, with RMSE and MAE values of 9.3 and 8.1, respectively. Discussion Sorghum spikes have a slender morphology and their orientation angles tend to be highly variable in natural environments. MOSSNet 's ability has been proved to handle complex scenes with dense distribution, strong occlusion, and complicated background information. This highlights its robustness and generalizability, making it an effective tool for sorghum spike detection and counting. In the future, we plan to further explore the detection capabilities of MOSSNet at different stages of sorghum growth. This will involve implementing object model improvements tailored to each stage and developing a real-time workflow for accurate sorghum spike detection and counting.
Why it matches plant phenotyping methodsUAV画像からソルガム穂の検出・計数・向き推定を行う深層学習手法を開発し、精度評価も実施しており、植物形態形質の取得手法が中心である。
abstractWe propose a multiscale and oriented sorghum spike detection and counting model in UAV images (MOSSNet).
Field / plotLeafClassificationObject detectionSegmentationStress / disease detectionDisease symptoms / severity
Due to the rapid growth of population and increased demand of food, agriculture plays an essential role worldwide. Here, the quality as well as the quantity of the agricultural production is greatly affected by plant disease. Recently, various advancements in plant disease have been greatly identified by considering deep learning models to provide promising outcomes. The disease symptoms appear on the leaves and are easily identified through recent developments in computer vision and deep learning techniques. Classifying the plant disease at the initial stage becomes a tedious process that impacts the performance of traditional models. Also, conventional techniques do not work properly in large image datasets, affecting the model’s efficiency while focusing on a wide variety of conditions. Hence, this paper aims to implement an efficient plant disease detection and classification approach with deep learning methods. Initially, the required data from publicly available sources are collected and provided to the image segmentation phase. Here, the developed Dilated Dense R2Unet (DD-R2Unet) technique is utilized to segment the appropriate regions in the collected plant disease-affected images. Further, the segmented images are given to the plant disease classification model. In this phase, the developed framework utilized the Adaptive DenseNet with Attention-based Capsule Network (Ada-D-ACapsNet). Later, several hyperparameters in the implemented Ada-D-ACapsNet are tuned using a novel optimization technique named Enhanced Controlling Parameter-based Humboldt Squid Optimization Algorithm (ECP-HSOA) to enhance the plant disease classification efficiency. Finally, the plant disease classified outcomes are attained from the developed Ada-D-ACapsNet. Further, various performance analysis is executed in the implemented plant disease detection and classification approach over classical models. During the performance evaluation, the developed model shows 93.88%, 99.45%, and 93.89% in terms of accuracy, specificity and Negative Predictive Value (NPV). This performance enhancement facilitates accurate plant disease classification promptly.
Why it matches plant phenotyping methods植物病害の症状を画像からセグメンテーションし、病害状態を分類する画像ベースの表現型推定手法が研究の中心であり、技術比較による性能評価も行っている。
abstractthis paper aims to implement an efficient plant disease detection and classification approach with deep learning methods.
Abstract Early-stage, accurate and high-throughput phenotyping through leaf area estimation is critical for future rapeseed breeding, but faces two key constraints: expensive data annotation and persistent challenge of leaf occlusion. To address these issues, we present a data-efficient deep learning framework using smartphone-captured top-down RGB images for rapeseed leaf area quantification. Our approach utilizes a two-stage strategy where a Vision Transformer (ViT) backbone is first pre-trained on a large, aggregated corpus of diverse, non-rapeseed public plant datasets using the DINOv2 self-supervised learning method. This pre-trained model is then fine-tuned on a custom rapeseed dataset using a novel Canopy-Mix data augmentation technique to handle fragmented views analogous to occlusion, and a hybrid loss function combining Smooth L1 and Log-Cosh for robust convergence. Through rigorous 5-fold cross-validation, our proposed model achieved state-of-the-art predictive performance (Coefficient of Determination, R$^2$=0.805). What’s more, the predicted leaf area demonstrated a remarkably strong correlation with both fresh weight (r=0.900) and dry weight (r=0.885). The model significantly outperformed a range of baselines, including models trained from scratch, those pre-trained on ImageNet, and a heuristic method based on manually annotated bounding boxes. Ablation studies confirmed the essential contribution of each component, while qualitative analysis of attention maps demonstrated the model's ability to precisely localize the leaf canopy and ignore background distractors. This study demonstrates that domain-specific self-supervised pre-training offers a powerful solution to overcome data limitations in agricultural vision, providing a robust and scalable tool for non-destructive phenotyping that can potentially accelerate the rapeseed breeding cycle.
Why it matches plant phenotyping methods画像から rapeseed の葉面積を推定する計算・画像ベースの表現型計測手法を開発し、交差検証、ベースライン比較、アブレーションで技術的に評価しているため、方法が研究の中心である。
abstractwe present a data-efficient deep learning framework using smartphone-captured top-down RGB images for rapeseed leaf area quantification.
Background: Cotton is an important crop globally and early detection of plant diseases is crucial for maintaining yields. Traditional methods for disease detection are manual and inefficient, highlighting the need for advanced technology like AI to enhance productivity. Methods: The study utilized the Inception-v3 deep learning model along with techniques such as transfer learning and hyper-parameter tuning. These approaches helped design an efficient system to classify whether a cotton plant is healthy or diseased. Comparisons were made with other pre-trained models like VGG16, ResNet50 and ResNet152V2. Result: The Inception-v3 model showed exceptional performance: • Achieved 87.52% accuracy without tuning. • Achieved 98.85% accuracy after hyper-parameter tuning, marking an improvement of ~11%. This approach also demonstrated faster and more precise predictions for diseases like bacterial blight, army worms and aphids. It supports sustainable farming by reducing chemical usage while maintaining crop quality and yield.
Why it matches plant phenotyping methods綿花の健康・罹病状態を画像ベースの深層学習で分類する手法が研究の中心であり、植物病害状態のフェノタイピング手法に該当する。
abstractThe study utilized the Inception-v3 deep learning model along with techniques such as transfer learning and hyper-parameter tuning.
Rice diseases pose a severe threat to global food security, while traditional detection methods suffer from low efficiency and dependence on manual expertise. To address the challenges of insufficient feature extraction and poor multi-scale disease adaptability in existing deep learning approaches under complex field environments, this study proposes ADAM-DETR, a rice disease detection algorithm based on improved RT-DETR. We constructed the RiDDET-5 dataset containing 9,303 images covering five major disease categories. The algorithm innovatively designs three core modules: the AdaptiveVision Network (AVN) backbone for enhanced feature extraction, the Dual-Domain Enhanced Transformer (DDET) module for spatiotemporal-frequency domain collaboration, and the Adaptive Multi-scale Feature Model (AMFM) for improved feature fusion. Experimental results demonstrate that ADAM-DETR achieves 94.76% mAP@50 on the RiDDET-5 dataset, representing a 3.25% improvement over the baseline, and 83.32% mAP@50 on the public Kamatis dataset with a 2.19% enhancement, validating its cross-domain generalization capability. The algorithm requires only 42.8G FLOPs with 14.3M parameters, achieving an optimal balance between accuracy and efficiency, providing an effective technical solution for disease monitoring in smart agriculture.
Why it matches plant phenotyping methodsイネ葉の病徴を画像から検出する深層学習手法を開発し、データセット上で性能評価しており、植物病害状態のフェノタイピング手法が中心である。
abstractthis study proposes ADAM-DETR, a rice disease detection algorithm based on improved RT-DETR.
This study presents an ensemble-based approach for detecting and classifying sesame diseases using deep convolutional neural networks (CNNs). Sesame is a crucial oilseed crop that faces significant challenges from various diseases, including phyllody and bacterial blight, which adversely affect crop yield and quality. The objective of this research is to develop a robust and accurate model for identifying these diseases, leveraging the strengths of three state-of-the-art CNN architectures: ResNet-50, DenseNet-121, and Xception. The proposed ensemble model integrates these individual networks to enhance classification accuracy and improve generalization across diverse datasets. A comprehensive dataset of sesame leaf images, representing healthy, phyllody, and bacterial blight conditions was utilized to train and evaluate the models. The ensemble approach achieved an impressive overall accuracy of 96.83%, demonstrating superior performance in accurately classifying the different leaf conditions. The results highlight the effectiveness of combining multiple deep learning models, which allows for the extraction of diverse feature representations and decision-making strategies. This thesis also discusses the advantages of the ensemble methodology, including improved robustness to variations in disease symptoms and enhanced adaptability to changing agricultural practices. The findings of this research have significant implications for precision agriculture. They offer a reliable tool for the early detection and classification of sesame diseases. By enabling timely interventions, this ensemble-based framework can contribute to the sustainability and productivity of sesame cultivation, ultimately supporting food security and agricultural resilience.
Why it matches plant phenotyping methodsゴマ葉画像から病害状態を推定するCNN分類手法の開発と評価が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThis study presents an ensemble-based approach for detecting and classifying sesame diseases using deep convolutional neural networks (CNNs).
Agriculture plays a critical role in the global economy, providing livelihoods and ensuring food security for billions. Progress in agricultural techniques has helped boost crop yield, along with a growing need for precise disease monitoring solutions. This requires accurate, efficient, and timely disease detection methods. The research presented in this paper addresses this need by analyzing a hybrid model built using Graph Attention Network (GAT) and Graph Convolution Network (GCN) models. The integration of these models has witnessed a notable improvement in the accuracy of leaf disease classification. GCN has been widely used for learning from graph-structured data, and GAT enhances this by incorporating attention mechanisms to focus on the most important neighbors. The methodology incorporates superpixel segmentation for efficient feature extraction, partitioning images into meaningful, homogeneous regions that better capture localized features. The robustness of the model is further enhanced by the edge augmentation technique. The edge augmentation technique in the context of graph has introduced a significant degree of generalization in the detection capabilities of the model as analyzed on apple, potato, and sugarcane leaves. To further optimize training, weight initialization techniques are applied. The hybrid model is evaluated against the individual performance of the GCN and GAT models and the hybrid model achieved a precision of 0.9822, recall of 0.9818, and F1-score of 0.9818 in apple leaf disease classification, a precision of 0.9746, recall of 0.9744, and F1-score of 0.9743 in potato leaf disease classification, and a precision of 0.8801, recall of 0.8801, and F1-score of 0.8799 in sugarcane leaf disease classification. The results indicate that the model is effective and consistent in identifying leaf diseases in plants.
Why it matches plant phenotyping methods植物葉画像から病害状態を分類するGAT-GCNモデルを開発・比較評価しており、病害表現型の抽出手法が中心である。
abstractThe methodology incorporates superpixel segmentation for efficient feature extraction, partitioning images into meaningful, homogeneous regions that better capture localized features.
Reproduction assets foundThe paper evaluates its GAT-GCN hybrid leaf disease classifier on three public leaf image datasets. Two of them (apple and potato) are cited with explicit Kaggle URLs that match allowed_urls entries; the sugarcane dataset is cited without a public URL. No author code or model release is mentioned.Dataset · publicAdvanced Comput. Sci. Appl.
10 ( 8 ), 486 – 492 . doi:
10.14569/IJACSA.2019.0100863
Alsayed A. Alsabei A. Muhammad A.
( 2021 ).
Classification of apple tree leaves diseases using deep learning methods
. Int. J. Comput. Sci. Network Secur.
21 , 324 – 330 .
Antor M. H.
( 2020 ). Apple leaf diseases dataset . Available online at: https://www.kaggle.com/datasets/mhantor/apple-leaf-diseases (Accessed October 13, 2024 ).
Bansal P. Kumar R. Kumar S.
( 2021 ).
Disease detection in apple leaves using deep convolutional neural network
. Agriculture
11 , 617 . doi:
10.3390/agriculture11070617
Bera A. Bhattacharjee D. Krejcar O.
( 2024 ).
Pnd-net: plant nutrition deficiency and disease classification usOpen asset ↗Kaggle · mhantor/apple-leaf-diseaseslines:548-708Dataset · publicnt. J. Res. Eng.
5 , 516 – 523 . doi:
10.21276/ijre.2018.5.9.4
Peng Y. Wang Y.
( 2022 ).
Leaf disease image retrieval with object detection and deep metric learning
. Front. Plant Sci.
13 , 963302 . doi:
10.3389/fpls.2022.963302
, PMID:
36176678
PMC9513793
Putra M. A.
( 2020 ). Potato leaf disease dataset . Available online at: https://www.kaggle.com/datasets/muhammadardiputra/potato-leaf-disease-dataset (Accessed October 13, 2024 ).
Rao S. U. M. Sreekala K. Rao P. Srinivas Shirisha N. Srinivas G. Sreedevi E.
( 2024 ).
Plant disease classification using novel integration of deep learning cnn and graph convolutional networks
. Indonesian J. Electrical Eng. Comput. Sci.
36 , 1721 – 1730 .
RathOpen asset ↗Kaggle · muhammadardiputra/potato-leaf-disease-datasetlines:709-821Plant phenotyping relevance match · UnverifiedEurope PMC · bioRxiv · checked 6 Sept 2026
Plants engineered with synthetic genetic programs can transform how we monitor and manage the extension of crop pests and diseases. Here, we establish a bioluminescent platform in Nicotiana benthamiana for autonomous viral sensing based on the fungal bioluminescence pathway (FBP). We first demonstrate that recombinant viruses can deliver missing pathway components, enabling spatially resolved tracking of infection dynamics. Leveraging this starting point, we developed a dual-output sentinel circuit that uses a protease-responsive Bioluminescence Resonance Energy Transfer (BRET) module to report infection through a virus-triggered spectral shift in luminescence. In the absence of infection, plants emit a stable yellow glow indicating system integrity. Upon infection with potyviruses, cleavage of the BRET fusion by the virus-encoded NIa-Pro protease activates a distinct colour change detectable with low-cost imaging. This modular design is compatible with other pathogens carrying specific proteases and supports future multiplexing strategies. Our results highlight the potential of synthetic sentinel gene circuits as autonomous biosensors for precision crop protection.
Why it matches plant phenotyping methods植物のウイルス感染状態を発光変化として検出するセンチネル回路と低コスト画像診断プラットフォームの開発が中心であり、病害状態のフェノタイピング手法に該当する。
abstractHere, we establish a bioluminescent platform in Nicotiana benthamiana for autonomous viral sensing based on the fungal bioluminescence pathway (FBP).
Green crops like guava, unlike the majority that can be distinctly separated from the background by color contrast, often share color characteristics with the surrounding leaves, making the accuracy of crop detection and further pixel-level prediction decrease in complex natural environment. Therefore, this work took the texture and boundaries of crops as the focus, proposed a Gabor based texture consistency loss and a reverse attention module (RAM). Meanwhile, both a receptive field module (RFM) and a mutual fusion decoder (MFD) were proposed to enhance the utilization of semantic information. Finally, a stepwise prediction refinement method with the deep prediction map as prior information was designed in the model framework, realizing a further enhancement of the inference ability. In the ablation experiments, this work verified the effectiveness of the proposed improvements step by step using Classification Evaluation Metrics and provided the visualization of the reverse attention. In the comparative experiments, this model demonstrated its advantages in contrast to state-of-the-arts such as U-Net, SETR, and SegFormer. The Acc and IoU reached 0.9954 and 0.9420, exceeding those of SegFormer by 0.0087 and 0.0119 respectively, demonstrating its application potential for agricultural robot visual systems. Moreover, to further demonstrate the inference capability of the proposed model, we conducted validation on two open-source building extraction datasets, WHU and MBD, which have similar task difficulties, and achieved significant results.
Why it matches plant phenotyping methodsグアバ果実の画素レベル分割を目的とする画像解析手法を開発・比較検証しており、植物器官の位置・形状を抽出する方法が中心である。
abstractproposed a Gabor based texture consistency loss and a reverse attention module (RAM)
PURPOSE: Bacterial blight poses a significant threat to red kidney bean growth, often leading to substantial yield losses. Real-time monitoring of this disease is crucial for effective prevention and control, ensuring optimal yield. This study proposes a hyperspectral-based approach to assess the the bacterial blight disease in red kidney beans. METHODS: In this study, canopy hyperspectral data from two experimental areas were collected, and five spectral preprocessing methods—multiple scattering correction (MSC), standard normal variation (SNV), first-order derivative (FD), second-order derivative (SD), and logarithmic transformation (LOG)—were applied to the raw spectra (R). Feature bands were extracted using a combination of the competitive adaptive reweighted sampling (CARS) and successive projection algorithm (SPA). Disease severity classification models were constructed using support vector machine (SVM) and partial least squares discriminant analysis (PLS-LDA), while estimation models were developed using support vector regression (SVR) and partial least squares regression (PLSR). RESULTS: Results demonstrated that FD preprocessing most effectively enhanced spectral features for bacterial blight detection, with sensitive bands optimally extracted using the CARS-SPA algorithm. The bands centered at 750 nm and 945 nm were identified as the most sensitive across all preprocessing methods. For condition index estimation, the PLSR model performed best, with FD preprocessing achieving R² values of 0.883 (modeling set) and 0.863 (validation set), and RMSE values of 0.072 and 0.083, respectively. CONCLUSIONS: These findings highlight the potential of hyperspectral technology, combined with feature extraction and machine learning algorithms, for efficient and accurate detection of bacterial blight in red kidney beans. This study provides a methodological and technical framework for monitoring other crops and diseases.
Why it matches plant phenotyping methodsハイパースペクトルデータからインゲンマメの病害状態・重症度を推定し、前処理、特徴帯抽出、分類・回帰モデルを検証することが研究の中心であるため、植物フェノタイピング手法として採用。
abstractThis study proposes a hyperspectral-based approach to assess the the bacterial blight disease in red kidney beans.
Grapes are widely cultivated fruit crops, essential for fresh consumption, winemaking and dried product production. However, their yield and quality are significantly impacted by various fungal diseases. This paper provides a large dataset of 2,726 high-quality grape leaf disease images collected from grapes farm of Nashik, India in two years of span 2023 to 2025. The dataset is precisely annotated under the guidance and observation of agriculture domain expert and organized in a well-defined folder structure. The dataset captures the two major categories healthy leaves and unhealthy leaves, during cultivation period. A primary directory containing two main classes Heathy Leaf Images and Unhealthy Leaf images. Further unhealthy class is divided into three subfolders for disease class, namely Downy Mildew, Powdery Mildew and Bacterial Leaf Spot. These are the major fungal disease observed on grape crop causes substantially crop losses and ultimately impact on the yield production. Timely identification of these diseases can significantly reduce the risk of crop loss and help to improve quality of fruit with maximum yield production. This High-quality annotated image dataset can help to design standard advanced AI models for automated disease detection, classification, and prediction. The dataset was validated through a transfer learning approach using the ResNet-18 algorithm and demonstrated the remarkable classification accuracy of 96 %. These results validate the dataset’s quality and its suitability for deep learning-based grape disease detection. Overall, this open-access resource provides a valuable foundation for computer vision, machine learning, and agricultural technology researchers aims to enhance disease management practices in grape production. thus, this is an effective source of data for future studies and real-world applications in sustainable grape production.
Why it matches plant phenotyping methodsブドウ葉の健康状態と病害を画像として収集・注釈したデータセットが研究の中心であり、植物病害状態を直接評価する再利用可能な資源として構築・検証されている。
abstractThis paper provides a large dataset of 2,726 high-quality grape leaf disease images collected from grapes farm of Nashik, India in two years of span 2023 to 2025.
Abstract Field trials are critical in the development of genetically modified and genome-edited biotechnology plants to evaluate the growth and yield of breeding lines and to test commercial viability or any potential off-target effects. In Australia, conducting field trials of biotechnology derived crops requires compliance with federally mandated regulations, including strict protocols for forecasting flowering times. Conventional practices are based on time consuming, subjective and costly visual field inspections of individual wheat plants at respective growth stages (Zadoks growth stages Z37, Z39, and Z41). To enable automatic forecasting, hyperspectral and RGB images were captured in the greenhouse, and hyperspectral reflectance data were acquired in a semi-natural environment. In the greenhouse, imaging was conducted under controlled lighting with a fixed top-view setup; in semi-natural environments, spectral data were collected manually from multiple oblique angles under supplemented natural light. Support Vector Machine classification achieved F1 scores above 0.8 for anthesis prediction when reflectance data were transformed using Standard Normal Variate, Hyper-hue, or Principal Component Analysis. After feature selection, F1 scores above 0.75 could be achieved with only five wavelengths. Furthermore, the SNV transformation demonstrated robust performance under limited training conditions, maintaining high classification accuracy and strong generalizability across varying data sizes. These findings highlight the effectiveness of transformation-enriched data and optimized feature selection for accurate growth stage classification. This study provides a low-cost approach to alleviate manual inspection burdens, improve regulatory compliance, and increase biosafety during biotechnology field trial practices.
Why it matches plant phenotyping methods個体コムギの生殖生長段階をハイパースペクトル/RGB画像と機械学習で自動推定する方法が研究の中心であり、検証性能も報告しているため。
titleHyperspectral-Based Classification of Individual Wheat Plants into Fine-Scale Reproductive Stages for Anthesis Prediction
Plant diseases significantly impact agricultural productivity and food security, making early and accurate disease detection crucial for effective crop management. Traditional disease identification methods rely on manual inspection, which is time-consuming, labor-intensive, and prone to errors. Recent advancements in artificial intelligence (AI) and computer vision have enabled automated plant disease detection using deep learning techniques. This paper explores various machine learning approaches, including convolutional neural networks (CNNs), to classify and detect plant diseases from leaf images. The PlantVillage dataset of diseased and healthy plant images is used to train and evaluate the model. The proposed system achieves high accuracy in distinguishing different plant diseases, demonstrating its potential for real-time application in precision agriculture. By integrating AI-driven plant disease detection with smartphone applications or IoT-based monitoring systems, farmers can receive instant alerts and take timely corrective actions, ultimately reducing crop losses and improving yield quality. Key Words: artificial intelligence, convolutional neural networks, computer vision, internet of things(IoT), deep learning, machine learning
Why it matches plant phenotyping methods葉画像から植物病害を分類・検出する画像ベースの植物状態推定法が研究の中心であり、モデルの訓練・評価も行っているため含める。
abstractThis paper explores various machine learning approaches, including convolutional neural networks (CNNs), to classify and detect plant diseases from leaf images.
Abstract Ensuring food security is a crucial priority for nations worldwide, but plant diseases significantly hinder this objective through their impacts on agricultural productivity. Chili pepper (Capsicum spp.) is a major crop in West Africa, including in Benin. However, its production is challenged by diseases such as anthracnose and Tomato Yellow Leaf Curl Virus (TYLCV), which severely impact yields and farmer livelihoods. While traditional methods for disease detection and management have been commonly used, they are no longer sufficient to combat rising pest infestations and declining agricultural productivity. To tackle this issue, we built a comprehensive dataset of 213 images of anthracnose-affected leaves, 202 images of TYLCV-infected leaves, and 119 images of healthy leaves, collected under diverse environmental conditions in Benin. The study compared the performance of thirteen (13) deep learning models, including YOLOv8, MobileNetV2, and DenseNet121, for the classification of chili diseases using transfer learning techniques. Performance was evaluated using metrics such as Accuracy, Precision, Recall, and F1-Score. Results show that YOLOv8 outperformed other models in real-time detection and localization of leaf diseases, achieving a mean Average Precision (mAP@0.5) of 0.995 and mAP@0.5-0.95 of 0.941, with precision and recall exceeding 99%. Among CNN models, MobileNetV2 and DenseNet121 achieved 96.25% accuracy. These findings demonstrate that deep learning models, particularly YOLOv8, hold immense potential for real-time, automated detection of chili pepper diseases. Future research should focus on expanding datasets, integrating climatic variations, and improving disease severity assessment for enhanced agricultural sustainability.
Why it matches plant phenotyping methodsトウガラシ葉の病徴を画像から分類・検出する深層学習手法を開発・比較検証しており、植物の病害状態のフェノタイピングが研究の中心です。
abstractwe built a comprehensive dataset of 213 images of anthracnose-affected leaves, 202 images of TYLCV-infected leaves, and 119 images of healthy leaves
Abstract The detection of plant leaf diseases is essential for ensuring crop health and productivity. This study uses a comprehensive merged dataset, including the Mendeley Plant Leaf Dataset, which includes 22 classes, while the Jute and Mulberry datasets provide 2 classes each, representing healthy and diseased categories from various species. The final dataset, consisting of 26 classes, was augmented to ensure 500 training samples per class. In this study, the Segment Anything Model (SAM) was employed for zero-shot segmentation, enabling the automatic extraction of precise regions of interest (ROIs) from leaf images without the need for task-specific training for region-focused analysis. An EfficientNetB7- Multi-Head Attention (MHA) model that combines EfficientNetB7 with MHA was used to improve plant disease classification across 26 distinct classes. The proposed model is designed to handle the variety and diversity of leaf diseases, achieving a high classification accuracy of 98.01%, with precision, recall, and F1-scores all exceeding 97.9%. The integration of MHA allows the model to focus on disease-specific features, significantly enhancing its ability to generalize across diverse agricultural settings while maintaining scalability. Experimental results show that the EfficientNetB7-MHA model consistently outperforms several state-of-the-art (SOTA) models in terms of accuracy and robustness, making it a promising tool for precision agriculture. Explainable AI (XAI) including the use of Grad-CAM was utilized to detect the precise regions of interest for each class providing interpretability and insights into the model’s decision-making process. Finally, to demonstrate the model’s performance, a web application was developed that displays the predicted outputs when given different images of healthy and diseased leaves from the dataset. This comprehensive approach demonstrates significant potential for improving agricultural disease management through accurate, scalable, interpretable, and efficient disease detection.
Why it matches plant phenotyping methods植物葉画像から病害状態をセグメンテーション・分類する手法が研究の中心であり、植物病害表現型の画像ベース推定に該当する。
abstractthe Segment Anything Model (SAM) was employed for zero-shot segmentation, enabling the automatic extraction of precise regions of interest (ROIs) from leaf images
This study aims to utilise natural variation in pea seed composition from NordGen collections to identify key traits for optimized plant-based ingredients functionality while minimizing refined extraction processes. Given the impracticality of chemically analysing 1942 accessions, an algorithm-assisted approach was employed, using image-derived features and datasets to pre-select 51 accessions. Protein content, thousand kernel weight, perimeter, and G-value were determined as primary criteria via PCA, capturing variations in protein composition and other key components. Protein and starch content ranged from 21.2 to 36.9 % and 21.0-48.1 %, respectively. Image analysis linked geometry to composition, aiding pea selection and application. X-ray scattering differentiates peas based on starch structure. Proteomic profiling revealed that legumin and vicilin varied most, with legumin dominant in smooth peas and vicilin in wrinkled ones, enabling control of their ratio through selection. This study highlights the potential of using natural variation of seed composition for less-refined plant-based ingredients for various applications.
Why it matches plant phenotyping methods画像由来特徴量とアルゴリズムを用いて多数のエンドウ遺伝資源から種子形質・組成を推定し、化学分析対象を選抜するワークフローが研究の中心であるため、植物フェノタイピング手法の実質的応用と判断します。
abstractGiven the impracticality of chemically analysing 1942 accessions, an algorithm-assisted approach was employed, using image-derived features and datasets to pre-select 51 accessions.
Plant disease classification plays a vital role in advancing modern agriculture, transitioning from traditional manual diagnosis to intelligent, automated systems powered by machine learning. Historically, identification of plant diseases relied on visual inspections, expert advice, and lab tests— methods that were accurate for small-scale use but often subjective, slow, and inconsistent. These limitations resulted in delayed treatment and substantial crop losses, highlighting the inefficiency and high cost of conventional approaches, especially at scale. To address this, the proposed system introduces an innovative machine learning-based solution capable of accurately classifying plant diseases using sparse and categorical IoT data. It incorporates comprehensive data preprocessing techniques, including handling missing values, label encoding, and class imbalance correction using the Synthetic Minority Oversampling Technique (SMOTE), ensuring a high-quality dataset for model training. The classification pipeline integrates multiple models—Gaussian Naive Bayes, Support Vector Machines, K-Nearest Neighbors, and a novel Decision Tree Classifier. Among these, the Decision Tree model demonstrated superior performance, achieving an accuracy of 99.07% with precision, recall, and F1-scores consistently exceeding 98%, confirming its robustness and reliability. This research is significant in offering real-time, data-driven diagnostics that enable early disease detection and precise pesticide recommendations. It not only improves crop yield and reduces financial losses but also promotes environmentally sustainable agriculture by limiting excessive chemical usage. By overcoming the limitations of traditional methods—such as subjectivity, delay, and lack of scalability—this system presents a transformative approach to plant disease management through advanced machine learning, marking a pivotal shift toward precision agriculture.
Why it matches plant phenotyping methods植物病害をIoTデータから機械学習で自動分類する手法が研究の中心であり、感染植物の病害状態を推定する植物フェノタイピング手法に該当する。
abstractthe proposed system introduces an innovative machine learning-based solution capable of accurately classifying plant diseases using sparse and categorical IoT data.
Rice leaf disease poses a significant threat to global food security and ecological stability. While existing studies predominantly concentrate on detecting symptoms after visible lesions emerge, early-stage disease features—which are often subtle—are critical for timely intervention. This paper introduces a novel detection approach based on an enhanced YOLOv11n architecture, tailored for the precise and efficient recognition of early-stage rice leaf disease indicators. To address the limitations of traditional detection techniques in identifying fine-grained features, we propose three key modules: the Multi-branch Large-kernel Fusion Depthwise (MLFD) module, the Multi-scale Dilated Transformer-based Attention (MDTA) module, and the Lightweight Detection Head (Lo-Head). The MLFD module enhances multi-scale feature extraction via parallel pathways and depthwise convolutions with large kernels. The MDTA module integrates both spatial and channel attention through a multi-head mechanism, improving the representation of diverse lesion features. Meanwhile, the Lo-Head detection head significantly reduces model complexity and parameter count, facilitating deployment on edge devices without compromising accuracy. Experimental results show that the proposed network achieves substantial performance gains. At an input resolution of 640×640, the model reaches a mean Average Precision (mAP@50:95) of 0.7927—an increase of 1.84 percentage points over the baseline YOLOv11n. It also outperforms Faster R-CNN, YOLOv5n, YOLOv8n, and YOLOv10n by 17%, 7.2%, 3%, and 2.5% respectively, while maintaining a low computational load of 6.2 GFLOPs and 2.66M parameters. These findings underscore the model’s potential for real-world agricultural applications, particularly in enabling early detection and precise disease control. The proposed method represents a step toward proactive plant health monitoring and precision agriculture.
Why it matches plant phenotyping methodsイネ葉の病斑という植物状態を画像から検出する新規深層学習手法を開発し、既存モデルとの性能比較・検証を行っており、表現型取得が中心である。
abstractThis paper introduces a novel detection approach based on an enhanced YOLOv11n architecture, tailored for the precise and efficient recognition of early-stage rice leaf disease indicators.
AppleField / plotFruitPhysiological trait estimation2D/3D reconstructionGrowth / development / phenology
The full view of the apples in the orchard is often obscured by leaves and trunks, making it challenging to accurately determine their ripeness, whilst it is an essential yet difficult task for apple-harvesting robots. Within this context, we propose a novel method to address two critical challenges: ripeness determination and in-field occlusion. The proposed method is trained in a self-supervised manner on a dataset consisting of less than 1% labelled images and the rest of unlabelled images. It is made up of three key parts: a reconstructor, a feature extractor, and a predictor. The reconstructor is designed to reconstruct the missing parts of occluded apples. The feature extractor is introduced to learn ripeness-related features from the vast number of unlabelled images. Unlike the previous approaches classifying the fruit ripeness into several discrete categories, the predictor uses the learned features to generate a continuous ripeness score in the range between 0.0 and 1.0, thus eliminating the need to subjectively pre-define ripeness stages and offering end-users the flexibility to make their own decisions. Experimental results comparing our method to another method with different settings show that our method achieves the best Structural Similarity Index Measure (SSIM) of 0.75 and the second-best Peak-Signal-to-Noise Ratio (PSNR) of 25.36 for reconstructing missing apple parts, whilst using the fewest 86.3M parameters. Besides, our method outperforms 15 other self-supervised methods and even a supervised method in the ripeness score prediction, with the smallest score 0.0127 for fully unripe and the highest score 0.8933 for fully ripe apples. The results demonstrate the potential of our method to be incorporated with in-field robotic systems, enabling them to assess ripeness for selective harvesting effectively. It is helpful to monitor the overall ripeness of large orchards digitally, aid the decision-making processes and advance the goals of smart and precision agriculture.
Why it matches plant phenotyping methodsリンゴの遮蔽画像から連続的な成熟度スコアを推定する自己教師あり画像解析法を開発し、再構成性能と成熟度予測性能を比較検証しているため、植物フェノタイピング手法が中心である。
abstractwe propose a novel method to address two critical challenges: ripeness determination and in-field occlusion
CowpeaRootMorphology / geometry measurementRoot system architecture
Improving crop production in changing environments can be achieved through selective breeding; however, limited advanced root phenotyping and genotyping in early growth stages hinder assessing root architecture variation and diversity, despite its importance. Therefore, this study utilized advanced image phenotyping on a diverse set of 222 cowpea accessions, revealing significant variations in key phenotypic traits and the genomic regions influencing them. Our study revealed a total of 55 genes linked to major root traits. Among eight root traits-total root length (TRL), surface area (SA), average diameter (AD), root volume (RV), tip number (TN), fork number (FN), primary root length (PRL), and lateral root length (LRL), analyzed, seven significant single nucleotide polymorphisms (SNPs) demonstrated particularly strong associations with three key traits, including surface area (SA), tip number (TN), and fork number (FN). SA emerged as a significant trait, exhibiting considerable variation across the studied accessions. The mean SA was 59.59 cm 2 , with some genotypes surpassing 140.72 cm 2 . Further analysis identified two SNPs that showed significant association with SA, located on two distinct chromosomes: 3 and 11. Similarly, two significant SNPs associated with TN were found on chromosome 3, while three SNPs associated with FN were identified on chromosomes 2, 3, and 8. These findings significantly advance our understanding of the genetic foundations underlying important phenotypic traits in cowpeas, offering a robust framework for future genetic improvement initiatives. The results strongly suggest that implementing breeding programs focused on selecting root phenotypes could significantly enhance cowpea productivity across various environments.
Why it matches plant phenotyping methods根系形態を対象とした高度な画像フェノタイピングを多数アクセッションに適用し、複数の根形質を抽出・解析しているため、フェノタイピング手法の実質的な応用研究と判断する。
titleAdvanced High-Throughput Root Phenotyping and GWAS Identifies Key Genomic Regions in Cowpea During Vegetative Growth Stage.
Abstract Tomato leaf disease poses a significant threat to global agricultural productivity, underscoring the need for accurate and automated segmentation techniques for early detection and intervention. In this study, we proposed DSGSU-Net, an enhanced U-Net-based architecture explicitly designed for the precise segmentation of tomato leaf diseases. The model incorporates depthwise separable convolutions for efficient feature extraction, dilated convolutions in deeper layers for multi-scale context aggregation, and Ghost Sampling in the decoder for improved upsampling. To further enhance segmentation performance, a hybrid loss function combining Dice Loss and Focal Loss is utilized to manage class imbalance and enhance the boundary delineation. Experiments conducted on the PlantVillage dataset (bacterial spot class) demonstrated that DSGSU-Net achieved an accuracy of 0.9572, an F1-score of 0.8276,precision of 0.7156,recall of 0.9885, IoU of 0.7102, and a Dice coefficient of 0.9822. The results show that DSGSU-Net outperforms conventional U-Net models in segmentation accuracy and computational efficiency, making it a strong contender for practical use in precision agriculture and disease surveillance.
Why it matches plant phenotyping methodsトマト葉の病徴を画像からセグメンテーションするモデルを開発・比較しており、植物病害状態の表現型抽出が研究の中心である。
abstractwe proposed DSGSU-Net, an enhanced U-Net-based architecture explicitly designed for the precise segmentation of tomato leaf diseases.
Reproduction assets foundThe paper's tomato leaf disease segmentation study uses the public PlantVillage tomato leaf dataset (bacterial spot class) from Kaggle, explicitly declared in the Data Availability section. No author analysis code, trained model checkpoints, or custom mask annotations are stated as publicly available.Dataset · publicThe datasets generated and analyzed during the current study are available in the Kaggle repository: https://www.kaggle.
com/datasets/charuchaudhry/plantvillage-tomato-leaf-datasetOpen asset ↗Kaggle · plantvillage-tomato-leaf-datasetpdf-page:20 lines:1-51Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
The foremost task in agriculture is the decisive identification of citrus plants and the timely identification of diseases in the plants with the aim of improving the quality of crops and the yield. In this work, a machine learning algorithm focuses on image processing of citrus to solve issues that are significant and cause concern in agriculture. This work focus on the machine learning models like VGG 19 and VGG 16. In addition, dataset curation, data augmentation and various other methods were employed. The dataset used in this research is a composed one which is recorded in a comprehensive manner including the data of both the affected and healthy pieces of citrus fruits. The ensemble model utilised here to ensure the improvement of trained datasets. Reviewing the research on machine learning models indicates a possibility for accurate classification of the fruits and disease detection models of the fruit. The three contenders performed admirably, with VGG 19 dominating with 95.5% accuracy. In second place was CNN with 93.4% and VGG 16 trailing at 91.2%. Such models are recognisable, because they perform well in agricultural environments, thanks to their precision, recall, and F1 scores, which are all balanced properly. The models’ capacity to lessen the number of false alarms and misses is further assessed with the use of confusion matrices, which are of utmost importance in disease control. New developments in early disease diagnosis and detection of citrus fruits in agriculture may greatly enhance the health and productivity of crops. This research can be critical in increasing agricultural productivity while ensuring the environmental sustainability and health of growers and citrus crops in the long run.
Why it matches plant phenotyping methods柑橘の画像から健全・罹病状態を分類する機械学習・画像処理手法が研究の中心であり、植物病害状態のフェノタイピングに該当する。
titleEnhancing Citrus Plant Health through the Application of Image Processing Techniques for Disease Detection
Plants develop characteristic shoot architectures by extending branches at specific angles. Primary shoots bend in response to gravity and then adjust the orientation through an organ-straightening process to achieve a mechanically favorable shape. However, how plants integrate branch structure with the shoot architecture remains uncertain. Here, we examined the lateral branch morphology of Arabidopsis thaliana mutants for myosin XI motor proteins through a combination of three-dimensional reconstruction and temporal imaging. The wild type and myosin xif mutant formed S-shaped branches and gradually adjusted the branch angle upwards. The myosin xik mutant exhibited straighter and drooping branches and maintained branch angles. The myosin xif xik double mutant formed branches with irregular directional changes with fluctuating angles. These results suggest that MYOSIN XIk and XIf are required for the establishment of branch morphology through upward bending, stabilizing growth direction, and maintaining curvature.
Why it matches plant phenotyping methods三次元再構成と時系列画像による四次元フェノタイピングが、枝形態・角度・成長方向の定量的評価に中心的に用いられているため。
titleFour-dimensional phenotyping reveals MYOSIN XI-dependent establishment of branch morphology through upward- and stably-directed growth in Arabidopsis
The designed Project introduces an innovative autonomous robot for plant disease detection, harnessing the power of a Raspberry Pi, advanced imaging technology, and real time SMS alerts to revolutionize agricultural practices. Designed to navigate fields independently, this robot captures detailed images of plant leaves and employs sophisticated image processing algorithms to identify early signs of diseases, including fungal infections, bacterial blight, and nutrient deficiencies. When a potential disease is detected, the system sends instant SMS notifications to farmers, enabling immediate action to mitigate crop loss. Central to the design is the Raspberry Pi microcontroller, which orchestrates the robot’s operations and runs the detection algorithms. The high-resolution camera module plays a crucial role in ensuring accurate diagnosis, while the integrated GSM module facilitates seamless communication. Utilizing cutting-edge machine learning techniques, this system achieves high accuracy in disease recognition, even in diverse agricultural settings. Field tests have showcased its effectiveness, delivering rapid alerts and enhancing decision-making for farmers. By empowering growers with timely insights and proactive disease management, this robot not only promotes sustainable farming practices but also paves the way for smarter, technology driven agriculture.
Why it matches plant phenotyping methods葉画像と画像処理・機械学習を中核として植物病徴を検出する自律ロボットを開発しており、植物の病害状態を直接推定する方法が中心である。
abstractthis robot captures detailed images of plant leaves and employs sophisticated image processing algorithms to identify early signs of diseases
Plant leaf diseases cause significant impacts on agricultural production, hence earlier intervention is more effective with effective detection. In this work, machine learning is employed to detect five major tomato leaf diseases, including Mosaic Virus, Late Blight, Bacterial Spot, Powdery Mildew, Leaf Mold, and Tomato Training and model testing were done based on a dataset of 1,485 images. Classification accuracy demonstrates good performance with Precision, Recall, and F1-Score at 94.98% to 95.47%. The Support Ratio in different classes of diseases varied between 0.19 and 0.21, and the model, in every class of diseases, also possessed a similar accuracy of 98%. Moreover, an elaborate study of the classification performance vis-a-vis true positives, true negatives, false positives and false negatives proves how well the model can potentially reduce the errors in classification. The overall accuracy of the model is found to be 95.28%, suggesting that it is valid and efficient as an automated tool for disease identification. This system offers prompt and precise disease identification, allowing farmers to act proactively against crop damage. Utilizing machine learning methods, this study facilitates sustainable agriculture by better monitoring crop health and managing diseases, which ultimately leads to increased agricultural productivity.
Why it matches plant phenotyping methodsトマト葉の画像から病害状態を機械学習で分類し、画像データセットと性能指標によって自動判定法を評価しており、植物病害表現型の取得・抽出が中心である。
abstractmachine learning is employed to detect five major tomato leaf diseases
Background In response to the limited models for salt tolerance detection in wild rice, the subtle leaf features, and the difficulty in capturing salt stress characteristics, resulting in low recognition and detection rates and accuracy, a deep learning-based ST-YOLO wild rice seedling salt tolerance phenotype evaluation and identification model is proposed. Method In order to improve accuracy and achieve model lightweighting, a multi branch structure DBB (Diverse Branch Block) is used to replace the convolutional layers in the C2f module, and a reparameterization module C2f DBB is proposed to replace some C2f modules. Diversified feature extraction paths are introduced to enhance the ability of feature extraction; Introducing CAFM (Context Aware Feature Modulation) convolution and attention fusion modules into the backbone network to enhance feature representation capabilities while improving the fusion of features at various scales; Design a more flexible and effective spatial pyramid pooling layer using deformable convolution and spatial information enhancement modules to improve the model's ability to represent target features and detection accuracy. Results The experimental results show that the improved algorithm improves the average precision by 2.7% compared with the original network; the accuracy rate improves by 3.5%; and the recall rate improves by 4.9%. Conclusion The experimental results show that the improved model significantly improves in precision compared with the current mainstream model, and the model evaluates the salt tolerance level of wild rice varieties, and screens out a total of 2 varieties that are extremely salt tolerant and 7 varieties that are salt tolerant, which meets the real-time requirements, and has a certain reference value for the practical application.
Why it matches plant phenotyping methods深層学習モデルによる野生イネ幼苗の塩耐性表現型評価・識別が研究の中心であり、モデル改良と精度検証を実施しているため、植物フェノタイピング手法に該当する。
abstracta deep learning-based ST-YOLO wild rice seedling salt tolerance phenotype evaluation and identification model is proposed.
Food security and sustainable agriculture rely heavily on the timely detection and classification of plant diseases. In this study, we investigate the performance of the You Only Look Once (YOLO) object detection algorithm—specifically versions v5, v7, and v8—for identifying seven common tomato leaf diseases: Mosaic Virus, Leaf Miner, Septoria, Spider Mites, Early Blight, Yellow Leaf Curl Virus, and Late Blight. We trained and validated each YOLO variant using a comprehensive dataset comprising annotated images of diseased tomato leaves. YOLOv8 achieved the highest performance, with a mean Average Precision (mAP) of 85%, followed by YOLOv7 (84.7%) and YOLOv5 (83%). Additionally, YOLOv8 demonstrated the fastest inference time, indicating its suitability for real-time or near real-time disease detection applications. Our findings emphasize YOLOv8’s potential in enhancing agricultural productivity through accurate and efficient disease identification. The proposed framework offers practical implications for precision farming by aiding early disease management, optimizing crop yield, conserving resources, and promoting sustainable agricultural practices through advanced deep learning techniques.
Why it matches plant phenotyping methodsトマト葉の病徴を画像から検出・分類するYOLO手法を訓練・検証し、性能比較も行っており、植物病害状態の表現型取得が中心である。
abstractwe investigate the performance of the You Only Look Once (YOLO) object detection algorithm—specifically versions v5, v7, and v8—for identifying seven common tomato leaf diseases
Plant diseases pose significant challenges to farmers and the agricultural sector at large. However, early detection of plant diseases is crucial to mitigating their effects and preventing widespread damage, as outbreaks can severely impact the productivity and quality of crops. With advancements in technology, there are increasing opportunities for automating the monitoring and detection of disease outbreaks in plants. This study proposed a system designed to identify and monitor plant diseases using a transfer learning approach. Specifically, the study utilizes YOLOv7 and YOLOv8, two state-of-the-art models in the field of object detection. By fine-tuning these models on a dataset of plant leaf images, the system is able to accurately detect the presence of Bacteria, Fungi and Viral diseases such as Powdery Mildew, Angular Leaf Spot, Early blight and Tomato mosaic virus. The model's performance was evaluated using several metrics, including mean Average Precision (mAP), F1-score, Precision, and Recall, yielding values of 91.05, 89.40, 91.22, and 87.66, respectively. The result demonstrates the superior effectiveness and efficiency of YOLOv8 compared to other object detection methods, highlighting its potential for use in modern agricultural practices. The approach provides a scalable, automated solution for early any plant disease detection, contributing to enhanced crop yield, reduced reliance on manual monitoring, and supporting sustainable agricultural practices.
Why it matches plant phenotyping methods植物葉画像から病害の有無・種類を推定する画像ベースの病害表現型計測法をYOLOモデルで開発・評価しており、手法が研究の中心です。
abstractThis study proposed a system designed to identify and monitor plant diseases using a transfer learning approach.
Reproduction assets foundThe paper's Data Availability statement provides a public Google Drive link to the study data and a public GitHub repository, and the study's input images come from the public Roboflow 'Detecting Diseases' dataset. These are paper-specific, publicly accessible assets supporting the plant disease detection experiments.Dataset · publicone who inspired our work.
Author contributions
BSM: conceptualization and drafting, HSN: data collection and analysis. MNW: Methodology and review. NOF: Drafting and interpretation. CCZ: Writing and method. HDA: writing and Data Collection; EMO: Drafting, Supervision and Editing.
Data availability
The data can be accessed via: https://drive.google.com/file/d/1kA_JWhHQhyzzuzlpzppK2nNTtbiR2N77/view . https://github.com/Sachinthana-Lokuyaddage/Plant_Disease_Detection_Using_Transfer_Learning_with_ResNet50 .
Declarations
Competing interests
The authors declare no competing interests.
Consent to participate
All authors consent to participate.
Footnotes
Publisher’s note
Springer Nature remains neuOpen asset ↗lines:209-247Plant phenotyping relevance match · UnverifiedOpenAlex · checked 6 Sept 2026
Accurate grain yield (GY) prediction is essential in wheat breeding to enhance selection and accelerate breeding cycles. This study explored whether high-throughput phenotyping (HTP) data collected from small plot (SP) trials can effectively predict GY outcomes in later-stage big plot (BP) trials. Genomic (G) data were combined with hyperspectral (H) and multispectral + thermal (M) imaging across the 2022 and 2023 growing seasons at the Plant Science Research and Education Unit, Citra, Florida. A panel of 312 wheat genotypes was analyzed using GBLUP-based models, integrating G + H and G + M data from SP to predict BP yield. SP models demonstrated promising predictive ability, with G + H models achieving moderate within-year (0.43 to 0.51) and across-year (0.43) prediction accuracies, while G + M models reached 0.53 to 0.58 and 0.45, respectively. The Random Forest Regression (RFR) model produced an accuracy of 0.47 when M data from the 2022 SP, combined with G, was used to predict BP yield in 2023. Additionally, the top 25% specificity (coincide index) was evaluated, with models showing up to 47–51% within a year and 43–45% between years overlap in the highest predicted-yielding lines between SP and BP trials, further emphasizing the potential of SP data for early selection. These findings suggest that SP trials can provide meaningful predictions for BP yields, enabling earlier selection and faster breeding cycles.
Why it matches plant phenotyping methods小区試験の高スループット画像データを用いて大区画の穀粒収量を予測し、複数年・モデル間の予測精度を評価しており、フェノタイピングデータの解析ワークフローが中心的です。
abstractThis study explored whether high-throughput phenotyping (HTP) data collected from small plot (SP) trials can effectively predict GY outcomes in later-stage big plot (BP) trials.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 14 Sept 2026
Phenotyping host-pathogen interactions is crucial for understanding infectious diseases in plants. Traditionally, this process has relied on visual assessments or manual measurements, which can be subjective and labor-intensive. Recent advances in image processing and mathematical modeling enable the precise and high-throughput phenotyping of plant symptoms. Among many challenges, considering local deformations of symptoms and host tissues is difficult in plant pathology. In this study, we address this question using a level-set method. We propose an innovative approach in plant pathology that allows one to reconstruct the continuous deformation of leaf and lesion contours from daily image sequences of inoculated leaves. We consider pea stipules inoculated by the fungal pathogen Peyronellaea pinodes as an example pathosystem. After extracting lesion and stipule contours from daily visible images, we use the level-set method to track their deformations within image sequences. The visual assessment of model adequacy, along with the Jaccard Index and relative error metrics, demonstrated strong overall performance. Results showed a gradual decrease in model accuracy over time for leaf contours, while lesion contours exhibited a higher relative error on the first targeted date. These findings highlight the robustness of our method while identifying specific challenges in early lesion detection. We finish by discussing the interest in this method based on partial differential equations for the study of host-pathogen interactions, especially the development of original phenotyping methods in plant pathology.
Why it matches plant phenotyping methods植物の葉・病斑輪郭を画像から抽出し、level-set法で時系列変形を追跡する病害表現型計測法の開発・検証が中心である。
abstractWe propose an innovative approach in plant pathology that allows one to reconstruct the continuous deformation of leaf and lesion contours from daily image sequences of inoculated leaves.
The temporal and spatial irregularity of plant diseases results in insufficient image data for certain diseases, challenging traditional deep learning methods that rely on large amounts of manually annotated data for training. Few-shot learning has emerged as an effective solution to this problem. This paper proposes a method based on the Feature Adaptation Score (FAS) metric, which calculates the FAS for each feature layer in the Swin-TransformerV2 structure. By leveraging the strict positive correlation between FAS scores and test accuracy, we can identify the Swin-Transformer V2-F6 network structure suitable for few-shot plant disease classification without training the network. Furthermore, based on this network structure, we designed the Plant Disease Feature Calibration (PDFC) algorithm, which uses extracted features from the PlantVillage dataset to calibrate features from other datasets. Experiments demonstrate that the combination of the Swin-Transformer V2F6 network structure and the PDFC algorithm significantly improves the accuracy of few-shot plant disease classification, surpassing existing state-of-the-art models. Our research provides an efficient and accurate solution for few-shot plant disease classification, offering significant practical value.
Why it matches plant phenotyping methods植物病害画像分類のための特徴校正アルゴリズムとネットワーク構成を開発・評価しており、病害状態の推定手法が研究の中心である。
abstractThis paper proposes a method based on the Feature Adaptation Score (FAS) metric
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
This study investigates plant stress assessment by integrating advanced sensor technologies and Artificial Intelligence (AI). Multi-sensor data—including electrical impedance spectroscopy, temperature, and humidity—were used to capture plant physiological responses under environmental stress conditions. The key task addressed was the prediction of stress-related parameters using machine learning. A novel boosting-based ensemble method, AdapTree, combining AdaBoost and decision trees, was proposed to improve predictive accuracy and model interpretability. Experimental evaluation across multiple regression metrics demonstrated that AdapTree outperformed baseline models, achieving an R2 score of 0.993 for impedance magnitude prediction and 0.999 for both relative humidity (RH) and temperature, along with low root mean squared error (134.565 for impedance, 0.006966 for RH, and 0.0050099 for temperature) and mean absolute error values (22.789 for impedance; 1.51 × 10−5 for RH and 2.51 × 10−5 for temperature). These findings validate the reliability and effectiveness of the proposed AI-driven framework in accurately interpreting sensor data for plant stress detection. The approach offers a scalable, data-driven solution to enhance precision agriculture and agricultural sustainability. Furthermore, this method can be extended to monitor additional stress markers or applied across diverse plant species and field conditions, supporting future developments in intelligent crop monitoring systems.
Why it matches plant phenotyping methods植物ストレス状態の取得・推定を目的にマルチセンサーと機械学習手法を開発し、ベースラインとの性能比較で検証しており、フェノタイピング手法が研究の中心である。
abstractThis study investigates plant stress assessment by integrating advanced sensor technologies and Artificial Intelligence (AI).
The real-time monitoring and counting of maize seed germination at seedling stage is of great significance for seed quality detection, field management and yield estimation. Traditional manual monitoring and counting is very time-consuming, cumbersome and error-prone. In order to quickly and accurately identify and count maize seedlings in a complex field environment, this study proposes an end-to-end maize seedling plant detection model H-RT-DETR (Hierarchical-Real-Time DEtection TRansformer) based on hierarchical feature extraction and RT-DETR (Real-Time DEtection TRansformer). H-RT-DETR uses Hierarchical Feature Representation and Efficient Self-Attention as the backbone network for feature extraction, thereby improving the network's ability to extract features of maize seedling stage in UAV remote sensing images. Through experiments on the UAV remote sensing data set of maize seedling stage, the mean Average Precision mAP0.5-0.95, mAP0.5 and mAP0.75 of the improved H-RT-DETR model reached 51.2%, 94.7% and 48.1%, respectively, and the Average Recall (AR) reached 68.5%. In order to verify the efficiency of the proposed method, H-RT-DETR is compared with the widely used and advanced target recognition methods. The results show that the detection accuracy of H-RT-DETR is better than that of the comparison methods. In terms of detection speed, the H-RT-DETR model does not require Non-Maximum Suppression (NMS) post-processing operations, the Frames Per Second (FPS) on the test dataset reaches 84f/s, which is 19,12,11 and 21 higher than that of YOLOv5, YOLOv7, YOLOv8 and YOLOX, respectively, under the same hardware environment. This model can provide technical support for real-time detection of maize seedlings under UAV remote sensing images in terms of both detection accuracy and speed (see https://github.com/wylSUGAR/H-RT-DETR for model implementation and results).
Why it matches plant phenotyping methodsUAV画像からトウモロコシ幼苗を検出・計数する深層学習手法を開発し、既存手法と精度・速度を比較検証しているため、植物フェノタイピング手法が中心である。
abstractIn order to quickly and accurately identify and count maize seedlings in a complex field environment, this study proposes an end-to-end maize seedling plant detection model H-RT-DETR
Reproduction assets foundThe authors provide a public GitHub repository containing the H-RT-DETR model implementation and results for maize seedling detection in UAV images. The UAV image dataset itself is not stated as publicly available, and other linked repositories (labelme, YOLOv5, ultralytics) are generic third-party tools, not paper-Code · publicthe test dataset reaches 84f/s, which is 19,12,11 and 21 higher than that of YOLOv5, YOLOv7, YOLOv8 and YOLOX, respectively, under the same hardware environment. This model can provide technical support for real-time detection of maize seedlings under UAV remote sensing images in terms of both detection accuracy and speed (see https://github.com/wylSUGAR/H-RT-DETR for model implementation and results).
Keywords
Maize seedling stage UAV remote sensing RT-DETR Target recognition Real-time detection Plant counting the National Key Research and Development Program of China 2023YFD1900704 2023YFD1900704 pmc-status-qastatus 0 pmc-status-live yes pmc-status-embargo no pmc-status-released yes pmOpen asset ↗wylSUGAR/H-RT-DETRlines:1-26Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Accurate classification of plant disease by farming robot cameras can increase crop yield and reduce unnecessary agricultural chemicals, which is a fundamental task in the field of sustainable and precision agriculture. However, until now, disease classification has mostly been performed by manual methods, such as visual inspection, which are labor-intensive and often lead to misclassification of disease types. Therefore, previous studies have proposed disease classification methods based on machine learning or deep learning techniques; however, most did not consider real-world plant images with complex backgrounds and incurred high computational costs. To address these issues, this study proposes a computationally effective residual convolutional attention network (RCA-Net) for the disease classification of plants in field images with complex backgrounds. RCA-Net leverages attention mechanisms and multiscale feature extraction strategies to enhance salient features while reducing background noises. In addition, we introduce fractal dimension estimation to analyze the complexity and irregularity of class activation maps for both healthy plants and their diseases, confirming that our model can extract important features for the correct classification of plant disease. The experiments utilized two publicly available datasets: the sugarcane leaf disease and potato leaf disease datasets. Furthermore, to improve the capability of our proposed system, we performed fractal dimension estimation to evaluate the structural complexity of healthy and diseased leaf patterns. The experimental results show that RCA-Net outperforms state-of-the-art methods with an accuracy of 93.81% on the first dataset and 78.14% on the second dataset. Furthermore, we confirm that our method can be operated on an embedded system for farming robots or mobile devices at fast processing speed (78.7 frames per second).
Why it matches plant phenotyping methods植物画像から病害状態を推定する画像解析手法を開発・評価しており、病害分類とモデル性能検証が研究の中心であるため。
abstractthis study proposes a computationally effective residual convolutional attention network (RCA-Net) for the disease classification of plants in field images with complex backgrounds.
Reproduction assets foundThe authors explicitly state their RCA-Net model and code are publicly available on GitHub, which constitutes the paper's computational analysis asset. The sugarcane and potato leaf disease datasets are cited third-party prior datasets, not paper-specific deposits.Code · publicData Availability Statement: Our model and code are made publicly available on GitHub site
(https://github.com/mhamza92/RCA-Net, accessed on 15 April 2025).Open asset ↗https://github.com/mhamza92/RCA-Netpdf-page:33 lines:1-57Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Tea pest and disease detection is crucial in tea plantation management, however, challenges such as multi-target occlusion and complex background impact detection accuracy and efficiency. To address these issues, this paper proposes an improved lightweight model, WMC-RTDETR, based on the RT-DETR model. The model significantly enhances the ability to capture multi-scale features by introducing wavelet transform convolution, improving the feature extraction accuracy in complex backgrounds, and increasing detection efficiency while reducing the number of model parameters. Combined with multiscale multihead self-attention, global feature fusion across scales is realized, which effectively overcomes the shortcomings of traditional attention mechanisms in small target detection. Additionally, a context-guided spatial feature reconstruction feature pyramid network is designed to refine the target feature reconstruction through contextual information, thereby improving the robustness and accuracy of target detection in complex scenes. Experimental results show that the proposed model achieves 97.7% and 83.1% respectively in mAP50 and mAP50:95 indicators, which outperform the original model. In addition, the number of parameters and floating-point operations are reduced by 35.48% and 40.42% respectively, enabling highly efficient and accurate detection of pests and diseases in complex scenarios. Furthermore, this paper successfully deploys the lightweight model on the Raspberry Pi platform, which proves that it has good real-time performance in resource-constrained embedded environments, providing a practical solution for low-cost disease monitoring in agricultural scenarios.
Why it matches plant phenotyping methods茶葉の病害虫を画像から検出するモデルを開発・評価し、病害状態の推定性能と組込み実装まで検証しているため、植物フェノタイピング手法が中心である。
abstractthis paper proposes an improved lightweight model, WMC-RTDETR, based on the RT-DETR model.
Efficient nutrient management is critical to enhancing agricultural productivity while promoting sustainable practices. However, traditional methods for diagnosing nutrient deficiencies in crops such as soil testing and visual inspection are often costly, time-consuming, and limited in scalability. This study proposes a machine learning-based framework for the automated detection of crop nutrient deficiencies, focusing on the three essential macronutrients: Nitrogen (N), Phosphorus (P), and Potassium (K). Utilizing a dataset of 1,156 leaf images, the system extracts 26 colour, texture, and shape based features. Feature selection methods, including ANOVA, Mutual Information, Random Forest, XGBoost, and Recursive Feature Elimination (RFE), are employed to identify the most discriminative features. Seven machine learning models are evaluated K Nearest Neighbours (KNN), Support Vector Machine (SVM), Naïve Bayes, Logistic Regression, Multi-Layer Perceptron (MLP), Random Forest, and Decision Tree using accuracy and weighted F1-score. The results demonstrate that feature selection significantly improves model performance, with Random Forest achieving 87.62% accuracy and MLP yielding the highest F1 score of 81.84%. This research highlights the potential of machine learning for scalable, real-time nutrient deficiency detection, contributing to the advancement of precision agriculture and sustainable farming.
Why it matches plant phenotyping methods葉画像から色・質感・形状特徴を抽出し、作物の栄養欠乏状態を自動推定する機械学習フレームワークの開発が中心であり、植物状態の取得・分類手法に該当する。
abstractThis study proposes a machine learning-based framework for the automated detection of crop nutrient deficiencies
Premise This study investigates advanced training techniques to improve the performance of convolutional neural networks for disease detection in cocoa, Theobroma cacao . Methods Despite recent stagnation in accuracy improvements in computer vision for image classification, our research demonstrates significant advancements in performance through semi-supervised learning, specialised loss functions, and the inclusion of a non-cocoa class. Results Semi-supervised learning reduced overfitting and enhanced generalisability, particularly for subtle symptoms. The non-cocoa class exposed models to a broad range of relevant features, significantly improving model robustness and performance in difficult cases. Grad-CAM for qualitative assessment provided valuable insights into model behaviour, highlighting cases of overfitting missed by summary statistics. We also describe dynamic focal loss, a novel loss function that uses an empirical measure of difficulty to weight each image. Our results suggest that while PhytNet shows promise in terms of computational efficiency and superior handling of difficult images, ResNet18 with semi-supervised learning and dynamic focal loss emerged as the strongest contender for real-world deployment. Discussion This research underscores the potential of semi-supervised learning and advanced loss functions in enhancing the applicability of deep learning models in agricultural disease management. It also presents a new high-quality benchmark dataset of 7220 images of diseased and healthy cocoa trees, offering a much greater and more realistic challenge than the Plan Village dataset.
Why it matches plant phenotyping methodsカカオ葉・樹体の病徴画像から植物の病害状態を推定する深層学習手法を開発・比較し、性能評価とベンチマークデータセット構築を行っており、フェノタイピング手法が中心である。
abstractThis study investigates advanced training techniques to improve the performance of convolutional neural networks for disease detection in cocoa, Theobroma cacao .
Reproduction assets foundThe paper's data availability statement explicitly provides the paper-specific cocoa image dataset and the FAIGB dataset on OSF, plus authors' analysis code on GitHub, all with public URLs.Dataset · publicThe cocoa image data is available at https://osf.io/2fw6gOpen asset ↗osf · 2fw6glines:753-923Dataset · publicthe FAIGB web‐scraped dataset of crop disease images is available at https://osf.io/nuafhOpen asset ↗osf · nuafhlines:753-923Code · publicAll code necessary to reproduce these results is available on GitHub ( https://github.com/jrsykes/CocoaReader/tree/main/CocoaNet/PhytNet_Cocoa )Open asset ↗github · jrsykes/CocoaReaderlines:753-923Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Spectral reflectance indices (SRIs) are increasingly recognized as valuable tools in wheat breeding programs for assessing traits that typically require destructive measurements. Little is known about the application of non-descriptive methods in synthetic wheat and the effect of phenological stage. This study assessed variation and genetic parameters of SRIs and physiological parameters in a panel of synthetic wheat under both control and salinity conditions as well as the efficacy of SIR indices for selection across different phenological stages. Results indicated that salinity stress significantly reduced grain yield and relative water content while increasing ascorbate peroxidase (APX) enzyme activity across all growth stages. APX, peroxidase (POD), and the Green Difference Vegetation Index (GDVI) showed the highest heritability and genotypic coefficient of variation (GCV) across all phenological stages, suggesting strong genetic control over these indices. The Normalized Difference Vegetative Index (RNDVI) also demonstrated a similar trend under control conditions across all phenological stages. Principal Component Analysis (PCA) indicated that assessing SRIs concerning grain yield and physiological parameters was more effective during the anthesis and maturity stages than at milking. However, PCA effectively identified high-yielding and salt-tolerant genotypes during the milking stage, particularly at maturity. Overall, the SRIs analysis in wheat genotypes highlights their potential for optimizing selection timing and improving precision in breeding programs.
Why it matches plant phenotyping methods合成コムギの生育段階・塩ストレス下でスペクトル反射指数を評価し、遺伝率や選抜への有効性、選抜時期を検証しており、非破壊的な植物表現型取得法の応用が中心です。
abstractSpectral reflectance indices (SRIs) are increasingly recognized as valuable tools in wheat breeding programs for assessing traits that typically require destructive measurements.
Genomic tools have transformed our understanding of species and population genetic structure in landscapes. However, discerning the impacts of neutral and adaptive evolutionary forces remains challenging, largely due to the scarcity of tools capable of measuring a broad spectrum of phenotypic traits. We used spectroscopic data from preserved leaves to test for adaptive divergence among populations of live oaks (Quercus section Virentes) across genetic and phylogenetic levels. The monophyletic lineage includes seven species that diversified under sympatric, parapatric and allopatric speciation modes. We used 427 individuals to test for isolation-by-distance (IBD) and isolation-by-environment (IBE), as well as the influences of selection and phylogenetic inertia on traits. Finally and to examine how phylogenetic signals are distributed across their foliar reflectance spectra. Partial redundancy analyses (pRDA) revealed that (IBE explains more phenotypic variation than (IBD among sympatric species, particularly in certain spectral regions and traits derived from spectra. Across the phylogeny, phylogenetic generalized least squares (PGLS) models show that environmental variables—including minimum temperature of the coldest month and annual precipitation—predict traits related to stress tolerance across climatic gradients, such as lignin content and anthocyanin levels. These results demonstrate that leaf reflectance spectra can be used to capture adaptive differentiation and evolutionary history across scales, offering a powerful, non-destructive tool for linking phenotype, environment, and evolutionary processes in long-lived plant lineages.
Why it matches plant phenotyping methods葉の反射スペクトルからリグニン含量やアントシアニン量などの植物形質を抽出し、適応分化を評価する分光フェノタイピングの適用が研究の中心である。
abstractWe used spectroscopic data from preserved leaves to test for adaptive divergence among populations of live oaks
Abstract The timely and precise identification of diseases in plants is essential for efficient disease control and safeguarding of crops. Manual identification of diseases requires expert knowledge in the field, and finding people with domain knowledge is challenging. To overcome the challenge, computer vision-based machine learning techniques have been proposed by the researchers in recent years. Most of these solutions with the standard convolutional neural network (CNN) approaches use uniform background laboratory setup leaf images to identify the diseases. However, only a few works considered real-field images in their work. Therefore, there is a need for a robust CNN architecture that can identify the diseases in plants in both laboratory and real-field conditioned images. In this paper, we have proposed an Inception-enabled vision transformer (ViT) architecture to identify the diseases in plants. The proposed Inception-enabled ViT architecture extracts local as well as global features, which improves feature learning. The use of multiple filters with different kernel sizes efficiently use computing resources to extract relevant features without the need for deeper networks. The robustness of the proposed architecture is established by hyper-parameter tuning and comparison with state-of-the-art. In the experiment, we consider five datasets with both laboratory-conditioned and real-field conditioned images. From the experimental results, we see that the proposed model outperforms state-of-the-art deep learning models with fewer parameters. The proposed model archives an accuracy rate of 99.17% for the apple leaf dataset, 99.32% for the rice dataset, 96.89% for the ibean dataset, 75.42% for the cassava leaf dataset, and 99.33% for the plantvillage dataset.
Why it matches plant phenotyping methods植物病害の画像から病害状態を推定するコンピュータビジョン手法を開発・比較しており、植物表現型（病害状態）の抽出が中心です。
abstractIn this paper, we have proposed an Inception-enabled vision transformer (ViT) architecture to identify the diseases in plants.
Reproduction assets foundThe paper evaluates an Inception-enabled ViT model on five publicly available plant disease image datasets. The Data Availability section explicitly lists Kaggle URLs for the apple, bean (ibean), rice/wheat-rust, PlantVillage, and cassava datasets. These are public, paper-specific image datasets directly used for the模型Dataset · publicThe datasets generated and/or analysed during the current study
are available in Kaggle repository at:
https://www.kaggle.com/datasets/piantic/plantpathology-apple-datasetOpen asset ↗Kaggle · piantic/plantpathology-apple-datasetpdf-page:22 lines:1-48Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
Tea ( Camellia sinensis L.) disease detection in complex field conditions faces significant challenges due to the scarcity of labeled data. While current mainstream visual deep learning algorithms depend on large-scale curated datasets. To address this, we propose a novel few-shot end-to-end detection network called MAF-MixNet that achieves robust detection with minimal annotation data. The network effectively overcomes the bottleneck of insufficient feature extraction under limited samples of existing methods, through the design of a mixed attention branch (MA-Branch) and a multi-path feature fusion module (MAFM). The former extracts contextual features, while the latter combines and enhances the local and global features. The entire model uses a two-stage paradigm to pretrain on public datasets and fine-tune on balanced subset datasets, including novel tea disease classes, anthracnose, and brown blight. Comparative experiments with six models on four evaluation metrics verified the advancement of our model. At 5-shot, MAF-MixNet achieves scores of 62.0%, 60.1%, and 65.9% in precision, nAP50, and F1 score, respectively, significantly outperforming other models. Similar superiority is achieved in the 10-shot scenario, where nAP50 is 73.8%. Our model maintains a certain computational efficiency and achieves the second fastest inference speed at 11.63 FPS, making it viable for real-world deployment. The results confirm MAF-MixNet's potential to enable cost-effective, intelligent disease monitoring in precision agriculture.
Why it matches plant phenotyping methods植物病害の症状を画像から検出する新規深層学習手法を開発し、複数モデルとの比較検証を行っているため、植物フェノタイピング手法が中心である。
abstractwe propose a novel few-shot end-to-end detection network called MAF-MixNet
Reproduction assets foundThe authors openly released the annotated leaf disease detection dataset (718 JPEG images with XML annotations of tea and cotton diseases) used in this study via Hugging Face Datasets with a DOI, making it a public, paper-specific, actionable asset.Dataset · publicThe leaf disease detection dataset supporting the findings of this
study is openly available in Hugging Face Datasets. This dataset contains 718 annotated images
of tea and cotton leaves across four disease categories (Tea Anthracnose Disease, Tea Brown Blight
Disease, Cotton Fusarium Wilt Disease, and Cotton Powdery Mildew), formatted as JPEG with
accompanying XML metadata.Open asset ↗Hugging Face Datasetspdf-page:26 lines:1-58Plant phenotyping relevance match · UnverifiedOpenAlex · checked 14 Sept 2026
Plant measurements are crucial to determine which plants grow optimal under certain conditions. These measurements can be done by hand, or automated using cameras, also known as image-based plant phenotyping. These images can be used to create point clouds to measure plant traits in 3D. To extract plant traits, accurate segmentation is crucial. Most point cloud segmentation methods rely on 3D segmentation algorithms. These algorithms are not as advanced and developed as 2D algorithms. In addition, 2D neural networks are pre-trained on large diverse datasets. In our work, it was therefore hypothesised that segmentation of point clouds using projection-based methods can obtain a higher accuracy than voxel or point-based algorithms. To test this hypothesis, a 2D-to-3D reprojection method was developed and compared with three state-of-the-art 3D segmentation algorithms; Swin3D-s, Point Transformer v3 and MinkUNet34C. The 2D-to-3D method segmented images using Mask2Former, reprojected the predictions to the point cloud, and used a majority vote algorithm to merge multiple predictions. All algorithms were trained and tested to segment 3D point clouds into leaves, main stem, side stem, and pole. There was no significant difference between the 2D-to-3D, Swin3D-s and Point Transformer v3 algorithm, indicating that state-of-the-art voxel or point-based methods perform similar than our projection-based method. However, the 2D-to-3D method had a higher performance by including virtual cameras and it had a higher training efficiency. With only five annotated plants, a similar performance was obtained than training Swin3D-s on 25 plants indicating the added value of the developed pipeline.
Why it matches plant phenotyping methods植物の3D形態計測を目的とした点群セグメンテーション手法を開発し、既存アルゴリズムと比較評価しており、表現型取得ワークフローが研究の中心です。
abstractTo extract plant traits, accurate segmentation is crucial.
Sugarcane is the crucial crop in the world, and the many diseases are impacted on this crop. Early disease detection of the crop is the important for the preventing losses of the yield. This research proposes a deep learning based approach for the detecting diseases of the sugarcane using the DenseNet and Sequential models. This pre-trained model uses the convolutional neural networks (CNNs) to extract features from the sugarcane images and classify them into the different diseases based on their features. The Sequential model achieves the high accuracy i.e. 94% while the DenseNet achieves the 75% accuracy. These result shows that this models can effectively detect the diseases of the sugarcane crop which is helpful for the preventing the disease spread and the reduce the yield losses. Sugarcane is a vital crop worldwide, and its production is severely impacted by various diseases. Early detection of these diseases is crucial for preventing significant yield losses. This research proposes a deep learning-based approach for detecting sugarcane crop diseases using DenseNet and Sequential models. The proposed models utilize convolutional neural networks (CNNs) to extract features from sugarcane images and classify them into different disease categories. The DenseNet model achieves a high accuracy of 75%, while the Sequential model attains an accuracy of 94%. The results demonstrate that the proposed models can effectively detect sugarcane crop diseases, enabling farmers and agricultural experts to take timely measures to prevent disease spread and reduce yield losses. This research contributes to the development of precision agriculture techniques, promoting sustainable and efficient sugarcane production.
Why it matches plant phenotyping methodsサトウキビ画像から病害状態を推定する深層学習手法が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThis research proposes a deep learning based approach for the detecting diseases of the sugarcane using the DenseNet and Sequential models.
Rice is a strategic and important food crop for the economy in Indonesia. Rice can be infected with diseases caused by fungi, bacteria and viruses. The disease that attacks rice plants goes unnoticed by farmers and farmers often do not understand the diseases that attack rice plants so that it is too late in treating them to diagnose the symptoms, causing rice production to decrease. To solve this problem, it is necessary to carry out a disease detection process in rice plants. In this research, the Dual-Channel Convolutional Neural Network (DCCNN) method will be used. This DCCNN method consists of two channels, namely deep channel and shallow channel. The process of detecting grape plant diseases using the DCCNN method will start from the process of extracting leaf parts from the input image using the Gabor Filter method. After that, the Segmentation Based Fractal Co-Occurrence Texture Analysis method will be used to carry out the process of extracting characteristics, color and texture from the extracted leaf parts. Finally, the DCCNN method will be applied to carry out the process of classifying and detecting types of grape plant diseases. The results of this research are that the DCCNN method can be used to detect types of leaf diseases in rice plants. The accuracy of disease detection results using the DCCNN method depends on the number of datasets contained in the system with an accuracy level of up to 85%. However, more datasets will cause the execution process to take longer.
Why it matches plant phenotyping methods葉画像から植物病害を検出・分類するDCCNN、葉抽出、特徴抽出、精度評価が中心であり、植物の病害状態を推定する画像ベースのフェノタイピング手法に該当します。
titleImplementation of the Dual Channel Convolution Neural Network Method for Detecting Rice Plant Diseases
Rice blast is one of the most destructive diseases of rice leaves, seriously affecting rice production and quality. An accurate and rapid large-scale disease detection method is essential for rice production management. This study employed unmanned aerial vehicle (UAV) hyperspectral remote sensing technology for continuous observation of rice blast in the field. Advanced deep-learning techniques were utilized and combined with UAV data to detect rice blast. Firstly, the sensitivity and importance of canopy reflectance and texture features in disease monitoring were assessed. Considering the limitations of single texture features, the rice blast texture indices (RBTIs) were constructed by multiple texture features. Secondly, based on characteristic wavelengths, RBTIs, and their combinations, an effective rice blast detection framework based on the transformer network, multi-scale integrator selection attention transformer network (MS-STNet) model, was proposed. By incorporating multi-scale integrator and adopting a multi-scale and multi-pooling strategy that considered the interactions between different layers, the ability of the model to capture fine-grained information was enhanced. The top-k selection mechanism was introduced to generate corresponding attention masks, preserving the most contributive feature combinations while maintaining the global structural information of the input. The results demonstrated that the MS-STNet model could adequately learn significant features at different scales, demonstrating excellent accuracy and strong spatial adaptability in both field experiments. Compared with single texture features, the model using RBTIs as inputs demonstrated superior classification performance, with a maximum increase in overall accuracy (OA) of 4.27%. Furthermore, the model constructed by combining spectral features and RBTIs outperformed models built using only spectral features or RBTIs, with a maximum OA of 96.98% and Kappa of 96.22%. Overall, the feature-based combination method can improve the early phases of rice blast classification accuracy. The study results can provide valuable reference for accurately monitoring rice blast using UAV hyperspectral imagery.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像からイネ葉の病害状態を推定するデータ取得・特徴抽出・深層学習手法を中心に開発・評価しており、植物表現型計測法に該当する。
abstractThis study employed unmanned aerial vehicle (UAV) hyperspectral remote sensing technology for continuous observation of rice blast in the field.
Counting soybean plants is a crucial strategy for assessing sowing quality and supporting high production. Despite its importance, the laborious nature of traditional assessment methods makes them unreliable and not scalable. Additionally, innovative image-based solutions have demonstrated limitations in detecting dense crops such as soybeans. Therefore, in this study, we developed neural network models to analyze a set of RGB and multispectral images and perform plant classification in a comprehensive dataset, which included data collected at three vegetative stages of soybean (VC, V1, and V2). Our results demonstrated high accuracy in classifying plants using either RGB (98%) or multispectral images (92%). A significant strength of this study is the ability to classify highly dense plants, without a trend for misclassification. Clearly, our findings provide stakeholders with a timely and effective approach to counting soybean plants, reducing labor and time, while increasing reliability.
Why it matches plant phenotyping methodsRGB・マルチスペクトル画像とニューラルネットワークによるダイズ個体数の推定手法を開発・評価しており、植物形質取得が研究の中心である。
abstractwe developed neural network models to analyze a set of RGB and multispectral images and perform plant classification
Since rice is a widely consumed food and can be exposed to different diseases depending on the climatic conditions of the region where it grows, it is very important to monitor it before harvest. Unlike the literature, instead of using an image that contains a single leaf taken with a controlled background, a new database consisting of images taken in uncontrolled field conditions close to its natural state was studied. Another challenge about the images taken from the field is that the five classes in the database are not evenly distributed. In this study, a method based on vision transformers which is robust to the class imbalance problem is proposed for rice leaf images taken in the wild with complex backgrounds. Additionally, the vision transformer-based model was compared with several transfer learning methods with and without fine-tuning. The results obtained revealed that the proposed approach significantly increased the performance of the sensitivity metric while reaching the highest accuracy rate. Since the images studied are close to images taken with a drone and no preprocessing is applied against the field conditions, the proposed method can be used in the development of a drone-based plant disease early warning system in the future.
Why it matches plant phenotyping methodsイネ葉画像から病害状態を分類する視覚モデルを提案・比較しており、植物の病徴推定と画像解析手法が研究の中心である。
abstractIn this study, a method based on vision transformers which is robust to the class imbalance problem is proposed for rice leaf images taken in the wild with complex backgrounds.
Field / plotLeafClassificationObject detectionStress / disease detectionDisease symptoms / severity
India's agricultural sector faces persistent challenges due to the prevalence of plant diseases, which severely impact crop quality and productivity, exacerbating the ongoing food supply crisis. Traditional methods of diagnosing plant diseases are often time-consuming, labor-intensive, and prone to inaccuracies, making it difficult for farmers to implement timely interventions. To address these issues, a forward-looking strategy utilizing artificial intelligence (AI) and machine learning (ML) has been proposed, aiming to revolutionize disease detection and management in agriculture. This involves the development of a comprehensive novel dataset named Leafsnap, which is uniquely sourced directly from real-world agricultural environments. This dataset ensures the authenticity and relevance of the data, reflecting the actual conditions faced by farmers. Leafsnap serves as a foundation for training advanced algorithmic models designed to identify patterns and symptoms indicative of various leaf diseases. The proposed system leverages a combination of cutting-edge AI and ML techniques, including convolutional neural networks (CNN), random forest (RF), support vector machines (SVM), and extreme gradient boosting (XGBoost) and logistic regression (LR). By integrating these advanced computational techniques into agricultural practices, the system aims to provide farmers with an efficient, reliable, and scalable solution for disease management. The ultimate goal is to foster agricultural sustainability by minimizing crop losses due to disease, thereby bolstering food security and supporting the livelihoods of farmers across India.
Why it matches plant phenotyping methods実環境由来の葉画像データセット開発と、植物葉の病徴を画像から検出する機械学習手法が研究の中心であり、植物病害状態のフェノタイピングに該当する。
abstractThis involves the development of a comprehensive novel dataset named Leafsnap, which is uniquely sourced directly from real-world agricultural environments.
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 15 Sept 2026
Published1 Apr 2025International Journal of Biological MacromoleculesCited by 0 · OpenAlex ↗
Resin biosynthesis in conifer is a complex process, controlled by multiple quantitative trait loci (QTLs). Quantifying resin components is traditionally expensive and labor-intensive. In this study, we employed near infrared (NIR) spectroscopy to quantify resin components in Slash pine using 240 genotypes. A partial least squares regression model was applied to identify the characteristic bands responsed to variations in Alpha and Beta pinene levels. Genome-wide association study (GWAS) identified 35 significant SNPs involved in terpenoid precursor biosynthesis, transport, modification, and abiotic stress resistance. eQTL mapping co-localized four candidate genes: PeCHITINASE (c166891.graph_c0), PeGLYCOSYLTRANSFERASE (c160167.graph_c0), PeASIL2 (c324347.graph_c0), and PeERF168 (c311225.graph_c0). Mutations in two SNPs increased the expression of PeASIL2 and PeERF168, leading to higher levels of Alpha and Beta pinene. Further heterologous transformation experiments confirmed that the PeERF168 gene regulates the concentration of both monoterpenes and sesquiterpenes. These findings provide valuable insights into the molecular mechanisms of resin biosynthesis, facilitating cost-effective gene discovery through high-throughput resin component detection and genomics integration, with substantial potential to enhance molecular breeding and improve resin yield and quality.
Why it matches plant phenotyping methodsNIR分光法とPLS回帰による樹脂成分（植物の生化学的形質）のハイスループット定量が明示され、240遺伝子型への適用と検出手法の説明が研究の重要な構成要素である。
abstractQuantifying resin components is traditionally expensive and labor-intensive.
Abstract Modern agriculture faces a critical challenge in ensuring the health and yield of crops, with the early detection and treatment of diseases playing a pivotal role. Traditional methods reliant on manual inspection are not only time-consuming but also prone to errors, leading to significant crop losses and economic impact. The importance of this research lies in mitigating these inefficiencies by developing a robust ML model capable of accurately identifying diseased tomato leaves in the plants. Datasets considered while algorithm training comprise around 6 thousand to 8 thousand images, including both healthy and diseased leaves. The primary gap this research addresses is the inadequacy of conventional methods in providing timely and accurate disease detection. The research aims to harness the power of advanced ML algorithms including Visual Geometry Group 16 & Residual Network for the deep feature extraction. The model is trained, validated, and tested using a split dataset approach to ensure high accuracy and reliability. Key findings indicate that the model achieves an accuracy of around 95% in simulations, although a slight drop in accuracy is observed in real-time applications. Despite this, the ML-based approach significantly surpasses traditional methods, offering a more efficient and scalable solution to find the diseased leaves soon in tomato. These findings highlight potential in ML to transform agricultural practices by providing timely and accurate disease detection, reducing the reliance on manual labor, and contributing to increased crop yields and sustainable farming practices.
Why it matches plant phenotyping methodsトマト葉の病徴を画像から検出・分類する深層学習モデルの開発と検証が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採用する。
abstractdeveloping a robust ML model capable of accurately identifying diseased tomato leaves in the plants
Abstract Background Rapeseed( Brassica napus L. ) inflorescence coverage is a crucial phenotypic parameter for assessing crop growth and estimating yield. Accurate crop cover assessment is typically performed using Unmanned Aerial Vehicles (UAVs) in combination with semantic segmentation methods. However, the irregular and variable morphology of rapeseed inflorescences presents significant challenges in segmentation. To address these challenges, advanced methods that can improve segmentation accuracy, particularly under limited data conditions, are needed. Results In this study, we propose a cost-effective and high-throughput approach using a semi-supervised learning framework, DM_CorrMatch. This method enhances input images through strong and weak data augmentation techniques, while leveraging the Denoising Diffusion Probabilistic Model (DDPM) to generate additional samples in data-scarce scenarios.We propose an automatic update strategy for labeled data to dilute the proportion of erroneous labels in manual segmentation. Furthermore, a novel network architecture, Mamba-Deeplabv3+, is proposed, combining the strengths of Mamba and Convolutional Neural Networks (CNNs) for both global and local feature extraction. This architecture effectively captures key inflorescence features, even under varying poses, while reducing the influence of complex backgrounds. The proposed method is validated on the Rapeseed Flower Segmentation Dataset (RFSD), which consists of 720 UAV images from the Yangluo experimental station of the Oil Crops Research Institute of the Chinese Academy of Agricultural Sciences (CAAS). The experimental results showed that our method outperforms four traditional segmentation methods and eleven deep learning methods, achieving an Intersection over Union (IoU) of 0.886, Precision of 0.942, and Recall of 0.940. Conclusions The proposed semi-supervised learning-based method, combined with the Mamba-Deeplabv3+ architecture, demonstrates superior performance in accurately segmenting rapeseed inflorescences under challenging conditions. Our approach effectively handles complex backgrounds and various poses of inflorescences, providing a reliable tool for rapeseed flower cover estimation. This method can aid in the development of high-yield cultivars and improve crop monitoring through UAV-based technologies.
Why it matches plant phenotyping methodsUAV画像からナタネ花序被覆率という植物形質を推定する半教師ありセグメンテーション手法を開発し、データセット上で既存手法と比較検証しているため、方法が中心である。
abstractwe propose a cost-effective and high-throughput approach using a semi-supervised learning framework, DM_CorrMatch.
Background Seed testing plays a crucial role in improving crop yields.In actual seed testing processes, factors such as grain sticking and complex imaging environments can significantly affect the accuracy of wheat grain counting, directly impacting the effectiveness of seed testing. However, most existing methods primarily focus on simple counting tasks and lack general applicability. Results To enable fast and accurate counting of wheat grains under severe adhesion and complex scenarios, this study collected images of wheat grains from different varieties, backgrounds, densities, imaging heights, adhesion levels, and other natural conditions using various imaging devices and constructed a comprehensive wheat grain dataset through data enhancement techniques. We propose a wheat grain detection and counting model called GrainNet, which significantly improves the counting performance and detection speed across diverse conditions and adhesion levels by incorporating lightweight and efficient feature fusion modules. Specifically, the model incorporates an Efficient Multi-scale Attention (EMA) mechanism, effectively mitigating the interference of background noise on detection results. Additionally, the ASF-Gather and Distribute (ASF-GD) module optimizes the feature extraction component of the original YOLOv7 network, improving the model's robustness and accuracy in complex scenarios. Ablation experiments validate the effectiveness of the proposed methods.Compared with classic models such as Faster R-CNN, YOLOv5, YOLOv7, and YOLOv8, the GrainNet model achieves better detection performance and computational efficiency in various scenarios and adhesion levels. The mean Average Precision reached 93.15%, the F1 score was 0.946, and the detection speed was 29.10 frames per second (FPS). A comparative analysis with manual counting results revealed that the GrainNet model achieved the highest coefficient of determination and Mean Absolute Error values for wheat grain counting tasks, which were 0.93 and 5.97, respectively, with a counting accuracy of 94.47%. Conclusions Overall, the GrainNet model presented in this study enables accurate and rapid recognition and quantification of wheat grains, which can provide a reference for effective seed examination of wheat grains in real scenarios. Related content can be accessed through the following link: https://github.com/1371530728/grainnet.git .
Why it matches plant phenotyping methods小麦粒の画像検出・計数モデルとデータセットを開発し、複数条件で性能検証しているため、植物器官形質の取得手法が中心である。
abstractWe propose a wheat grain detection and counting model called GrainNet
To ensure that plant diseases are well controlled and managed that would reduce crop losses and ultimately improve on food security then diseases need to be identified correctly at the right time. This paper uses a CNN approach for identifying plant diseases using the Plant Village, web-based dataset that has on average 35 classes, with 29281 images, comprising of both healthy and diseased leaves. To improve the model performance further techniques like data augmentation, contrast enhancement, noise reduction techniques were used. The training results of the proposed CNN had a training loss of 0.0808 and a validation loss of 0.3330.The training as well as the validation accuracy achieved were 97.41% as well as 90.34% respectively. Other measures of evaluation of the presented model are precision of 0.9139; recall of 0.9034; the F1 score was 0.9019. Thus, in order to raise the accuracy in classification, other features like color, veins, roughness of the leaf surface etc., were also considered. It was also indicated how much effective the proposed model was for edge computing solutions as compared to other models including DenseNet121, ResNet50, Alex Net and VGG16. This work shows that contemporary agriculture could reliably and dependably utilize deep learning in the detection of plant diseases as a dependable and scalable tool.
Why it matches plant phenotyping methods植物葉の画像から病害状態をCNNで推定する手法の開発・評価が中心であり、植物表現型としての病害検出に該当する。
abstractThis paper uses a CNN approach for identifying plant diseases using the Plant Village, web-based dataset
Rice serves as a fundamental staple for a significant portion of the global population, playing an essential role in ensuring food security worldwide. However, the continuous threat of various diseases risks both yield and quality. Detecting these diseases at an early stage is very important for effective management of these risks. This research introduces a novel approach for rice disease detection using the fusion vision boosted classifier (FVBC), integrating VGG19 for feature extraction and LightGBM for classification. The meticulously curated dataset comprises 2627 rice leaf images, categorized into training, validation, and test sets for robust model evaluation. The FVBC model achieves impressive accuracies of 97.78% on the training set, 97.5% on the validation set, and 97.6% on the test set, demonstrating its efficacy in disease detection. The model's performance compared with other classifiers, including Softmax, highlights its superiority. Hyperparameter tuning, such as learning rate and tree depth for LightGBM, was crucial for optimizing model performance. The proposed FVBC model offers a non-invasive, scalable solution for early disease detection, empowering farmers to implement timely interventions and enhance agricultural productivity.
Why it matches plant phenotyping methodsイネ葉画像から病害状態を推定する分類手法を開発・評価しており、植物病害表現型の取得が研究の中心である。
abstractThis research introduces a novel approach for rice disease detection using the fusion vision boosted classifier (FVBC), integrating VGG19 for feature extraction and LightGBM for classification.
Yield prediction is an essential part of farm management and has been investigated with various kinds of data and technologies in the last decades. With the advent of deep learning technology, recent studies are focusing on crop growth analysis with image processing. Instead of measuring crops in a destructive way, image analysis enables crop measurement without manipulation of the crop itself. Counting crops using tracker algorithms such as DeepSORT is one of the famous approaches for yield prediction and analysis. However, to enable crop growth monitoring and analysis, it needs consideration of temporal analysis along with spatial analysis. It should be able to compare the previous status of the target crop to the current status to analyze the growth, for example, from bud to flower to strawberry. This paper proposes a novel method for monitoring crop growth with crop clustering. Instead of counting the crops from the images, the proposed methods recognized a crop cluster from the image and measured how it changed during its lifespan. Further, the proposed method is implemented in an edge device for a greenhouse that is able to collect and measure. The proposed method has been validated on a strawberry greenhouse for around a year, which shows MoTA score from 0.57 to 0.86, with respect to the dataset.
Why it matches plant phenotyping methods画像から作物クラスターの成長変化を追跡・測定する手法を開発し、エッジデバイスに実装してイチゴ温室で約1年間検証しており、植物表現型の取得が中心です。
abstractThis paper proposes a novel method for monitoring crop growth with crop clustering.
Potato blight, sometimes referred to as late blight, is a deadly disease that affects Solanaceae plants, including potato. The oomycete Phytophthora infestans is causal agent, and it may seriously damage potato crops, lowering yields and causing financial losses. To ensure food security and reduce economic losses in agriculture, potato diseases must be identified. The approach we have proposed in our study may provide a reliable and efficient solution to improve potato late blight classification accuracy. For this purpose, we used the ResNet-50, GoogLeNet, AlexNet, and VGG19Net pre-trained models. We used the AlexNet model for feature extraction, which produced the best results. After extraction, we selected features using ten optimization algorithms in their binary format. The Binary Waterwheel Plant Algorithm Sine Cosine (WWPASC) achieved the best results amongst the ten algorithms, and we performed statistical analysis on the selected features. Five machine learning models—Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbour (KNN)—were used to train the chosen features. The most accurate model was the MLP model. The hyperparameters of the MLP model were optimized using the Waterwheel Plant Algorithm Sine Cosine (WWPASC). The results indicate that the suggested methodology (WWPASC-MLP) outperforms four other optimization techniques, with a classification accuracy of 99.5%.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習・特徴選択・最適化手法が研究の中心であり、植物病害フェノタイピング手法に該当する。
titleOptimized Deep Learning for Potato Blight Detection Using the Waterwheel Plant Algorithm and Sine Cosine Algorithm
In rice, infections caused by Pantoea ananatis or Enterobacter asburiae closely resemble the bacterial blight induced by Xanthomonas oryzae pv. oryzae , yet they differ in drug resistance and management strategies. This study explores the potential of combining hyperspectral imaging (HSI) with machine learning for the rapid and accurate detection of rice bacterial blight symptoms caused by various pathogens. One-dimensional convolutional neural networks (1DCNNs) were employed to construct a classification model, integrating various spectral preprocessing techniques and feature selection algorithms for comparison. To enhance model robustness and mitigate overfitting due to limited spectral samples, generative adversarial networks (GANs) were utilized to augment the dataset. The results indicated that the 1DCNN model, after feature selection using uninformative variable elimination (UVE), achieved an accuracy of 86.11% and an F1 score of 0.8625 on the five-class dataset. However, the dominance of Pantoea ananatis in mixed bacterial samples negatively impacted classification performance. After removing mixed-infection samples, the model attained an accuracy of 97.06% and an F1 score of 0.9703 on the four-class dataset, demonstrating high classification accuracy across different pathogen-induced infections. Key spectral bands were identified at 420-490 nm, 610-670 nm, 780-850 nm, and 910-940 nm, facilitating pathogen differentiation. This study presents a precise, non-destructive approach to plant disease detection, offering valuable insights into disease prevention and management in precision agriculture.
Why it matches plant phenotyping methodsイネの病徴をハイパースペクトル画像と機械学習で直接検出・分類する手法が研究の中心であり、植物病害状態の非破壊的フェノタイピングに該当する。
abstractThis study explores the potential of combining hyperspectral imaging (HSI) with machine learning for the rapid and accurate detection of rice bacterial blight symptoms caused by various pathogens.
Accurate detection of soybean diseases is a critical component in achieving intelligent agricultural management. However, traditional methods often underperform in complex field scenarios. This paper proposes a diffusion-based object detection model that integrates the endogenous diffusion sub-network and the endogenous diffusion loss function to progressively optimize feature distributions, significantly enhancing detection performance for complex backgrounds and diverse disease regions. Experimental results demonstrate that the proposed method outperforms multiple baseline models, achieving a precision of 94%, recall of 90%, accuracy of 92%, and mAP@50 and mAP@75 of 92% and 91%, respectively, surpassing RetinaNet, DETR, YOLOv10, and DETR v2. In fine-grained disease detection, the model performs best on rust detection, with a precision of 96% and a recall of 93%. For more complex diseases such as bacterial blight and Fusarium head blight, precision and mAP exceed 90%. Compared to self-attention and CBAM, the proposed endogenous diffusion attention mechanism further improves feature extraction accuracy and robustness. This method demonstrates significant advantages in both theoretical innovation and practical application, providing critical technological support for intelligent soybean disease detection.
Why it matches plant phenotyping methods大豆病害を対象に、画像ベースの病徴・病害状態推定モデルを開発し、複数モデルとの性能比較で検証しているため、植物フェノタイピング手法が中心である。
abstractThis paper proposes a diffusion-based object detection model that integrates the endogenous diffusion sub-network and the endogenous diffusion loss function to progressively optimize feature distributions, significantly enhancing detection performance for complex backgrounds and diverse disease regions.
Remote sensing and artificial intelligence are pivotal technologies of precision agriculture nowadays. The efficient retrieval of large-scale field imagery combined with machine learning techniques shows success in various tasks like phenotyping, weeding, cropping, and disease control. This work will introduce a machine learning framework for automatized large-scale plant-specific trait annotation for the use case of disease severity scoring for CLS in sugar beet. With concepts of DLDL, special loss functions, and a tailored model architecture, we develop an efficient Vision Transformer based model for disease severity scoring called SugarViT. One novelty in this work is the combination of remote sensing data with environmental parameters of the experimental sites for disease severity prediction. Although the model is evaluated on this special use case, it is held as generic as possible to also be applicable to various image-based classification and regression tasks. With our framework, it is even possible to learn models on multi-objective problems, as we show by a pretraining on environmental metadata. Furthermore, we perform several comparison experiments with state-of-the-art methods and models to constitute our modeling and preprocessing choices.
Why it matches plant phenotyping methods植物病害重症度をUAV画像から自動推定するVision Transformerベースの手法を開発・比較評価しており、植物表現型取得が中心である。
abstractThis work will introduce a machine learning framework for automatized large-scale plant-specific trait annotation for the use case of disease severity scoring for CLS in sugar beet.
Reproduction assets foundThe paper's Data Availability statement explicitly says the data and code supporting the findings are publicly available on GitHub at the authors' repository URL, which is an allowed URL. This qualifies as a paper-specific public asset containing the authors' analysis code and the UAV multispectral plant image dataset.Code · publicData Availability: The data and code supporting the findings in this paper are available at GitHub ( https://github.com/mrcgndr/disease_severity_prediction/ ).Open asset ↗https://github.com/mrcgndr/disease_severity_prediction/lines:154-190Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published12 Feb 2025International Journal of Advanced Trends in Engineering and ManagementCited by 0 · OpenAlex ↗
Ensuring crop health and increasing agricultural productivity depend on the diagnosis of leaf diseases. This research work offers a sophisticated deep learning based strategy for automatically classifying leaf diseases. To improve accuracy, the proposed method combines features from both classification and feature extraction. Research findings indicate that the model outperforms traditional models like CNN, AlexNet, and MobileNet V2 with a high classification accuracy of 95%. The confusion matrix and ROC curve demonstrate little misclassification and good class separation, confirming the model’s efficacy. Additionally, high precision, recall, and F1 scores across multiple disease categories confirm balanced performance. Training and validation trends indicate effective learning, with minor overfitting be addressed using dropout regularization and data augmentation. The findings establish proposed model as a trustworthy and efficient solution for automated leaf disease diagnosis in precision agriculture.
Why it matches plant phenotyping methodsトマト葉の病徴を画像から自動分類する深層学習手法が研究の中心であり、植物の病害状態を直接推定・評価しているため。
abstractThis research work offers a sophisticated deep learning based strategy for automatically classifying leaf diseases.
The detection and identification of tea leaf diseases and pests play a crucial role in determining the yield and quality of tea. However, the high similarity between different tea leaf diseases and the difficulty of balancing model accuracy and complexity pose significant challenges during the detection process. This study proposes an enhanced Tea Leaf Disease Detection Model (TLDDM), an improved model based on YOLOv8 to tackle the challenges. Initially, the C2f-Faster-EMA module is employed to reduce the number of parameters and model complexity while enhancing image feature extraction capabilities. Furthermore, the Deformable Attention mechanism is integrated to improve the model's adaptability to spatial transformations and irregular data structures. Moreover, the slim neck structure is incorporated to reduce the model scale. Finally, a novel detection head structure, termed EfficientPHead, is proposed to maintain detection performance while improving computational efficiency and reducing parameters which leads to inference speed acceleration. Experimental results demonstrate that the TLDDM model achieves an AP of 98.0%, which demonstrates a significant performance enhancement compared to the SSD and Faster R-CNN algorithm. Furthermore, the proposed model is not only of great significance in improving the performance in accuracy, but also can provide remarkable advantages in real-time detection applications with an FPS (frames per second) of 58.0.
Why it matches plant phenotyping methods茶葉画像から病害を検出・識別するYOLOv8改良モデルの開発と性能評価が研究の中心であり、植物の病害状態を直接推定するフェノタイピング手法に該当する。
abstractThis study proposes an enhanced Tea Leaf Disease Detection Model (TLDDM), an improved model based on YOLOv8 to tackle the challenges.
The global attention to the utilization of unmanned aerial vehicle remote sensing drones in crop disease-wide detection has led to the urgent need to find an adapted model for different environmental conditions. Therefore, the current study has focused on spatiotemporal usage of different multispectral cameras in acquiring spectral reflectance models of in-field rice bacterial blight stresses. Where, long short-term memory (LSTM) model was compared with the other models in transfer learning strategy for assessing the blight stress severity. The results revealed that by extracting 30% of the data from the target domain and transferring it to the source domain, the adaptability of the model across different sites was effectively enhanced. Besides, LSTM showed high tuning transfer efficiency that demonstrated optimal predictive performance and the shortest training time in transfer tasks. Its coefficient of the prediction set was 0.82, and its residual prediction deviation has reached 2.26. In practice, LSTM enabled the acquisition of reliable prediction results at a minimal sample collection cost while circumventing feature reduction resulting from inter-domain data alignment. When the transfer ratio reached 20%, the coefficient of determination of the prediction set reached 0.71, and the residual prediction deviation reached 1.79. The novelty of this study came from the transfer learning efficiency in improving the model’s application capabilities across the different sites, environment, and unmanned aerial vehicle in farmland disease detection.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からイネ白葉枯病の発病ストレス重症度を推定するモデルを開発・比較し、異なる環境・圃場への転移性能を検証しているため、植物表現型取得手法が中心である。
abstractThe novelty of this study came from the transfer learning efficiency in improving the model’s application capabilities across the different sites, environment, and unmanned aerial vehicle in farmland disease detection.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
In agriculture, promptly and accurately identifying leaf diseases is crucial for sustainable crop production. To address this requirement, this research introduces a hybrid deep learning model that combines the visual geometric group version 19 (VGG19) architecture features with the transformer encoder blocks. This fusion enables the accurate and précised real-time classification of leaf diseases affecting grape, bell pepper, and tomato plants. Incorporating transformer encoder blocks offers enhanced capability in capturing intricate spatial dependencies within leaf images, promising agricultural sustainability and food security. By providing farmers and farming stakeholders with a reliable tool for rapid disease detection, our model facilitates timely intervention and management practices, ultimately leading to improved crop yields and mitigated economic losses. Through extensive comparative analyses on various datasets and filed tests, the proposed depth wise separable convolutional-TransNet (DSC-TransNet) architecture has demonstrated higher performance in terms of accuracy (99.97%), precision (99.94%), recall (99.94), sensitivity (99.94%), F1-score (99.94%), AUC (0.98) for Grpae leaves across different datasets including bell pepper and tomato. Furthermore, including DSC layers enhances the computational efficiency of the model while maintaining expressive power, making it well-suited for real-time agricultural applications. The developed DSC-TransNet model is deployed in NVIDIA Jetson Nano single board computer. This research contributes to advancing the field of automated plant disease classification, addressing critical challenges in modern agriculture and promoting more efficient and sustainable farming practices.
Why it matches plant phenotyping methods葉画像から植物病害を分類する深層学習モデルを開発し、複数データセットで比較評価するとともにエッジデバイスへ実装しており、植物病害状態の取得・推定手法が研究の中心である。
abstractthe proposed depth wise separable convolutional-TransNet (DSC-TransNet) architecture has demonstrated higher performance in terms of accuracy (99.97%), precision (99.94%), recall (99.94), sensitivity (99.94%), F1-score (99.94%), AUC (0.98)
Early and accurate detection of plant diseases is crucial for making informed decisions to increase the yield and quality of crops through the decision of appropriate treatments. This study introduces an automated system for early disease detection in plants that enhanced a lightweight model based on the robust machine learning algorithm. In particular, we introduced a transformer module, a fusion of the SPP and C3TR modules, to synthesize features in various sizes and handle uneven input image sizes. The proposed model combined with transformer-based long-term dependency modeling and convolution-based visual feature extraction to improve object detection performance. To optimize a model to a lightweight version, we integrated the proposed transformer model with the Ghost module. Such an integration acted as regular convolutional layers that subsequently substituted for the original layers to cut computational costs. Furthermore, we adopted the SIoU loss function, a modified version of CIoU, applied to the YOLOv8s model, demonstrating a substantial improvement in accuracy. We implemented quantization to the YOLOv8 model using ONNX Runtime to enhance to facilitate real-time disease detection on strawberries. Through an experiment with our dataset, the proposed model demonstrated mAP@.5 characteristics of 80.30%, marking an 8% improvement compared to the original YOLOv8 model. In addition, the parameters and complexity were reduced to approximately one-third of the initial model. These findings demonstrate notable improvements in accuracy and complexity reduction, making it suitable for detecting strawberry diseases in diverse conditions.
Why it matches plant phenotyping methodsイチゴの病害を画像から検出する軽量Transformer/YOLOベース手法を開発・評価しており、植物の病害状態の画像計測が中心である。
abstractThis study introduces an automated system for early disease detection in plants that enhanced a lightweight model based on the robust machine learning algorithm.
Plants have been a key interface in the global carbon and water cycles for nearly 475 million years. The magnitude of vegetational effects has waxed and waned dynamically because plant abundance and community composition have changed over time. Unravelling how plant communities have shaped, and been shaped by, global biogeochemical cycles relies upon reconstructing the paleoecology and paleoecophysiology of plants, and this process can be challenging in deep time, when plant communities contained organisms with traits that are rare in—or absent from—present-day ecosystems. Fortunately, the archive of how plants have shaped and responded to environmental change is preserved in the fossil record, because the traits and properties of extinct plants can be interpreted from fossilized anatomy in a qualitative, semi-quantitative, and quantitative way. Traits related to water transport in plants. including drought resistance and hydraulic supply to leaves, are particularly useful and important because these traits link individual plant performance to the water and carbon cycles.The collapse of tropical everwet rainforests end of the Carboniferous Period (~300 Ma) provides an illustration of how plant water transport traits influenced, and were shaped by, the water and carbon cycles. These traits are quantified by combining mathematical models of stem hydraulic conductivity and drought resistance with anatomical measurements from scanning electron and light microscopy images of fossilized plant water transport cells, called xylem. Analysis of stem hydraulic traits in five lineages of extinct Carboniferous plants—arborescent lycophytes, stem group seed plants, stem group tree ferns, coniferophytes, and sphenophytes—reveals differential hydraulic capacity and drought resistance among these plants, despite their simultaneous presence in tropical everwet ecosystems. Significant differences in these two traits are not only present between these five lineages, but can also be observed within several of these plant groups: for example, key parameters may vary by more than an order of magnitude in related plants. High hydraulic capacity and low drought resistance traits were associated with a decline in relative abundance toward the close of the Carboniferous Period, whereas plants with lower hydraulic capacity and higher drought resistance traits increased in relative abundance and survived this floral transition. This change in relative abundance within these communities shaped the hydrologic and carbon cycles which, in turn, amplified environmental stress that, consequently, further altered plant community composition. Implementing this analysis in trait-aware paleoecosystem models illustrates the effect of plant traits on global environments, and vice versa, yielding insight into plant performance during extreme environmental change that is analogous to anthropogenic impacts predicted for the late 21st century and beyond.
Why it matches plant phenotyping methods化石植物の解剖学的画像測定と数学モデルを組み合わせ、木部の水理伝導度・乾燥抵抗性という植物生理形質を定量化しており、形質取得・推定手法が研究の中心的要素です。
abstractThese traits are quantified by combining mathematical models of stem hydraulic conductivity and drought resistance with anatomical measurements from scanning electron and light microscopy images of fossilized plant water transport cells, called xylem.
The newest Earth Observation optical sensors, such as Sentinel-2, provide global biophysical products and vegetation indices at high spatial (decametric or twentimetric resolution) and temporal resolution (about 5 days retrieval). These biophysical parameters are essential for constant crop status monitoring at local scale. Optimizing the water use for irrigation, the weed mapping, quantifying ground above biomass and crop yield production, are some of the benefits of biophysical parameters in agriculture. This research investigates the crop status during the 2021’s growing season in Thessaly agricultural area in Greece. Thus, in maize, biophysical variables, and vegetation indices, that is, Leaf Area Index (LAI), fraction of absorbed photosynthetically active Radiation (FAPAR), Fraction of Vegetation Cover (FVC), Leaf Chlorophyll content (Cab), Canopy Water Content (CWC), Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red Edge Index (NDRedEdge) are retrieved. The PROSAIL radiative transfer model by artificial neural network approach is employed (available of the free SNAP® software) to retrieve the biophysical parameters from Sentinel-2 multispectral imagery. The monitoring of the abovementioned biophysical variables during the growth period of maize crop shows a uniform behavior. Finally, high consistency among vegetation parameters confirms the usefulness of Sentinel-2 products in agriculture.Keywords: Biophysical indices; phenological stages; monitoring maize crop; Mediterranean agroecosystems
Why it matches plant phenotyping methodsSentinel-2画像とPROSAIL・人工ニューラルネットワークを用いて、トウモロコシのLAI、FAPAR、葉面積・水分・クロロフィルなどの植物形質を推定するワークフローが中心であり、単なる生物学的実験のルーチン測定ではない。
abstractThe PROSAIL radiative transfer model by artificial neural network approach is employed (available of the free SNAP® software) to retrieve the biophysical parameters from Sentinel-2 multispectral imagery.
Agriculture is a cornerstone of economic prosperity, but plant diseases can severely impact crop yield and quality. Identifying these diseases accurately is often difficult due to limited expert availability and ambiguous information. Early detection and automated diagnosis systems are crucial to mitigate these challenges. To address this, we propose a lightweight convolutional neural network (CNN) designed for resource-constrained devices termed as LeafNet. LeafNet draws inspiration from the block-wise VGG19 architecture but incorporates several optimizations, including a reduced number of parameters, smaller input size, and faster inference time while maintaining competitive accuracy. The proposed LeafNet leverages small, uniform convolutional filters to capture fine-grained details of plant disease features, with an increasing number of channels to enhance feature extraction. Additionally, it integrates channel attention mechanisms to prioritize disease-related features effectively. We evaluated the proposed method on four datasets: the benchmark plant village (PV), the data repository of leaf images (DRLIs), the newly curated plant composite (PC) dataset, and the BARI Sunflower (BARI-Sun) dataset, which includes diverse and challenging real-world images. The results show that the proposed performs comparably to state-of-the-art methods in terms of accuracy, false positive rate (FPR), model size, and runtime, highlighting its potential for real-world applications.
Why it matches plant phenotyping methods植物病害の画像ベース診断を目的とする軽量CNNを開発し、複数データセットで精度・誤検出率・モデルサイズ・推論時間を評価しており、病害状態の表現型推定手法が中心である。
abstractwe propose a lightweight convolutional neural network (CNN) designed for resource-constrained devices termed as LeafNet.
Reproduction assets foundThe paper's authors publicly released their LeafNet analysis code on GitHub, and the plant leaf image datasets used for their phenotyping experiments (PV, DRLI, BARI-Sun) are openly available. The PC dataset is a composite of PV and DRLI and is not independently deposited.Code · publicTo promote
reproducibility and facilitate further research, the source code is publicly available at:
(https://github.com/sanaparez/LeafNet)Open asset ↗sanaparez/LeafNetpdf-page:3 lines:1-54Dataset · publicThe datasets utilized in this study are openly available at PV Dataset
(https://github.com/spMohanty/PlantVillage-Dataset)Open asset ↗spMohanty/PlantVillage-Datasetpdf-page:15 lines:1-59Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published7 Jan 2025Journal of Information Systems Engineering and ManagementCited by 0 · OpenAlex ↗
Accurate disease identification and early disease management strategies are required in India to achieve high production standards and good quality in fruits and vegetables. Image-based evaluations approaches have evolved nowadays as a result of technical developments. However, producing the wrong decision may have a negative impact on productivity. Thus, this study offered hybrid SVM-RBN model with attentive feature culling method for automatically recognizing diseases in apple fruits with high accuracy. As a result, the model generated more effective outcomes with 96% accuracy, 99% precision, 94% recall, and 93% F1 Score. Thus, by employing this technology, one may detect fruit plant illnesses at an early stage, thereby increasing fruit yield.
Why it matches plant phenotyping methodsリンゴ果実の画像から病害を自動認識するモデルを開発・評価しており、植物の病害状態を抽出する画像ベースのフェノタイピング手法が中心です。
abstractthis study offered hybrid SVM-RBN model with attentive feature culling method for automatically recognizing diseases in apple fruits with high accuracy
Abstract Food security is a vital aspect of the United Nations’ Sustainable Development Goals (SDGs) which aims to promote sustainable farming in the world. Farming-driven economies such as Ghana are faced with challenges due to plant diseases. Cacao, a vital crop in Ghana is severely impacted with diseases which affect its yield and decrease exports revenue through reduced exports. Leveraging deep learning techniques offers an effective solution for early detection of diseases in cacao plants. This study adopts a comprehensive approach, starting with an Exploratory Data Analysis (EDA) of the dataset containing images of both healthy and diseased cacao plants from Ghanaian farms. Using exploratory data analysis (EDA), we can identify patterns and understand the characteristics of the dataset, laying a solid foundation for developing robust machine learning models tailored to the specific challenges faced by Ghanaian cacao farmers. Our approach involves developing and evaluating deep learning models to detect and classify cacao plant diseases. These models are designed with the Predictability, Compatibility, and Stability (PCS) framework in mind, ensuring reliability and effectiveness in disease detection. The custom convolution neural network (CNN) model outperformed other models considered in experimental analysis. This study aims to revolutionize cacao farming through precise, stable, and ethical deep learning solutions, ultimately enhancing crop resilience, productivity, and the livelihood of Ghanaian farmers.
Why it matches plant phenotyping methodsカカオ植物画像から病害を検出・分類する深層学習手法の開発と評価が中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法に該当する。
abstractdeveloping and evaluating deep learning models to detect and classify cacao plant diseases
The earlier detection of diseases in plant leaves is very important in agriculture. This task requires huge time and someone with great knowledge about the subject. This project aims to develop a robust Web App capable of taking the input of an image and accurately identify plant diseases. A dataset with photographs of multiple types of plant leaves in both healthy and ill situations is selected. Multiple CNN models, including ResNet50 and a Custom CNN, were trained, achieving validation accuracies of 93.96% and 95.58%, respectively. The proposed system provides a scalable and efficient tool for precision agriculture, enabling farmers to address diseases proactively.
Why it matches plant phenotyping methods植物葉の画像から病害状態を推定するCNNモデルとWebアプリを開発しており、植物の病徴・病害状態の画像ベース推定が中心的な方法貢献です。
abstractThis project aims to develop a robust Web App capable of taking the input of an image and accurately identify plant diseases.
Background Poultry is a global industry with laying hens that are genetically optimized for high egg yield. Keel bone fractures can affect up to 80% of laying hens, posing welfare and production problems. Therefore, genetic selection to reduce keel fractures is important. However, the lack of a reliable, automated, and heritable phenotypes for keel bones makes this a challenging task. The aim of this study was to (1) develop automated analyses of radiographic images to phenotype keel bones, and (2) investigate whether the proposed phenotypes are heritable and genetically correlated with the post-dissection scores of keel bone fractures and deviations. A total of 1051 laying hens (Bovans Brown and Lohmann Brown) from a commercial farm were x-rayed, followed by keel bone dissection and scoring for deviations and fractures. Furthermore, blood was sampled for genotyping using 50 K Illumina SNP chips. Keel bones were segmented (with similar to 0.90 accuracy) from the radiographic images using deep learning models, after which the images were automatically measured for general geometry and radiopacity. Multi-trait genomic restricted maximum likelihood was used to estimate genetic parameters.Results Heritability estimates ranged from 0.28 to 0.30 for both keel deviations and fractures observed post-dissection. The automated phenotypes had heritability estimates ranging from 0.07 to 0.10 for keel radiopacity and from 0.11 to 0.39 for keel geometry. Estimates of genetic correlations of keel geometry with keel deviation and fractures ranged from -0.57 to 0.72.Conclusions Automated methods were developed for measuring keel bone radiopacity and geometry. Keel concave area was found to be a reliable and heritable phenotype that breeding companies can use to reduce keel deviations and fractures. These methods can also be adapted to measure other bones (e.g., tibiotarsal) or objects (e.g., eggs), allowing breeders to quickly compute phenotypes for keel, tibia, and egg size from the same radiographic image. The developed methods are well-suited for large-scale studies to assess different housing environments and nutrition strategies aimed at improving keel bone conditions.
Why it matches plant phenotyping methodsニワトリの生体画像から骨形状・放射線不透過性を自動抽出する深層学習ベースの表現型測定法を開発しており、方法開発が研究の中心である。
abstractThe aim of this study was to (1) develop automated analyses of radiographic images to phenotype keel bones
Tomatoes, globally cultivated and economically significant, play an essential role in both commerce and diet. However, the frequent occurrence of diseases severely affects both yield and quality, posing substantial challenges to agricultural production worldwide. In China, where tomato cultivation is carried out on a large scale, disease prevention and identification are increasingly critical for enhancing yield, ensuring food safety, and advancing sustainable agricultural practices. As agricultural production scales and the demand for efficient methodologies grows, traditional disease recognition methods no longer meet current needs. The agricultural sector's move towards more modern and scalable production methods necessitates more effective and precise disease recognition technologies to support swift decision-making and timely preventive actions. To address these challenges, this paper proposes a novel tomato disease recognition method that integrates the data-efficient image transformers (DeiT) model with strategies like exponential moving average (EMA) and self-distillation, named EMA-DeiT. By leveraging deep learning technologies, this method significantly improves the accuracy of disease recognition. The enhanced EMA-DeiT model demonstrated exemplary performance, achieving a 99.6 % accuracy rate in identifying ten types of tomato leaf diseases within the PlantVillage public dataset and 98.2 % on the Dataset of Tomato Leaves, which encompasses six disease types. In generalization tests, it achieved 97.1 % accuracy on the PlantDoc dataset and 97.6 % on the Tomato-Village dataset. Utilizing the improved DeiT model, a comprehensive tomato disease recognition system was developed, featuring modules for image collection, disease detection, and information display. This system facilitates an integrated process from image collection to intelligent disease analysis, enabling agricultural workers to promptly understand and respond to disease occurrences. This system holds significant practical value for implementing precision agriculture and enhancing the efficiency of agricultural production.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から認識するDeiTベースの手法を開発・評価しており、植物病害表現型の取得・推定が研究の中心である。
abstractthis paper proposes a novel tomato disease recognition method that integrates the data-efficient image transformers (DeiT) model with strategies like exponential moving average (EMA) and self-distillation, named EMA-DeiT.
The objectives of this study were to develop and evaluate a novel algorithm for image extraction of structural conformation traits and estimate variance components among skeletal conformation, growth, and herd retention traits. An Intel RealSense D435i camera was used to obtain left-side-view RGB images on individual purebred Duroc pigs (n = 846) at 156 d of age. Frames were selected by a trained swine evaluator when either the left front leg (n = 1056), left back leg (n = 888), or both left legs (n = 728) were present in the field of view and the respective foot pads from toe to heel were in contact with the ground. Selected images were processed through Apple Inc's image segmentation algorithm to extract the pig from the background. Segmented pig images were then processed through a novel algorithm developed in this study. The algorithm identified the leg and estimated 21 skeletal conformation traits from each leg. Steps for user intervention were added to assist the algorithm in identifying which leg(s) were present and the general location of each leg to increase the accuracy of leg identification and trait acquisition. The algorithm correctly identified at least one front and one back leg from an image for 99.9% and 98.0% of the pigs, respectively. Heritability estimates ranged from 0.01 to 0.33 for all conformation traits with the quadratic term for the curvature of the anterior side of the front and the height of the back leg having the highest heritability for each location (h2 = 0.33 and 0.30, respectively). Genetic correlations among image feet and leg conformation traits and production traits (finishing average daily gain, weight per day of age, and finishing feed efficiency) ranged from -0.37 to 0.19. Boars that remained in the breeding herd for longer than 200 d tended (P = 0.08) to have greater curvature of the front leg and lower (P = 0.07) angularity between the midpoint of the foot and the anterior point of the pastern and had significantly (P = 0.03) shorter distance between the pastern and the top of the shoulder than those that were removed prior to 200 d. Gilts that remained in the breeding herd for longer than 200 d tended (P = 0.08) to have less curvature of the back leg. The current study presents an algorithm that extracts novel, objective structural conformation traits and reports corresponding genetic and phenotypic parameters.
Why it matches plant phenotyping methods豚の脚画像から構造的形態形質を抽出する新規アルゴリズムの開発と精度評価が研究の中心であり、遺伝解析も併せて実施しているため。
abstractdevelop and evaluate a novel algorithm for image extraction of structural conformation traits
CowpeaRootMorphology / geometry measurementRoot system architecture
Improving crop production in changing environments can be achieved through selective breeding; however, limited advanced root phenotyping and genotyping in early growth stages hinder assessing root architecture variation and diversity, despite its importance. Therefore, this study utilized advanced image phenotyping on a diverse set of 222 cowpea accessions, revealing significant variations in key phenotypic traits and the genomic regions influencing them. Our study revealed a total of 55 genes linked to major root traits. Among eight root traits—total root length (TRL), surface area (SA), average diameter (AD), root volume (RV), tip number (TN), fork number (FN), primary root length (PRL), and lateral root length (LRL), analyzed, seven significant single nucleotide polymorphisms (SNPs) demonstrated particularly strong associations with three key traits, including surface area (SA), tip number (TN), and fork number (FN). SA emerged as a significant trait, exhibiting considerable variation across the studied accessions. The mean SA was 59.59 cm², with some genotypes surpassing 140.72 cm². Further analysis identified two SNPs that showed significant association with SA, located on two distinct chromosomes: 3 and 11. Similarly, two significant SNPs associated with TN were found on chromosome 3, while three SNPs associated with FN were identified on chromosomes 2, 3, and 8. These findings significantly advance our understanding of the genetic foundations underlying important phenotypic traits in cowpeas, offering a robust framework for future genetic improvement initiatives. The results strongly suggest that implementing breeding programs focused on selecting root phenotypes could significantly enhance cowpea productivity across various environments.
Why it matches plant phenotyping methods根系形態を対象とした高度な画像フェノタイピングを多数アクセッションに適用し、複数の根形質を定量化しているため、フェノタイピング手法の実質的な適用研究である。
abstractTherefore, this study utilized advanced image phenotyping on a diverse set of 222 cowpea accessions, revealing significant variations in key phenotypic traits and the genomic regions influencing them.
Protecting plants from diseases involves recognizing the symptoms and identifying practical, safe, and reasonable treatment methods. Holistic approaches based on particular times or seasons can reduce plant resistance and minimize tedious work. Technological advancements have led to the development of microscopic examinations and computational methods using machine learning techniques to detect diseases automatically and quickly using leaf images. This study builds the prediction model using EfficientNet and YOLO neural network architectures from computer vision. The development of a model that assists farmers in identifying cotton disease so that they use pesticides that may treat it further utilizes this concept. In the physical world, the input is accepted from many different sources, so observing the model’s output is necessary. This work concentrates on model response to the inputs from physical devices, and analysis shows that the monitoring varies the results. A novel convolutional neural network (CNN) based on the EfficientNet architectures and variations of YOLO architectures is used to classify and identify the objects in cotton leaf. The EfficientNetB4 yielded 100% accuracy for healthy leaf and powdery mild leaf classes, and YOLO v4 version with 96%, 98.3%, 99.2%, and 0.70 for precision, recall, mAP@0.5, mAP120.5:095 respectively. These results indicate that consequences vary in real-time per environmental parameters such as light effect and devices, and analysis shows that monitoring affects the results.
Why it matches plant phenotyping methods綿花葉の画像から病徴・病害状態を推定する画像解析モデルを開発・評価しており、植物フェノタイピング手法が中心である。
abstractThis study builds the prediction model using EfficientNet and YOLO neural network architectures from computer vision.
Precision agriculture leverages data and machine learning so that farmers can monitor their crops and target interventions precisely. This enables the precision application of herbicide only to weeds, or the precision application of fertilizer only to undernourished crops, rather than to the entire field. The approach promises to maximize yields while minimizing resource use and harm to the surrounding environment. To this end, we propose a hierarchical panoptic segmentation method that simultaneously determines leaf count (as an identifier of plant growth)and locates weeds within an image. In particular, our approach aims to improve the segmentation of smaller instances like the leaves and weeds by incorporating focal loss and boundary loss. Not only does this result in competitive performance, achieving a PQ+ of 81.89 on the standard training set, but we also demonstrate we can improve leaf-counting accuracy with our method. The code is available at https://github.com/madeleinedarbyshire/HierarchicalMask2Former.
Why it matches plant phenotyping methods植物・葉の階層的パノプティックセグメンテーション法を開発し、葉数という植物成長形質の推定精度を評価しているため、フェノタイピング手法が中心である。
abstractwe propose a hierarchical panoptic segmentation method that simultaneously determines leaf count (as an identifier of plant growth)and locates weeds within an image.
Potato late blight is a common disease affecting crops worldwide. To help detect this disease in complex environments, an improved YOLOv5 algorithm is proposed. First, ShuffleNetV2 is used as the backbone network to reduce the number of parameters and computational load, making the model more lightweight. Second, the coordinate attention mechanism is added to reduce missed detection for leaves that are overlapping, damaged, or hidden, thereby increasing detection accuracy under challenging conditions. Lastly, a bidirectional feature pyramid network is employed to fuse feature information of different scales. The study results show a significant improvement in the model's performance. The number of parameters was reduced from 7.02 to 3.87 M, and the floating point operations dropped from 15.94 to 8.4 G. These reductions make the model lighter and more efficient. The detection speed increased by 16 %, enabling faster detection of potato late blight leaves. Additionally, the average precision improved by 3.22 %, indicating better detection accuracy. Overall, the improved model provides a robust solution for detecting potato late blight in complex environments. The study's findings can be useful for applications and further research in controlling potato late blight in similar environments.
Why it matches plant phenotyping methodsジャガイモ葉の疫病検出を目的にYOLOv5を改良し、精度・速度・計算量を評価しており、植物病害状態の画像ベース推定が中心である。
titlePotato late blight leaf detection in complex environments.
WheatLiDAR / point cloudPanicle / ear / spikeLeafSegmentation
Plant phenotyping is crucial for precisely measuring traits across diverse morphotypes in cereals such as wheat, where the variability in the proportion of ears to leaves poses significant challenges due to class imbalances and the granularity limitations of 3D point cloud data. Our study addresses these intra-class imbalances through two strategies using the PointNet++ network: use plant features i.e., ear ratio and ear count for weighted point cloud sampling and apply class weights in the loss function. We analyze datasets from three morphologically distinct wheat varieties: Paragon, Gladius, and Apogee. Introducing point cloud weights based on ear ratio and ear count significantly improves the network’s ability to recognize underrepresented parts in datasets with uneven distributions of ear and non-ear points. We observe a differential impact in all the categories in terms of segmentation accuracy and average mIoU. In comparison to the base method, all the wheat categories display enhancement in performance after applying both techniques. The best results are obtained with point cloud weights in the loss function for the Gladius dataset, showing a substantial improvement of 10% to 12% in average ear mIoU compared to base method (0.483). Although a similar trend is observed with weighted sampling, the enhanced results in the Gladius dataset range from 0.611 to 0.626 indicate model’s enhanced capability to identify different segments or parts precisely. This research demonstrates the efficacy of our methods in addressing class imbalance issues in point cloud segmentation and provides enhanced accuracy for particularly across different wheat genotypes. In conclusion, the techniques in this study can reliably handle intra class imbalance in diverse datasets, which offers a scalable solution to improve agricultural phenotyping.
Why it matches plant phenotyping methods小麦の3D点群による器官セグメンテーションを対象に、クラス不均衡への重み付きサンプリングと損失関数を開発・評価しており、植物表現型取得の計算手法が研究の中心である。
abstractOur study addresses these intra-class imbalances through two strategies using the PointNet++ network: use plant features i.e., ear ratio and ear count for weighted point cloud sampling and apply class weights in the loss function.
Tea leaf diseases are significant causes of reduced quality and yield in tea production. In the Yunnan region, where the climate is suitable for tea cultivation, tea leaf diseases are small, scattered, and vary in scale, making their detection challenging due to complex backgrounds and issues such as occlusion, overlap, and lighting variations. Existing object detection models often struggle to achieve high accuracy in detecting tea leaf diseases. To address these challenges, this paper proposes a tea leaf disease detection model, BRA-YOLOv7, which combines a dual-level routing dynamic sparse attention mechanism for fast identification of tea leaf diseases in complex scenarios. BRA-YOLOv7 incorporates PConv and FasterNet as replacements for the original network structure of YOLOv7, reducing the number of floating-point operations and improving efficiency. In the Neck layer, a dual-level routing dynamic sparse attention mechanism is introduced to enable flexible computation allocation and content awareness, enhancing the model's ability to capture global information about tea leaf diseases. Finally, the loss function is replaced with MPDIoU to enhance target localization accuracy and reduce false detection cases. Experiments and analysis were conducted on a collected dataset using the Faster R-CNN, YOLOv6, and YOLOv7 models, with Mean Average Precision (mAP), Floating-point Operations (FLOPs), and Frames Per Second (FPS) as evaluation metrics for accuracy and efficiency. The experimental results show that the improved algorithm achieved a 4.8% improvement in recognition accuracy, a 5.3% improvement in recall rate, a 5% improvement in balance score, and a 2.6% improvement in mAP compared to the traditional YOLOv7 algorithm. Furthermore, in external validation, the floating-point operation count decreased by 1.4G, FPS improved by 5.52%, and mAP increased by 2.4%. In conclusion, the improved YOLOv7 model demonstrates remarkable results in terms of parameter quantity, floating-point operation count, model size, and convergence time. It provides efficient lossless identification while balancing recognition accuracy, real-time performance, and model robustness. This has significant implications for adopting targeted preventive measures against tea leaf diseases in the future.
Why it matches plant phenotyping methods茶葉の病徴を画像から検出・認識するモデルを開発し、データセット上で精度・効率・外部検証を評価しており、植物病害状態の表現型取得が中心である。
abstractthis paper proposes a tea leaf disease detection model, BRA-YOLOv7
Strawberry (Fragraria x ananassa) is a crop affected by various soil-borne fungal pathogens with mostly non-specific foliar symptoms and often requiring laboratory isolation for correct diagnosis. Moreover, these nonspecific foliar symptoms, appreciated by the human eye, appear after some time following infection by the pathogen. Early detection of plant diseases is one of the primary objectives in agriculture because it may contribute to identifying more tolerant cultivars in breeding programs and optimise pesticide use in agricultural production with earlier applications in emerging disease foci. New technologies, such as remote sensing and machine learning (ML) algorithms, have arisen as potential tools to improve the ability to detect and classify different crop diseases. The combined use of hyperspectral imagery and ML algorithms were investigated to detect and classify the physiological stress caused by early infections of Fusarium wilt in strawberry plants. Six ML models, namely artificial neural network, decision tree, K-nearest neighbour, support vector machine, multinomial logistic regression and Naïve Bayes were developed to estimate physiological stress associated with Fusarium wilt disease. The results showed that stomatal conductance (gₛ) and photosynthesis (A) declined even without visual symptoms of the disease. Among the six ML models evaluated, the artificial neural network model showed the highest classification performance with an overall accuracy of 81%, regardless of the physiological parameter utilized for model training. Moreover, the artificial neural network accurately predicted the absolute values of both physiological parameters (gₛ and A) based on the complete spectral signature from visually healthy foliar tissue, achieving coefficients of determination of 84% and 81%, respectively. Consequently, ML models utilizing physiological response data and hyperspectral imaging exhibited remarkable robustness, facilitating the estimation of Fusarium wilt severity in strawberry plants even without visual symptoms.
Why it matches plant phenotyping methodsハイパースペクトル画像と機械学習を用いて、イチゴ植物の感染初期の生理的ストレスと萎凋病重症度を推定する手法が研究の中心であるため。
abstractThe combined use of hyperspectral imagery and ML algorithms were investigated to detect and classify the physiological stress caused by early infections of Fusarium wilt in strawberry plants.
• Efficient phenotyping methods to evaluate wheat population under field conditions are needed to breed for high-yielding and heat-tolerant wheat varieties. • Here, we phenotyped the response of 184 genotypes of wheat to heat stress using aerial imagery and physiological dataset. • Wheat genotypes were classified using vegetative and stress indices for heat stress tolerance. • The multispectral-driven phenotypic traits can be used by breeders to select and develop heat-tolerant wheat varieties tolerant to heat stress. Heat stress is a critical environmental factor that adversely affects crop productivity. With the increasing frequency and intensity of heat waves and extreme weather events, heat stress has become a challenge for wheat production, which is one of the most important cereal crops. To sustain wheat production under heat stress conditions, there is an urgent need to develop high-yielding, heat-tolerant wheat varieties. This requires characterizing the genetic and physiological mechanisms underlying heat tolerance, as well as developing efficient phenotyping methods to evaluate a large number of wheat genotypes under heat stress field conditions. In this study, we used 184 wheat genotypes that were sown at two times of sowing (TOS), i.e., optimal sowing as TOS1 and late sowing as TOS2, with higher temperatures faced by plants during heading and grain filling in TOS2. We used a combination of physiological traits, multispectral vegetative indices (VIs) derived from aerial imagery and machine learning approaches to effectively differentiate wheat genotypes for heat tolerance and susceptibility. The response of wheat genotypes to heat stress was delineated as being susceptible, moderate, and tolerant using the stress susceptibility index, percentage loss, and tolerance index. Different VIs varied significantly between the two TOS. The decline in VIs during anthesis and post-anthesis was minimal in heat tolerant genotypes compared to susceptible genotypes under TOS2. We classified the stress severity and yield using VIs with a machine learning approach. A model was created with a random forest classifier (RFC) trained to categorize genotypes based on the stress susceptibility index using Python libraries. The PCA was utilized to reduce dimensionality, and five principal components explaining 99 % of the variability were employed as input for developing the model. The RFC model achieved an accuracy of 64 % and excelled in recognizing crops under extreme stress, with a recall rate of 0.87 and an F1 score of 0.77 for the susceptible class. The model had high precision metrics, with values of 0.69, 0.42, and 0.80 for the susceptible, moderate, and tolerant classes, respectively. Our results suggest that multispectral-driven phenotypic traits can be used by breeders to select and develop wheat varieties tolerant to heat stress.
Why it matches plant phenotyping methods熱ストレス耐性の評価において、航空マルチスペクトル画像からの形質抽出と機械学習分類を中核的に適用しており、植物フェノタイピング手法が中心である。
abstractEfficient phenotyping methods to evaluate wheat population under field conditions are needed to breed for high-yielding and heat-tolerant wheat varieties.
Agriculture is the backbone of the country’s economy. People depend on agriculture for food and exporting to generate income. However, agriculture faces various diseases that affect the quantity and quality of vegetables. Therefore, it is important to propose a model for detecting vegetable diseases. This study proposed a sustainable smart system for vegetable disease detection and classification. This system detects early vegetable diseases in common vegetables such as tomato, potato, lettuce, and cucumber. The study employed deep learning (DL) models to detect and classify vegetable diseases. Convolutional neural networks (CNN) are a type of DL model used for image classification. This study utilizes CNN and other extensions, such as VGG16 and MobileNet, for plant image classification. Three DL models were trained on four datasets for tomato disease classification, potato disease classification, lettuce disease classification, and cucumber disease classification. The results show that the three models achieved 84.49% accuracy on the tomato disease dataset, 97.65% accuracy on the cucumber disease dataset, 97% accuracy on the potato disease dataset, and 99.9% accuracy on the lettuce disease dataset. The proposed system can assist farmers in the early detection of vegetable diseases before they spread, and it can enhance agriculture by improving both the quality and quantity of products.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習手法が研究の中心であり、植物フェノタイピング手法として適格です。
abstractThis study proposed a sustainable smart system for vegetable disease detection and classification.
PURPOSE: The use of Unmanned aerial vehicle (UAV) data for predicting crop above-ground biomass (AGB) is becoming a more feasible alternative to destructive methods. However, canopy height, vegetation index (VI), and other traditional features can become saturated during the mid to late stages of crop growth, significantly impacting the accuracy of AGB prediction. METHODS: In 2022 and 2023, UAV multispectral, RGB, and light detection and ranging point cloud data of wheat populations were collected at seven growth stages across two experimental fields. The point cloud depth features were extracted using the improved PointNet++ network, and AGB was predicted by fusion with VI, color index (CI), and texture index (TI) raster image features. RESULTS: The findings indicate that when the point cloud depth features were fused, the R² values predicted from VI, CI, TI, and canopy height model images increased by 0.05, 0.08, 0.06, and 0.07, respectively. For the combination of VI, CI, and TI, R² increased from 0.86 to a maximum of 0.9, while the root-mean-square error (RMSE) and mean absolute error were 1.80 t ha⁻¹ and 1.36 t ha⁻¹, respectively. Additionally, our findings revealed that the hybrid fusion exhibits the highest accuracy, it demonstrates robust adaptability in predicting AGB across various years, growth stages, crop varieties, nitrogen fertilizer applications, and densities. CONCLUSION: This study effectively addresses the saturation in spectral and chemical information, provides valuable insights for high-precision phenotyping and advanced crop field management, and serves as a reference for studying other crops and phenotypic parameters.
Why it matches plant phenotyping methodsUAV画像・点群から小麦の地上部バイオマスを推定する特徴抽出と深層学習融合手法が研究の中心であり、技術的評価も実施しているため。
abstractThe point cloud depth features were extracted using the improved PointNet++ network, and AGB was predicted by fusion with VI, color index (CI), and texture index (TI) raster image features.
The phenomenon of fluctuating chili prices can be resolved in stages, one of which is through multiple crosses. However, this cross requires precise methods in the evaluation and selection process, especially regarding fruit characteristics. Image-based phenotyping 4.0 approaches can increase the potential precision of such evaluation genotypes, especially when this approach is combined with multivariate analysis. Therefore, both methods are needed to evaluate and select these cayenne multiple crosses. This research aims to identify the effectiveness of multivariate analysis and image-based explanatory characteristics of fruit phenotypes and to select multiple crosses that can continue to the F2 generation. The research was designed with a randomized complete block design of ten F1 multiple cross-genotypes and four check varieties. Each genotype was repeated three times, so there were 42 experimental units. Based on the results, multivariate was considered adequate in determining image explanatory characters based on fruit phenotype and genotype mapping of the population diversity of multiple crosses of cayenne pepper. The characteristics of fruit height, fruit area, and fruit Intden are image-based explanatory characters that can map the completeness of cayenne pepper fruit between multiple crosses well. This indicates that image-based phenotyping and multivariate analysis can provide more detailed image information of the potential of cayenne fruit from multiple crosses than just based on fruit weight. Therefore, both approaches are recommended for analyzing cayenne paper fruit potential, especially for multiple crosses. In addition, three crosses (MC4, MC8, and MC9) are optimal for the next generation to be recommended and continued.
Why it matches plant phenotyping methodsトウガラシ果実形質の画像ベース表現型解析と多変量解析が、交雑系統の評価・選抜の中心的手法として扱われているため。
abstractImage-based phenotyping 4.0 approaches can increase the potential precision of such evaluation genotypes, especially when this approach is combined with multivariate analysis.
Abstract. Accurate crop yield prediction is crucial for efficient agricultural and socio-economic management. Remote sensing, using satellite imagery and unmanned aerial vehicles (UAVs), provides an effective approach for yield prediction and crop monitoring, allowing time series of vegetation indices such as NDVI to be obtained and facilitating detailed analysis of crop phenology. In this study, multi-seasonality in rice yield prediction is analysed using NDVI time series obtained from Sentinel-2 (S2) and UAVs in the Lambayeque region, Peru. NDVI from S2 was extracted by applying scene classification map (SCM) masks to remove clouds and shadows. A total of 7 and 11 UAV flights were conducted during the growing season for 2022 and 2023, and yield was collected mechanically in 35 rice-producing plots. The results showed an overestimation of NDVI values obtained by UAV compared to Sentinel-2 values, as well as a significant difference in yield prediction between 2022 and 2023. In 2022, by integrating S2 and UAV NDVI series, a coefficient of determination (R2) of 0.66 was obtained for the combination of UAV and S2, higher value than those obtained with UAV or S2 independently, with a root mean square error (RMSE) of 1.096 t/ha and a %RMSE of 10.36. In 2023, a R2 of 0.32, a RMSE of 0.85 and a %RMSE of 9.21 were achieved. This difference is interpreted as a consequence of the cyclone Yaku, which caused rainfall and damage to the irrigation infrastructure, and fungi disease, leading to water stress and a decrease in yield, highlighting the importance of considering the meteorological conditions in the development of yield predictions based on NDVI series metrics obtained along the campaign.
Why it matches plant phenotyping methodsUAV・Sentinel-2のNDVI時系列からイネ圃場の収量を推定し、複数年・センサー間で予測性能を評価する方法論的研究であり、収量という植物形質の取得・推定が中心である。
abstractIn this study, multi-seasonality in rice yield prediction is analysed using NDVI time series obtained from Sentinel-2 (S2) and UAVs in the Lambayeque region, Peru.
Effective identification and classification of plant diseases are critical for maintaining agricultural productivity and ensuring food security. With recent advancements in computer vision, Convolutional Neural Networks (CNNs) have emerged as powerful tools for diagnosing crop diseases. This research presents a novel approach for detecting apple plant diseases through the analysis of leaf images using CNNs. We utilize the PlantVillage dataset, which comprises a diverse collection of healthy and diseased apple leaf images. The dataset undergoes rigorous preprocessing to enhance image quality, followed by training and evaluation of the CNN models. Our approach achieves remarkable results, demonstrating an accuracy of 99.67%, precision of 98.23%, and F1 score of 99.04%. These findings affirm the robustness of our CNN-based model in accurately classifying various apple diseases. This research not only provides a reliable method for early disease detection but also emphasizes its significance in optimizing crop yield and safeguarding food security. By facilitating timely interventions, our proposed framework has the potential to mitigate the impact of diseases in apple orchards and can be extended to broader applications in precision agriculture.
Why it matches plant phenotyping methodsリンゴ葉画像から病害状態をCNNで推定する画像ベースの植物表現型解析手法が研究の中心であり、学習・評価による技術検証も行っている。
abstractThis research presents a novel approach for detecting apple plant diseases through the analysis of leaf images using CNNs.
Hyperspectral images from newly launched (ASI-PRISMA and DLR-EnMAP) and future satellite (ESA-CHIME) are an opportunity, thanks to the high spectral resolution and full range continuity, to improve the retrieval of information about the crop parameters and status.The high dimensionality of hyperspectral data and the non-linear relationship between the crop biophysical parameters and their spectral signature make quantitative estimation of crop characteristics challenging, to address these problems we tested different configurations of neural networks (fully connected and convolutional).We tested the different architectures on two training dataset, one consists in ground data collected in three experiments, in different locations and seasons, the second one (hybrid) is composed by synthetic data generated using a radiative transfer model (PROSAIL-PRO).Preliminary results for LAI, CCC and CNC retrieval are encouraging in particular when ground data are exploited demonstrating of the potentiality of NN to fully exploit the information density of the hyperspectral data.
Why it matches plant phenotyping methodsハイパースペクトルデータからLAI・CCC・CNCなどの作物形質を推定するニューラルネットワーク構成を評価しており、形質取得・推定手法の検証が研究の中心である。
abstractwe tested different configurations of neural networks (fully connected and convolutional)
Field / plotLeafStem / branchSegmentationDisease symptoms / severity
Introduction Zanthoxylum bungeanum Maxim is an economically significant crop in Asia, but large-scale cultivation is often threatened by frequent diseases, leading to significant yield declines. Deep learning-based methods for crop disease recognition have emerged as a vital research area in agriculture. Methods This paper presents a novel model, LT-DeepLab, for the semantic segmentation of leaf spot (folium macula), rust, frost damage (gelu damnum), and diseased leaves and trunks in complex field environments. The proposed model enhances DeepLabV3+ with an innovative Fission Depth Separable with CRCC Atrous Spatial Pyramid Pooling module, which reduces the structural parameters of Atrous Spatial Pyramid Pooling module and improves cross-scale extraction capability. Incorporating Criss-Cross Attention with the Convolutional Block Attention Module provides a complementary boost to channel feature extraction. Additionally, deformable convolution enhances low-dimensional features, and a Fully Convolutional Network auxiliary header is integrated to optimize the network and enhance model accuracy without increasing parameter count. Results LT-DeepLab improves the mean Intersection over Union (mIoU) by 3.59%, the mean Pixel Accuracy (mPA) by 2.16%, and the Overall Accuracy (OA) by 0.94% compared to the baseline DeepLabV3+. It also reduces computational demands by 11.11% and decreases the parameter count by 16.82%. Discussion These results indicate that LT-DeepLab demonstrates excellent disease segmentation capabilities in complex field environments while maintaining high computational efficiency, offering a promising solution for improving crop disease management efficiency.
Why it matches plant phenotyping methods植物の葉・幹の病斑や病害状態を画像から抽出するセマンティックセグメンテーション手法を開発・評価しており、植物病害表現型の取得が中心的です。
abstractThis paper presents a novel model, LT-DeepLab, for the semantic segmentation of leaf spot (folium macula), rust, frost damage (gelu damnum), and diseased leaves and trunks in complex field environments.
Tea leaf blight (TLB) is a common disease of tea plants and is widely distributed in tea gardens. Although the use of unmanned aerial vehicle (UAV) remote sensing can help to achieve a wider scale for TLB detection, the blurring of UAV images, overlapping of tea leaves, and small size of TLB spots pose significant challenges to the task of detection. This study proposes a method of detecting TLB in UAV remote sensing images by integrating super-resolution (SR) and detection networks. We use an SR network called SERB-Swin2sr to reconstruct the detailed features of UAV images and solve the problem of detail loss caused by the blurring in UAV images. In SERB-Swin2sr, a squeeze-and-excitation ResNet block (SERB) is introduced to enhance the models' ability to extract the target details in the images, and the convolution stem replaces the convolution block in order to increase the convergence rate and stability of the network. A detection network called SDDA-YOLO is applied to achieve precise detection of TLB in UAV remote sensing images. In SDDA-YOLO, a shuffle dual-dimensional attention (SDDA) module is introduced to enhance the feature fusion capability of the network, and an Xsmall-scale detection layer is used to enhance the detection ability of small lesions. Experimental results show that the proposed method is superior to current detection methods. Compared with a baseline YOLOv8 model, the precision, mAP@0.5, and mAP@0.5:0.95 of the proposed method are improved by 4.2%, 1.6%, and 1.8%, and the size of our model is only 4.6 MB.
Why it matches plant phenotyping methods茶葉の病斑という植物病態をUAV画像から検出する新規画像解析手法を開発・比較しており、病害状態の表現型取得が中心である。
abstractThis study proposes a method of detecting TLB in UAV remote sensing images by integrating super-resolution (SR) and detection networks.
Stripe rust caused by Puccinia striiformis f. sp. tritici and leaf rust caused by Puccinia triticina , are two devastating diseases on wheat, which seriously affect the production safety of wheat. Timely detection and identification of the two diseases are essential for taking effective disease management measures to reduce wheat yield losses. To realize the accurate identification of wheat stripe rust and wheat leaf rust during the different growth stages, in this study, the image-based identification of wheat stripe rust and wheat leaf rust during different growth stages was investigated based on deep learning using image processing technology. Based on the YOLOv5s model, we built identification models of wheat stripe rust and wheat leaf rust during the seedling stage, stem elongation stage, booting stage, inflorescence emergence stage, anthesis stage, milk development stage, and all the growth stages. The models were tested on the different testing sets in the different individual growth stages and in all the growth stages. The results showed that the models performed differently in disease image identification. The model based on the disease images acquired during an individual growth stage was not suitable for the identification of the disease images acquired during the other individual growth stages, except for the model based on the disease images acquired during the milk development stage, which had acceptable identification performance on the testing sets in the anthesis stage and the milk development stage. In addition, the results demonstrated that wheat growth stages had a great influence on the image identification of the two diseases. The model built based on the disease images acquired in all the growth stages produced acceptable identification results. Mean F1 Score values between 64.06% and 79.98% and mean average precision (mAP) values between 66.55% and 82.80% were achieved on each testing set composed of the disease images acquired during an individual growth stage and on the testing set composed of the disease images acquired during all the growth stages. This study provides a basis for the image-based identification of wheat stripe rust and wheat leaf rust during the different growth stages, and it provides a reference for the accurate identification of other plant diseases.
Why it matches plant phenotyping methods画像から小麦の病害状態を推定するYOLOv5s手法を開発・評価しており、植物病害フェノタイピングが研究の中心です。
abstractthe image-based identification of wheat stripe rust and wheat leaf rust during different growth stages was investigated based on deep learning using image processing technology.
This research explores a new method for assessing chili plant health using multispectral camera imagery and deep learning-based image segmentation. Data from Bale Tatanen Universitas Padjadjaran chili farms were used to create a labeled dataset with four health categories. Initial image processing involved FastSAM inference to generate binary masks, followed by training a YOLOv8 model for improved segmentation accuracy. This model enabled NDVI calculation and automatic health labeling in unseen images, contributing to automated chili plant health monitoring systems. Evaluation showed an average Dice Coefficient of 63.80%, indicating moderate overlap between predicted and true masks. High precision and robust segmentation across various conditions were observed, though improvements are needed in fine detail segmentation. This approach enhances understanding of chili plant health and supports further studies in the field.
Why it matches plant phenotyping methodsマルチスペクトル画像のセグメンテーション、ラベル付きデータセット構築、未見画像での健康状態自動推定を中心とする植物フェノタイピング手法研究であり、性能評価も実施している。
abstractThis research explores a new method for assessing chili plant health using multispectral camera imagery and deep learning-based image segmentation.
Tea plants are susceptible to diseases during their growth. These diseases seriously affect the yield and quality of tea. The effective prevention and control of diseases requires accurate identification of diseases. With the development of artificial intelligence and computer vision, automatic recognition of plant diseases using image features has become feasible. As the support vector machine (SVM) is suitable for high dimension, high noise, and small sample learning, this paper uses the support vector machine learning method to realize the segmentation of disease spots of diseased tea plants. An improved Conditional Deep Convolutional Generation Adversarial Network with Gradient Penalty (C-DCGAN-GP) was used to expand the segmentation of tea plant spots. Finally, the Visual Geometry Group 16 (VGG16) deep learning classification network was trained by the expanded tea lesion images to realize tea disease recognition.
Why it matches plant phenotyping methods罹病茶葉の病斑を画像からセグメンテーションし、植物病害を認識する手法が研究の中心であり、植物状態の表現型推定に該当する。
abstractthis paper uses the support vector machine learning method to realize the segmentation of disease spots of diseased tea plants
Plant counting is a critical aspect of crop management, providing farmers with valuable insights into seed germination success and within-field variation in crop population density, both of which are key indicators of crop yield and quality. Recent advancements in Unmanned Aerial System (UAS) technology, coupled with deep learning techniques, have facilitated the development of automated plant counting methods. Various computer vision models based on UAS images are available for detecting and classifying crop plants. However, their accuracy relies largely on the availability of substantial manually labeled training datasets. The objective of this study was to develop a robust corn counting model by developing and integrating an automatic image annotation framework. This study used high-spatial-resolution images collected with a DJI Mavic Pro 2 at the V2-V4 growth stage of corn plants from a field in Wooster, Ohio. The automated image annotation process involved extracting corn rows and applying image enhancement techniques to automatically annotate images as either corn or non-corn, resulting in 80% accuracy in identifying corn plants. The accuracy of corn stand identification was further improved by training four deep learning (DL) models, including InceptionV3, VGG16, VGG19, and Vision Transformer (ViT), with annotated images across various datasets. Notably, VGG16 outperformed the other three models, achieving an F1 score of 0.955. When the corn counts were compared to ground truth data across five test regions, VGG achieved an R 2 of 0.94 and an RMSE of 9.95. The integration of an automated image annotation process into the training of the DL models provided notable benefits in terms of model scaling and consistency. The developed framework can efficiently manage large-scale data generation, streamlining the process for the rapid development and deployment of corn counting DL models.
Why it matches plant phenotyping methodsUAS画像からトウモロコシ個体数を抽出する自動アノテーションと深層学習計数モデルの開発・検証が研究の中心であり、植物個体数という形態・生育状態を測定するため。
abstractThe objective of this study was to develop a robust corn counting model by developing and integrating an automatic image annotation framework.
In-situ leaf chlorophyll content (LCC) estimation based on hyperspectral imaging (HSI) is crucial to track the growth status of crops for field management. However, spatial and spectral features of HSI data, suffering from interference of growth dynamic effect and soil, pose the challenge on accuracy and robustness of LCC estimation in several years and growth stages. Therefore, a joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation. Firstly, crop pixels were separated from soil with vegetation index segmentation method. Secondly, when raw images and segmented pixels were input, sensitive bands were selected by random frog (RF bands), and 3DCNN-LSTM was used to extract the joint spectral-spatial features. Finally, models established by RF bands, 3DCNN and 3DCNN-LSTM were compared, and robustness in individual years and stages was validated. Results showed that RF bands and 3DCNN obtained RP² of 0.76 and 0.84 when not segmented. After segmentation, performance of 3DCNN improved (RP² = 0.85) compared to RF bands (RP² = 0.80). Spectral-spatial features by 3DCNN reduced the interference of soil. 3DCNN-LSTM without and with segmentation obtained good performance with RP² of 0.95 and 0.96, and the proposed method could reduce the image segmentation process. The optimal model achieved RP² above 0.93 in individual years (RP² = 0.96 in 2021, RP² = 0.94 in 2021) and RP² in the range of 0.87–0.97 at individual stages. This paper provides a method to track growth variability between soil and crop for the LCC estimation optimisation.
Why it matches plant phenotyping methodsハイパースペクトル画像から葉緑素含量という植物形質を推定する特徴抽出・深層学習手法を開発し、複数年・生育段階で性能検証しており、表現型取得手法が中心である。
abstracta joint spectral-spatial feature extraction method was proposed by cascade of three-dimensional convolutional neural network (3DCNN) and long short-term memory (LSTM) to reduce the interference for optimising the LCC estimation.
The type of crops plays a critical role in determining the canopy light interception and is a decisive factor for yield. Thus, it is of significant importance to have a comprehensive understanding of the similarities and differences in plant type for crop improvement. In this study, the Structure-from-Motion in conjunction with multi-view stereo (SfM-MVS) method was employed to capture multi-angle images of 132 sugar beet varieties at two growth stages, from which three-dimensional(3D) point clouds were reconstructed for all individual sugar beets. Nine plant phenotypic traits were extracted based on the point clouds, and their correlations and heritability were calculated. An unsupervised machine learning approach was utilized to classify all varieties based on their plant type, and the characteristics of different types were statistically analyzed. Subsequently, a variety of different canopies were simulated, and a ray-tracing software was used to simulate light interception of the day. The results revealed that sugar beet plants could be roughly classified into five distinct types with significant differences of the structure. The coefficient of variation of phenotypic parameters for all varieties was 33.2 % in July and decreased to 26.7 % in August. The heritability similarly declined from 0.82 to 0.50, indicating that the structure of the sugar beet plants was exacerbated by environmental influences as the growing season progressed. The light interception results showed that intercropping with different plant types had different effects on light interception, with differences in light interception of up to 1000 W/h across the canopy in July, but this effect was not always favorable, and a decrease in the total amount of light interception also occurred in intercropping with different plant types compared to monocropping.
Why it matches plant phenotyping methodsSfM-MVSによる3D再構築から9つの植物表現型形質を抽出する手法が研究の中心であり、多数品種への実質的な適用と形質解析を行っている。
abstractthe Structure-from-Motion in conjunction with multi-view stereo (SfM-MVS) method was employed to capture multi-angle images of 132 sugar beet varieties at two growth stages, from which three-dimensional(3D) point clouds were reconstructed for all individual sugar beets.
The agricultural sector in Bangladesh is a cornerstone of the nation's economy, with key crops such as rice, corn, wheat, potato, and tomato playing vital roles. However, these crops are highly vulnerable to various leaf diseases, which pose significant threats to crop yields and food security if not promptly addressed. Consequently, there is an urgent need for an automated system that can accurately identify and categorize leaf diseases, enabling early intervention and management. This study explores the efficacy of the latest state-of-the-art object detection model, YOLOv8 (You Only Look Once), in surpassing previous models for the automated detection and categorization of leaf diseases in these five major crops. By leveraging modern computer vision techniques, the goal is to enhance the efficiency of disease detection and management. A dataset comprising 19 classes, each with 150 images, totaling 2850 images, was meticulously curated and annotated for training and evaluation. The YOLOv8 framework, known for its capability to detect multiple objects simultaneously, was employed to train a deep neural network. The system's performance was evaluated using standard metrics such as mean Average Precision (mAP) and F1 score. The findings demonstrate that the YOLOv8 framework successfully identifies leaf diseases, achieving a high mAP of 98% and an F1 score of 97%. These results underscore the significant potential of this approach to enhance crop disease management, thereby improving food security and promoting agricultural sustainability in Bangladesh.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定するYOLOv8手法の開発・評価が研究の中心であり、植物表現型（病害状態）の計測に該当する。
abstractThis study explores the efficacy of the latest state-of-the-art object detection model, YOLOv8 (You Only Look Once), in surpassing previous models for the automated detection and categorization of leaf diseases in these five major crops.
Plant diseases can inflict varying degrees of damage on agricultural production. Therefore, identifying a rapid, non-destructive early diagnostic method is crucial for safeguarding plants. Cladosporium fulvum (C. fulvum) is one of the major diseases in tomato growth. This work presents a method of data fusion using two hyperspectral imaging systems of visible/near-infrared (VIS/NIR) and near-infrared (NIR) spectroscopy for the early diagnosis of C. fulvum in greenhouse tomatoes. First, hyperspectral images of samples at health and different times of infection were collected. The average spectral data of the image regions of interest were extracted and preprocessed for subsequent spectral datasets. Then different classification models were established for VIS/NIR and NIR data, optimized through various variable selection and data fusion methods. The principal component analysis-radial basis function neural network (PCA-RBF) model established using low-level data fusion achieved optimal results, achieving accuracies of 100% and 99.3% for calibration and prediction, respectively. Moreover, both the macro-averaged F1 (Macro-F1) values reached 1, and the geometric mean (G-mean) values reached 1 and 1, respectively. The results indicated that it was feasible to establish a PCA-RBF model by using the hyperspectral technique with low-level data fusion for the early detection of C. fulvum in greenhouse tomatoes.
Why it matches plant phenotyping methodsトマト葉の感染状態をハイパースペクトル画像から直接推定するデータ融合・分類手法を開発し、精度評価しており、植物病害表現型の取得・判定が中心である。
abstractThis work presents a method of data fusion using two hyperspectral imaging systems of visible/near-infrared (VIS/NIR) and near-infrared (NIR) spectroscopy for the early diagnosis of C. fulvum in greenhouse tomatoes.
Agriculture is important for the survival of humanity since about 70% of the world's population is engaged in agricultural pursuits to varying degrees. The previous and present methodology lacks ways to identify diseases in different crops within an agricultural environment. The crops most impacted by these illnesses are tomatoes, leading to a significant increase in the price of tomatoes. Controlling tomato illnesses is crucial for optimal development and production, making early diagnosis and disease detection vital. Early disease diagnosis and treatment in tomato plants can lead to improved yields. Tomato plants are susceptible to illnesses, which can significantly affect the quality, quantity, and productivity of the crop if not properly treated. Despite many unsuccessful efforts to utilize machine learning methods for detecting and classifying illnesses in tomato plants. This study introduces a comparative framework for segmenting tomato leaf regions using both conventional and swarm intelligence methodologies to determine the more effective approach. This framework enables the development of a tomato plant diagnosis system capable of analyzing various sorts of images, including both standard and custom image datasets. The obtained evaluation parameters of the proposed model in terms of average precision, recall, f-measure, error, and accuracy are 0.914, 0.915, 0.915, 1.55% and 98.45%, respectively. We performed a comparative examination of six scenarios: T-model, K-model, TPSO-model, KPSO-model, TGO-model, and KGO-model. The combination of K-means with the GO algorithm proved to be a powerful hybrid technique, with an accuracy of 96.45%. Comparatively, the T-model, K-model, TPSO-model, KPSO-model, and TGO-model attained accuracies of 85.73%, 86.61%, 87.54%, 88.64%, and 92.21% correspondingly.
Why it matches plant phenotyping methodsトマト葉領域の画像セグメンテーション手法を比較・評価し、植物病害診断への利用を目指す研究であり、表現型取得・抽出の方法が中心です。
abstractThis study introduces a comparative framework for segmenting tomato leaf regions using both conventional and swarm intelligence methodologies to determine the more effective approach.
Food security depends on the early detection of agricultural diseases, particularly in Sub-Saharan Africa. Professionals visually evaluate the plants by searching for disease indications on the leaves to diagnose cassava infections, a notoriously subjective process. Farmers in remote areas may be able to monitor their crops without the assistance of specialists if crop diseases are automatically detected and classified. This could aid in the more accurate diagnosis of diseases by professionals. Crop disease classification and early identification have benefited from the application of machine learning techniques. Despite their excellent accuracy, there is no single machine learning model that can provide optimal results on all the datasets. In this study, a Bayesian optimization of the Convolutional Neural Network (CNN) model was proposed. The model was trained using the spectral dataset. Since spectral data is highly dimensional, dimensionality reduction was performed on the dataset using PCA. The experimental results revealed that the proposed model had an accuracy of 85.19%, Precision of 85.23%, Recall of 85.16%, and F1 score of 85.20%. Also, the proposed model had an AUC of 0.95 which demonstrates excellent performance. However, there is still a need to improve the overall performance of the proposed model and we recommend the use of a pretrained transfer learning approach in future studies.
Why it matches plant phenotyping methodsカッサバ葉のスペクトルデータから病害を自動分類するCNNをベイズ最適化し、性能評価している。感染植物の病害状態を直接推定する方法が研究の中心である。
abstractIn this study, a Bayesian optimization of the Convolutional Neural Network (CNN) model was proposed.
Utilizing visible and near-infrared (Vis-NIR) spectroscopy in conjunction with chemometrics methods has been widespread for identifying plant diseases. However, a key obstacle involves the extraction of relevant spectral characteristics. This study aimed to enhance sugarcane disease recognition by combining convolutional neural network (CNN) with continuous wavelet transform (CWT) spectrograms for spectral features extraction within the Vis-NIR spectra (380-1400 nm) to improve the accuracy of sugarcane diseases recognition. Using 130 sugarcane leaf samples, the obtained one-dimensional CWT coefficients from Vis-NIR spectra were transformed into two-dimensional spectrograms. Employing CNN, spectrogram features were extracted and incorporated into decision tree, K-nearest neighbour, partial least squares discriminant analysis, and random forest (RF) calibration models. The RF model, integrating spectrogram-derived features, demonstrated the best performance with an average precision of 0.9111, sensitivity of 0.9733, specificity of 0.9791, and accuracy of 0.9487. This study may offer a non-destructive, rapid, and accurate means to detect sugarcane diseases, enabling farmers to receive timely and actionable insights on the crops' health, thus minimizing crop loss and optimizing yields.
Why it matches plant phenotyping methodsサトウキビ葉の病害状態を対象に、Vis-NIR分光、CWTスペクトログラム、CNNおよび分類モデルを組み合わせた非破壊的な病害認識手法を開発・評価しており、植物表現型の取得・抽出が中心である。
abstractThis study aimed to enhance sugarcane disease recognition by combining convolutional neural network (CNN) with continuous wavelet transform (CWT) spectrograms for spectral features extraction within the Vis-NIR spectra (380-1400 nm)
Abstract Detecting and quantifying the diseased regions in a leaf is an important task in plant breeding in order to select plants based on disease resistance. Ratings done by eye and hand are not accurate, can be highly subjective and take a lot of work hours. Using machine learning, it is possible to generate faster more accurate data. By combining modern anomaly detection algorithms with masking algorithms a robust method capable of estimating the infected leaf area was developed, resulting in a novel method with superior results. Using unsupervised models both for the masking and for the detection, the method can easily be used for different kinds of detection tasks.
Why it matches plant phenotyping methods葉の病斑領域と感染面積を画像から推定する機械学習手法の開発が研究の中心であり、植物病害の表現型測定に該当する。
abstractUsing machine learning, it is possible to generate faster more accurate data.
Wheat exhibits complex characteristics during its growth, such as extensive tillering, slender and soft leaves, and severe organ cross-obscuration, posing a considerable challenge in full-cycle phenotypic monitoring. To address this, this study presents a synthesized method based on SFM-MVS (Structure-from-Motion, Multi-View Stereo) processing for handling and segmenting wheat point clouds, covering the entire growth cycle from seedling to grain filling stages. First, a multi-view image acquisition platform was constructed to capture image sequences of wheat plants, and dense point clouds were generated using SFM-MVS technology. High-quality dense point clouds were produced by implementing improved Euclidean clustering combined with centroids, color filtering, and statistical filtering methods. Subsequently, the segmentation of wheat plant stems and leaves was performed using the region growth segmentation algorithm. Although segmentation performance was suboptimal during the tillering, jointing, and booting stages due to the glut leaves and severe overlap, there was a salient improvement in wheat leaf segmentation efficiency over the entire growth cycle. Finally, phenotypic parameters were analyzed across different growth stages, comparing automated measurements of plant height, leaf length, and leaf width with actual measurements. The results demonstrated coefficients of determination ( R 2 ) of 0.9979, 0.9977, and 0.995; root mean square errors (RMSE) of 1.0773 cm, 0.2612 cm, and 0.0335 cm; and relative root mean square errors (RRMSE) of 2.1858%, 1.7483%, and 2.8462%, respectively. These results validate the reliability and accuracy of our proposed workflow in processing wheat point clouds and automatically extracting plant height, leaf length, and leaf width, indicating that our 3D reconstructed wheat model achieves high precision and can quickly, accurately, and non-destructively extract phenotypic parameters. Additionally, plant height, convex hull volume, plant surface area, and Crown area were extracted, providing a detailed analysis of dynamic changes in wheat throughout its growth cycle. ANOVA was conducted across different cultivars, accurately revealing significant differences at various growth stages. This study proposes a convenient, rapid, and quantitative analysis method, offering crucial technical support for wheat plant phenotypic analysis and growth dynamics monitoring, applicable for precise full-cycle phenotypic monitoring of wheat.
Why it matches plant phenotyping methodsSFM-MVS画像取得・点群処理・分割による小麦形質抽出ワークフローを開発し、実測値との比較で精度検証しているため、植物フェノタイピング手法が研究の中心である。
abstractthis study presents a synthesized method based on SFM-MVS (Structure-from-Motion, Multi-View Stereo) processing for handling and segmenting wheat point clouds
Introduction Mechanical damage significantly reduces the market value of fruits, making the early detection of such damage a critical aspect of agricultural management. This study focuses on the early detection of mechanical damage in blueberries (variety: Sapphire) through a non-destructive method. Methods The proposed method integrates hyperspectral image fusion with a multi-strategy improved support vector machine (SVM) model. Initially, spectral features and image features were extracted from the hyperspectral information using the successive projections algorithm (SPA) and Grey Level Co-occurrence Matrix (GLCM), respectively. Different models including SVM, RF (Random Forest), and PLS-DA (Partial Least Squares Discriminant Analysis) were developed based on the extracted features. To refine the SVM model, its hyperparameters were optimized using a multi-strategy improved Beluga Whale Optimization (BWO) algorithm. Results The SVM model, upon optimization with the multi-strategy improved BWO algorithm, demonstrated superior performance, achieving the highest classification accuracy among the models tested. The optimized SVM model achieved a classification accuracy of 95.00% on the test set. Discussion The integration of hyperspectral image information through feature fusion proved highly efficient for the early detection of bruising in blueberries. However, the effectiveness of this technology is contingent upon specific conditions in the detection environment, such as light intensity and temperature. The high accuracy of the optimized SVM model underscores its potential utility in post-harvest assessment of blueberries for early detection of bruising. Despite these promising results, further studies are needed to validate the model under varying environmental conditions and to explore its applicability to other fruit varieties.
Why it matches plant phenotyping methodsブルーベリー果実の打撲状態を、ハイパースペクトル画像から特徴抽出・情報融合し、最適化SVMで非破壊的に判定する手法が研究の中心であるため、植物状態の画像ベース表現型計測に該当する。
abstractThis study focuses on the early detection of mechanical damage in blueberries (variety: Sapphire) through a non-destructive method.
Recent advancements in high-throughput phenotyping have led to the use of drones with RGB sensors for evaluating plant traits. This study explored the relationships between vegetation indices (VIs) with grain yield and morphoagronomic and physiological traits in maize genotypes. Eight maize hybrids, including those from the UENF breeding program and commercial varieties, were evaluated using a randomized block design with four replications. VIs were obtained at various stages using drones and Pix4D Mapper 4.7.5 software. Analysis revealed significant differences in morphoagronomic traits and photosynthetic capacity. At 119 days after planting (DAP), the RGB vegetation index VARI showed a significant correlation (r = 0.99) with grain yield. VARI also correlated with female flowering (r = −0.87), plant height (r = −0.79), 100-grain weight (r = −0.77), and anthocyanin concentration (r = −0.86). PCA showed a clear separation between local and commercial hybrids, explaining 46.7% of variance at 91 DAP, 52.3% at 98 DAP, 64.2% at 112 DAP, and 66.1% at 119 DAP. This study highlights the utility of VIs in maize phenotyping and genotype selection during advanced reproductive stages.
Why it matches plant phenotyping methodsUAV RGB画像から植生指数を算出し、収量・形態・生理形質との関係を評価することが研究の中心であり、トウモロコシ表現型解析への実質的な手法適用に該当する。
titleUtilizing Visible Band Vegetation Indices from Unmanned Aerial Vehicle Images for Maize Phenotyping
Soybean pod count is a crucial aspect of soybean plant phenotyping, offering valuable reference information for breeding and planting management. Traditional manual counting methods are not only costly but also prone to errors. Existing detection-based soybean pod counting methods face challenges due to the crowded and uneven distribution of soybean pods on the plants. To tackle this issue, we propose a Soybean Pod Counting Network (SPCN) for accurate soybean pod counting. SPCN is a density map-based architecture based on Hybrid Dilated Convolution (HDC) strategy and attention mechanism for feature extraction, using the Unbalanced Optimal Transport (UOT) loss function for supervising density map generation. Additionally, we introduce a new diverse dataset, BeanCount-1500, comprising of 24,684 images of 316 soybean varieties with various backgrounds and lighting conditions. Extensive experiments on BeanCount-1500 demonstrate the advantages of SPCN in soybean pod counting with an Mean Absolute Error(MAE) and an Mean Squared Error(MSE) of 4.37 and 6.45, respectively, significantly outperforming the current competing method by a substantial margin. Its excellent performance on the Renshou2021 dataset further confirms its outstanding generalization potential. Overall, the proposed method can provide technical support for intelligent breeding and planting management of soybean, promoting the digital and precise management of agriculture in general.
Why it matches plant phenotyping methods大豆莢数という植物形質を画像から自動推定する手法を開発し、データセット上で性能評価しているため、植物フェノタイピング手法が研究の中心です。
abstractSoybean pod count is a crucial aspect of soybean plant phenotyping
Reproduction assets foundThe paper's SPCN analysis code is stated to be publicly available on GitHub. The BeanCount-1500 dataset itself has no public deposit or availability statement (authors must be contacted), so it does not qualify as a public asset.Code · publicThe source code is available at https://github.com/johnhamtom/
soybean_counting_SPCN (accessed on 10 August 2024).Open asset ↗pdf-page:2 lines:1-58Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
It is common to observe conventional methods for estimating soybean crop yields, making the process slow and susceptible to human error. Therefore, the objective was to develop a model based on deep learning to estimate soybean yield using digital images obtained through a smartphone. To do this, the ability of the proposed model to correctly classify pods that have different numbers of grains, count the number of pods and grains, and then estimate the soybean crop yield was analyzed. As part of the study, two types of image acquisition were performed for the same plant. Image acquisition 1 (IA1) included capturing the images of the entire plant, pods, leaves, and branches. Image acquisition 2 (IA2) included capturing the images of the pods removed from the plant and deposited in a white container. In both acquisition methods, two soybean cultivars, TMG 7063 Ipro and TMG 7363 RR, were used. In total, combining samples from both cultivars, 495 images were captured, with each image corresponding to a sample (plant) obtained through methods AI1 and AI2. With these images, the total number of pods in the entire dataset was 46,385 pods. For the training and validation of the model, the data was divided into subsets of training, validation, and testing, representing, respectively, 80, 10, and 10% of the total dataset. In general, when using the data from IA2, the model presented errors of 7.50 and 5.32% for pods and grains, respectively. These values are considerably lower than when the model used the IA1 data, where it presented errors of 34.69 and 35.25% for pod and grain counts, respectively. Therefore, the data used from IA2 provide better results to the model.
Why it matches plant phenotyping methodsスマートフォン画像と深層学習により、莢・粒数を抽出してダイズ収量を推定する方法を開発・検証しており、植物表現型取得が中心である。
abstractthe objective was to develop a model based on deep learning to estimate soybean yield using digital images obtained through a smartphone
Early and accurate plant disease detection is crucial for sustainable agriculture. This research proposes an Ensemble Residual Sequence Net (ERSN) architecture, combining LSTM and ResNet-50, for classifying plant diseases in pearl millet. Targeting diseases like downy mildew, ergot, blast, rust, and smut, the model achieved high accuracy (94.7%), precision, recall, F I-score, specificity, and sensitivity. This innovative approach demonstrates the potential of deep learning in enhancing plant disease management and safeguarding crop yields.
Why it matches plant phenotyping methods画像に基づき植物病害を分類・検出する深層学習手法の開発と性能評価が主題であり、植物の病害状態を推定するフェノタイピング手法に該当する。
abstractThis research proposes an Ensemble Residual Sequence Net (ERSN) architecture, combining LSTM and ResNet-50, for classifying plant diseases in pearl millet.
Drought stress is one of the main threats to poplar plant growth and has a negative impact on plant yield. Currently, high-throughput plant phenotyping has been widely studied as a rapid and nondestructive tool for analyzing the growth status of plants, such as water and nutrient content. In this study, a combination of computer vision and deep learning was used for drought-stressed poplar sapling phenotyping. Four varieties of poplar saplings were cultivated, and 5 different irrigation treatments were applied. Color images of the plant samples were captured for analysis. Two tasks, including leaf posture calculation and drought stress identification, were conducted. First, instance segmentation was used to extract the regions of the leaf, petiole, and midvein. A dataset augmentation method was created for reducing manual annotation costs. The horizontal angles of the fitted lines of the petiole and midvein were calculated for leaf posture digitization. Second, multitask learning models were proposed for simultaneously determining the stress level and poplar variety. The mean absolute errors of the angle calculations were 10.7° and 8.2° for the petiole and midvein, respectively. Drought stress increased the horizontal angle of leaves. Moreover, using raw images as the input, the multitask MobileNet achieved the highest accuracy (99% for variety identification and 76% for stress level classification), outperforming widely used single-task deep learning models (stress level classification accuracies of <70% on the prediction dataset). The plant phenotyping methods presented in this study could be further used for drought-stress-resistant poplar plant screening and precise irrigation decision-making.
Why it matches plant phenotyping methods画像解析と深層学習により、葉姿勢の定量化および干ばつストレス同定手法を開発・評価しており、植物表現型取得が研究の中心である。
abstractIn this study, a combination of computer vision and deep learning was used for drought-stressed poplar sapling phenotyping.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe codes for conducting the proposed poplar plant image generation method and for annotation format conversion were uploaded to the GitHub platform ( https://github.com/L-Zhou17/Plant-Image-Generation ). Other codes and datasets are available upon request.Open asset ↗L-Zhou17/Plant-Image-Generationlines:269-294Code / dataset availability confirmedEurope PMC · OpenAlex · checked 7 Sept 2026
Plant phenotype detection plays a crucial role in understanding and studying plant biology, agriculture, and ecology. It involves the quantification and analysis of various physical traits and characteristics of plants, such as plant height, leaf shape, angle, number, and growth trajectory. By accurately detecting and measuring these phenotypic traits, researchers can gain insights into plant growth, development, stress tolerance, and the influence of environmental factors, which has important implications for crop breeding. Among these phenotypic characteristics, the number of leaves and growth trajectory of the plant are most accessible. Nonetheless, obtaining these phenotypes is labor intensive and financially demanding. With the rapid development of computer vision technology and artificial intelligence, using maize field images to fully analyze plant-related information can greatly eliminate repetitive labor and enhance the efficiency of plant breeding. However, it is still difficult to apply deep learning methods in field environments to determine the number and growth trajectory of leaves and stalks due to the complex backgrounds and serious occlusion problems of crops in field environments. To preliminarily explore the application of deep learning technology to the acquisition of the number of leaves and stalks and the tracking of growth trajectories in field agriculture, in this study, we developed a deep learning method called Point-Line Net, which is based on the Mask R-CNN framework, to automatically recognize maize field RGB images and determine the number and growth trajectory of leaves and stalks. The experimental results demonstrate that the object detection accuracy (mAP50) of our Point-Line Net can reach 81.5%. Moreover, to describe the position and growth of leaves and stalks, we introduced a new lightweight "keypoint" detection branch that achieved a magnitude of 33.5 using our custom distance verification index. Overall, these findings provide valuable insights for future field plant phenotype detection, particularly for datasets with dot and line annotations.
Why it matches plant phenotyping methodsトウモロコシの葉・茎の数と成長軌跡をRGB画像から抽出する深層学習手法を開発し、精度評価も行っており、植物表現型取得が研究の中心である。
abstractin this study, we developed a deep learning method called Point-Line Net, which is based on the Mask R-CNN framework, to automatically recognize maize field RGB images and determine the number and growth trajectory of leaves and stalks.
Reproduction assets foundThe authors explicitly deposit the code (and data) supporting this maize leaf/stalk trajectory phenotyping study in a public GitHub repository, matching an allowed URL.Code · publicThe computer code and data that support the findings of this study are deposited in a GitHub repository at https://github.com/VEGETALOADING/Point-Line-Net .Open asset ↗VEGETALOADING/Point-Line-Netlines:319-524Plant phenotyping relevance match · UnverifiedEurope PMC · checked 7 Sept 2026
This study addresses the challenges of low detection precision and limited generalization across various ripeness levels and varieties for large non-green-ripe citrus fruits in complex scenarios. We present a high-precision and lightweight model, YOLOC-tiny, built upon YOLOv7, which utilizes EfficientNet-B0 as the feature extraction backbone network. To augment sensing capabilities and improve detection accuracy, we embed a spatial and channel composite attention mechanism, the convolutional block attention module (CBAM), into the head's efficient aggregation network. Additionally, we introduce an adaptive and complete intersection over union regression loss function, designed by integrating the phenotypic features of large non-green-ripe citrus, to mitigate the impact of data noise and efficiently calculate detection loss. Finally, a layer-based adaptive magnitude pruning strategy is employed to further eliminate redundant connections and parameters in the model. Targeting three types of citrus widely planted in Sichuan Province-navel orange, Ehime Jelly orange, and Harumi tangerine-YOLOC-tiny achieves an impressive mean average precision (mAP) of 83.0%, surpassing most other state-of-the-art (SOTA) detectors in the same class. Compared with YOLOv7 and YOLOv8x, its mAP improved by 1.7% and 1.9%, respectively, with a parameter count of only 4.2M. In picking robot deployment applications, YOLOC-tiny attains an accuracy of 92.8% at a rate of 59 frames per second. This study provides a theoretical foundation and technical reference for upgrading and optimizing low-computing-power ground-based robots, such as those used for fruit picking and orchard inspection.
Why it matches plant phenotyping methods柑橘の熟度状態を画像から推定する軽量検出モデルを開発し、精度・速度を比較評価しており、植物状態の取得手法が中心である。
abstractWe present a high-precision and lightweight model, YOLOC-tiny, built upon YOLOv7
Chinese fir is the most important native softwood tree in China and has significant economic and ecological value. Accurate assessment of the growth status is critical for both seedling cultivation and germplasm evaluation of this commercially significant tree. Needle leaf chlorophyll content (LCC) and needle leaf water content (LWC), which are determinants of plant health and photosynthetic efficiency, are important indicators of the growth status in plants. In this study, for the first time, the LCC and LWC of Chinese fir seedlings were estimated based on hyperspectral reflectance spectra and machine learning algorithms. A line-scan hyperspectral imaging system with a spectral range of 870 to 1,720 nm was used to capture hyperspectral images of seedlings with varying LCC and LWC. The spectral data of the canopy area of the seedlings were extracted and preprocessed using the Savitzky-Golay smoothing (SG) algorithm. Subsequently, the Successive Projection Algorithm (SPA) and Competitive Adaptive Reweighted Sampling (CARS) methods were employed to extract the most informative wavelengths. Moreover, SVM, PLSR and ANNs were utilized to construct models that predict LCC and LWC based on effective wavelengths. The results indicated that the CARS-ANNs were the best for predicting LCC, with R² C = 0.932, RSME C = 0.224, and R² P = 0.969, RSME P = 0.157. Similarly, the SPA-ANNs model exhibited the best prediction performance for LWC, with R² C = 0.952, RSME C = 0.049, and R² P = 0.948, RSME P = 0.051. In conclusion, the present study highlights the significant potential of combining hyperspectral imaging (HSI) with machine learning algorithms as a rapid, non-destructive, and highly accurate method for estimating LCC and LWC in Chinese fir.
Why it matches plant phenotyping methodsハイパースペクトル画像と機械学習により、苗木の葉緑素量・含水量という植物形質を非破壊推定する手法を開発・評価しており、フェノタイピング手法が中心である。
abstractthe LCC and LWC of Chinese fir seedlings were estimated based on hyperspectral reflectance spectra and machine learning algorithms
Abstract Agriculture in India is a vital sector that contains a major portion of the population and impacts substantially the country’s economy. Cocoa is a crop that has commercial importance and is used for the production of chocolates. It is one of the main crops cultivated in south India due to the humid tropical climate. However, the cocoa plant is susceptible to various diseases caused by bacteria, viruses, and pests resulting in yield losses. Visual analysis is a subjective and time-consuming process. Further, farmers use improper pesticides to prevent diseases, and this will degrade the plant and soil quality. To overcome these problems, this paper proposes an automatic cocoa plant disease detection and pesticide recommendation system using computer vision and deep learning techniques. The proposed system was evaluated on several cocoa plant images, and an accuracy of 97.36% was obtained in disease classification. The proposed system can help cocoa farmers in the detection of cocoa plant diseases in the early stage and reduce the use of excessive pesticides, thus promoting sustainable agriculture practices.
Why it matches plant phenotyping methodsココア植物画像から病害状態を推定する画像・深層学習手法が研究の中心であり、病害分類性能も評価しているため、植物フェノタイピング手法として収録する。
abstractthis paper proposes an automatic cocoa plant disease detection and pesticide recommendation system using computer vision and deep learning techniques.
Agriculture is an important sector for the growing people of the world to fulfil the minimum requirements of food. Identifying plant infection in the agricultural sector is complex. If the detection is wrong, there is more damage to crop production and economic loss of the market. Leaf infection identification need a large number of labors, command of plant disorders and requires a lot of observing time. Therefore, this analysis explains detection of plant leaf disease by utilizing CNN and image processing. Alex Net and ResNet-50 are Convolutional Neural Network (CNN) models. First, this method is performed on Kaggle datasets of potato and tomato plants to examine the characteristics of an infected leaves. Then, feature extraction and categorization method is executed on dataset pictures to observe leaf disorders using Alex Net and ResNet-50 models by executing image processing. Observational outputs demonstrate potential of described method, in which it reaches a complete accuracy of 98% and 95% of Alex Net and ResNet50. The output shows that described model particularly predicts defective plant leaves from healthy leaf images.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定するCNN・画像処理手法が研究の中心であり、精度評価も行っているため含める。
abstractTherefore, this analysis explains detection of plant leaf disease by utilizing CNN and image processing.
Globally, tea production and its quality fundamentally depend on tea leaves, which are susceptible to invasion by pathogenic organisms. Precise and early-stage identification of plant foliage diseases is a key element in preventing and controlling the spreading of diseases that hinder yield and quality. Image processing techniques are a sophisticated tool that is rapidly gaining traction in the agricultural sector for the detection of a wide range of diseases with excellent accuracy. This study focuses on a pragmatic approach for automatically detecting selected tea foliage diseases based on convolutional neural network (CNN). A large dataset of 3330 images has been created by collecting samples from different regions of Sylhet division, the tea capital of Bangladesh. The proposed CNN model is developed based on tea leaves affected by red rust, brown blight, grey blight, and healthy leaves. Afterward, the model's prediction was validated with laboratory tests that included microbial culture media and microscopic analysis. The accuracy of this model was found to be 96.65%. Chiefly, the proposed model was developed in the context of the Bangladesh tea industry.
Why it matches plant phenotyping methods茶葉画像から病害状態を自動推定するCNN手法の開発と検証が中心であり、植物病害の表現型推定に該当する。
abstractThis study focuses on a pragmatic approach for automatically detecting selected tea foliage diseases based on convolutional neural network (CNN).
In this study, our aim is to find an effective method to solve the problem of disease similarity caused by multiple diseases occurring on the same leaf. This study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases. We conducted comparisons and analyses on the impact of various factors, such as training methods, data expansion methods, optimizer selection, image background, and other factors, on model performance. The findings suggest that utilizing offline expansion and transfer learning to fine-tune all layer parameters can enhance the model's classification performance, while complex image backgrounds significantly influence model performance. Additionally, the optimized RegNet network model demonstrates good generalization ability for both datasets, achieving testing accuracies of 93.85% and 99.23%, respectively. These results highlight the potential of the optimized RegNet network model to achieve high-precision identification of different diseases on the same apple leaf under complex field backgrounds. This will be of great significance for intelligent disease identification in apple orchards in the future.
Why it matches plant phenotyping methodsリンゴ葉の病害状態を画像から識別する最適化CNNを提案し、学習条件・背景・データセットで性能比較と精度評価を行っており、植物表現型取得法が中心である。
abstractThis study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases.
Reproduction assets foundThe paper's apple leaf disease dataset fuses authors' field-collected images (not publicly deposited) with the public Kaggle Plant Pathology 2020 (FGVC7) dataset, which is directly used in this paper's phenotyping/classification measurements. No author analysis code, trained model checkpoints, or data deposit is statedDataset · publich period from apple tree germination to harvesting, and each disease image sample contained different stages of onset.
Considering the insufficient number of collected apple leaf disease images and the fact that the background and category of the apple disease leaf images in the “Plant Pathology Challenge” for CVPR 2020-FGVC7 ( https://www.kaggle.com/c/plantpathology-2020 fgvc7, accessed on 20 December 2023) [ 17 ] are consistent with the collected image data, the two were fused to form the dataset used in this study. Additionally, we collaborated with professional scholars to screen, classify, and organize the above two image types one by one, establishing a relatively reliable dataset of aOpen asset ↗Kaggle · plantpathology-2020lines:34-43Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Jun 2024Computers and Electronics in Agriculture.
Maize diseases caused by fungal pathogens are the primary factor resulting in reduced maize yield. However, in practical complex background scenarios, diseases caused by spores, such as gray leaf spot and rust, usually exhibit characteristics including diverse propagation routes, similar lesion appearances at the initial stage of infection, and varying lesion sizes, which raise a challenging task to recognize similar diseases. Focusing on the accurate recognition of maize leaf diseases in complex backgrounds, this paper proposes a texture-color dual-branch multiscale residual shrinkage network (TC-MRSN) model based on deep learning. To preserve the characteristic information of small-sized lesions during the sampling process, texture feature extraction block and texture-color dual-branch block are designed to extract texture features from lesions and fuse them with RGB features. To reduce the interference of redundant background noise in the fusion feature, the multi-scale residual shrinkage module is presented to extract different receptive field features and process redundant noise through soft threshold. The proposed model is also deployed on mobile phones to enable real-time data collection and analysis. Detailed experimental and practical testing results show that TC-MRSN can achieve an average accuracy rate of 94.88% and 99.59% on complex background dataset and PlantVillage dataset, respectively, which is higher than those of the existing models ResNet50, VGG-ICNN, HCA-MFFNet by 5.2%, 2.5% and 1.8%, respectively.
Why it matches plant phenotyping methodsトウモロコシ葉の病斑・病害状態を画像から認識する深層学習手法を開発・評価しており、植物病害フェノタイピングが中心的です。
abstractthis paper proposes a texture-color dual-branch multiscale residual shrinkage network (TC-MRSN) model based on deep learning.
Predicting accurately the Normalized Difference Vegetation Index (NDVI) trends from RGB images are essential to monitor crops and identify issues related to plant diseases, and water shortages. The current NDVI prediction models are primarily based on traditional machine learning models which lack reliability due to the problem related to atmospheric conditions. To predict NDVI in Prince Edward Island using RGB drone imagery data, this paper proposed a novel framework integrating empirical curvelet transform and DenseNet models. Each channel of RGB drone imagery data was passed through empirical curvelet transform method where the curvelet coefficients were analysed which result in creating a new formula to design NDVI. The output of the new formula was sent to the deep DenseNet to predict the final NDVI. The proposed model was evaluated using quantitative metrics including, Q-Q plot, regression, correlation coefficients, structural similarity (SSIM), peak signal to noise ratio (PSNR) and mean square error (MSE) as well as accuracy (ACC), sensitivity (SEN), f1-score, specificity. The obtained results showed that the proposed model outperformed the previous models by scoring the highest values of SSIM = 0.98, and lowest MSE = 120. It is believed that the proposed model is helpful to support farmers in monitoring the growth and plant health as well as to identify crops problems.
Why it matches plant phenotyping methodsRGBドローン画像からNDVIという植物状態・健康指標を推定する画像解析手法を開発し、複数指標で評価しており、フェノタイピング手法が中心です。
abstractthis paper proposed a novel framework integrating empirical curvelet transform and DenseNet models
Agriculture and modern farming is one of the fields where IoT and automation can have a great impact. Maintaining healthy plants and monitoring their environment in order to identify or detect diseases is essential in order to maintain a maximum crop yield. The implementation of current high rocketing technologies including artificial intelligence (AI), machine learning, and deep learning has proved to be extremely important in modern agriculture as a method of advanced image analysis domain. Artificial intelligence adds time efficiency and the possibility of identifying plant diseases, in addition to monitoring and controlling the environmental conditions in farms. Several studies showed that machine learning and deep learning technologies can detect plant diseases upon analyzing plant leaves with great accuracy and sensitivity. In this study, considering the worth of machine learning for disease detection, we present a convolutional neural network VGG-16 model to detect plant diseases, to allow farmers to make timely actions with respect to treatment without further delay. To carry this out, 19 different classes of plants diseases were chosen, where 15,915 plant leaf images (both diseased and healthy leaves) were acquired from the Plant Village dataset for training and testing. Based on the experimental results, the proposed model is able to achieve an accuracy of about 95.2% with the testing loss being only 0.4418. The proposed model provides a clear direction toward a deep learning-based plant disease detection to apply on a large scale in future. Keywords—Machine learning; VGG-16; disease detection; convolutional networks; Plant Village; modern farming. Keywords—Machine learning; VGG-16; disease detection; convolutional networks; Plant Village; modern farming.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定するVGG-16モデルの開発・評価が研究の中心であり、植物病害表現型の画像ベース推定に該当する。
abstractwe present a convolutional neural network VGG-16 model to detect plant diseases
The Plant Leaf Diseases Detection System addresses the critical challenge of early detection and management of plant diseases, significantly impacting agricultural productivity and food security. Utilizing advanced technologies, this cutting-edge agricultural solution employs a Convolutional Neural Network (CNN) model, specifically based on the VGG19 architecture implemented using Keras. This robust deep learning model is trained on a diverse dataset containing images of both healthy and diseased leaves, allowing it to extract intricate features and accurately classify various plant diseases automatically. The system seamlessly integrates HTML, CSS, and Flask for the front end, while Keras powers the back end, resulting in a user-friendly web application interface. Incorporating this technology not only enhances the efficiency of disease detection but also facilitates user interaction and accessibility
Why it matches plant phenotyping methods植物葉の画像から病害状態をCNNで自動分類する手法・システムが研究の中心であり、植物の病徴状態を直接推定するため、植物フェノタイピング手法として含める。
titlePlant Leaf Disease Detection using Deep Learning Algorithms
The diseases that affect the plants cannot be easily avoided due to rapid and substantial changes in the environment and climate. Generally, paddy crops are affected by several conditions including pests and nutritional deficiencies. Hence, it is important to detect these disease-affected paddy crops at an early stage for better productivity. To detect and classify the problems in this specific domain, deep learning approaches are utilized. In this paper, a novel attention convolutional stacked recurrent based binary Kepler search (ACSR-BKS) algorithm is used to detect diseases, nutritional deficiencies, and pest patterns at an early stage via diverse significant pipelines namely the data augmentation, data pre-processing, and classification phase thereby providing pest patterns and identifying nutritional deficiencies. Subsequent to data collection processes, the images are augmented via zooming, rotating, flipping horizontally, shifting of height, width, and rescaling. To acquire the accurate and best results in terms of classification, the parameters need to be tuned and adjusted using the binary Kepler search algorithm. The results revealed that the accuracy of the proposed ACSR-BKS algorithm is 98.2% in terms of detecting the diseases. Then, the obtained results are compared with the other existing approaches. Additionally, it is revealed that the yield of paddy can also be improved by utilizing the proposed disease-detecting methods.
Why it matches plant phenotyping methodsイネ画像から病害・栄養欠乏・害虫パターンを検出・分類する深層学習手法が研究の中心であり、植物の健康状態を直接推定するため採用。
abstracta novel attention convolutional stacked recurrent based binary Kepler search (ACSR-BKS) algorithm is used to detect diseases, nutritional deficiencies, and pest patterns at an early stage
Background: Legumes, such as lentils, field peas, Faba beans and chickpeas, are high in vitamins, fiber, important minerals and protein and can help avoid obesity and cardiovascular illnesses. They also contribute to ecosystem services, such as nitrogen fixation and resilience to environmental stresses. Despite a 60% increase in global pulse production from 2000 to 2021, a demand-supply gap, especially in South Asia, raises concerns about nutritional access. Since illnesses are currently an issue to the food security of faba beans, machine learning is required for efficient disease identification. Methods: This research employs Convolutional Neural Networks (CNNs) for robust Faba bean leaf disease identification. The CNN model is trained with diverse images representing specific diseases. The study focuses on diseases like Chocolate Spot, Faba Bean Gall, Rust and Healthy leaves. Image processing involves resizing, grayscale conversion and labeling. The CNN architecture includes eight convolutional layers, four max-pooling layers and three dropout layers. The model is trained using 80% of the dataset, validated using 20% and tested for accuracy. Result: The CNN model achieves an accuracy of 99.37% during training and 89.69% during validation after 75 epochs. Confusion matrix and classification report illustrate the model’s performance. It shows high precision, recall and F1 scores for each class, indicating balanced performance. Chocolate Spot and Rust exhibit the highest precision and F1 scores. The overall accuracy is 91%, comparable to other studies on Faba bean disease detection. The study presents a CNN-based disease identification system for Faba beans, demonstrating high accuracy and balanced performance across different diseases. The model’s effectiveness is comparable to other advanced techniques. The research highlights the potential of machine learning in optimizing disease management for Faba beans. Future work could explore a broader range of diseases and incorporate hybrid machine learning algorithms for further improvement.
Why it matches plant phenotyping methods葉画像から病害状態をCNNで推定し、学習・検証・テスト性能を評価する手法が研究の中心であるため、植物病害フェノタイピング手法として含める。
abstractThis research employs Convolutional Neural Networks (CNNs) for robust Faba bean leaf disease identification.
Plant height (PH) is an essential agronomic trait that can be used to assist in crop breeding pipelines, assess crop productivity and make crop management decisions. Improving the accuracy of the digital terrain model (DTM) and optimising the PH features of the crop surface model obtained from unmanned aerial vehicle (UAV) images contribute to PH estimation. The influence of the fractional vegetation cover (FVC) on DTM reconstruction accuracy was investigated for the first time, and the influence of the view angle (oblique and nadir) and spatial resolution on the accuracy of maize PH estimation was explored. The results show that the accuracy of the DTM constructed using the inverse distance weighted algorithm was significantly influenced by the FVC conditions. Compared with the DTM constructed using UAV images over bare soil, FVC less than 0.4 was necessary for the accurate construction of the DTM, with average estimation errors of 0.15 m in 2018 and 0.09 m in 2019. Compared with the nadir view, the oblique view resulted in a more accurate 3D reconstruction. When the original spatial resolution of 15 mm was upscaled to 20, 30, 60 and 120 mm, a decreasing trend of PH estimation accuracy was observed, with root mean square error increasing from 0.35 to 0.40 m and mean absolute error increasing from 0.30 to 0.36 m. Overall, this study investigated the optimal FVC conditions for accurate DTM construction and the influence of the view angle and spatial resolution on PH estimation based on UAV RGB images.
Why it matches plant phenotyping methodsUAV RGB画像から作物表面モデルを構築し、FVC・視角・空間解像度がトウモロコシ草高推定に及ぼす影響と精度を検証しており、表現型取得手法が研究の中心である。
abstractImproving the accuracy of the digital terrain model (DTM) and optimising the PH features of the crop surface model obtained from unmanned aerial vehicle (UAV) images contribute to PH estimation.
In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development.
Why it matches plant phenotyping methods茶葉葉面病斑という植物の病害状態を画像から検出・推定する改良YOLOv8手法を開発し、比較実験で技術性能を評価しており、表現型取得が中心である。
abstractan improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms.
Monitoring plants' responses to water deficit using remote sensing still faces large uncertainty, mostly due to the inaccurate characterization of plants' physiological responses. Solar induced chlorophyll fluorescence (SIF) contains information on plants' physiological processes which regulates the energy partitioning after solar radiation is absorbed by chlorophyll, providing new opportunities to monitor plant response to drought stress. However, the drought-induced physiological, biochemical, and structural changes are strongly coupled, hindering the mechanistic understanding of drought impacts on plants. Here, using tower-based observations of SIF together with high spectral resolution reflectance measurements, we derived the time series of the fraction of absorbed photosynthetically active radiation by canopy, chlorophyll content, and fluorescence efficiency using two radiative transfer model-based decomposition methods, and evaluated their responses to two consecutive dry spells at a tall-grass prairie site in the USA (34°59′05.0″ N, 97°31′20.6″ W). We observed a robust signal of afternoon depression based on the fluorescence efficiency estimates during the second dry spell, which had much lower soil moisture than the first one. The strong decline in fluorescence efficiency in the afternoon was likely caused by the high temperature and atmospheric dryness when the soil was dry. Such a direct physiological response contributed to 14.4% to 36.0% of seasonal variation of afternoon SIF, depending on the decomposition method used. Sustained water stress also caused lagged responses. Despite the subsequent rainfall after the dry spell, we observed a continued decline of SIF due to the lagged decline of chlorophyll content and green canopy coverage. Our study demonstrates the use of continuous SIF measurements to understand the development of drought effects on plants, and highlights the importance of afternoon SIF measurements for physiological stress detection.
Why it matches plant phenotyping methods連続SIF・高分解能反射測定と放射伝達モデル分解により、植物の生理状態や乾燥ストレス関連形質を抽出する手法の実質的応用であり、単なる生物学的測定ではない。
abstractusing tower-based observations of SIF together with high spectral resolution reflectance measurements, we derived the time series of the fraction of absorbed photosynthetically active radiation by canopy, chlorophyll content, and fluorescence efficiency using two radiative transfer model-based decomposition methods
As the global population and resource scarcity simultaneously increase, the pressure on plant breeders and growers to maximise the effectiveness of their operations is immense. In this article, we explore the usefulness of image-based data collection and analysis of field experiments consisting of multiple field sites, plant varieties, and treatments. The goal of this approach is to determine whether the noninvasive acquisition and analysis of image data can be used to find relationships between the canopy traits of field experiments and environmental factors. Our results are based on data from three field trials in 2016, 2017, and 2018 in South Australia. Image data were supplemented by environmental data such as rainfall, temperature, and soil composition in order to explain differences in growth and the development of plants across field trials. We have shown that the combination of high-throughput image-based data and independently recorded environmental data can reveal valuable connections between the variables influencing wheat crop growth; meanwhile, further studies involving more field trials under different conditions are required to test hypotheses and draw statistically significant conclusions. This work highlights some of the more responsive traits and their dependencies.
Why it matches plant phenotyping methods圃場試験での非侵襲的な画像取得・解析を中心に、コムギのキャノピー形質を環境要因と関連付けて評価しており、画像ベース表現型計測の実質的な適用研究である。
abstractwe explore the usefulness of image-based data collection and analysis of field experiments
Agriculture is important for ecology. The early detection and treatment of agricultural crop diseases are meaningful and challenging tasks in agriculture. Currently, the identification of plant diseases relies on manual detection, which has the disadvantages of long operation time and low efficiency, ultimately impacting the crop yield and quality. To overcome these disadvantages, we propose a new object detection method named “Plant Leaf Detection transformer with Improved deNoising anchOr boxes (PL-DINO)”. This method incorporates a Convolutional Block Attention Module (CBAM) into the ResNet50 backbone network. With the assistance of the CBAM block, the representative features can be effectively extracted from leaf images. Next, an EQualization Loss (EQL) is employed to address the problem of class imbalance in the relevant datasets. The proposed PL-DINO is evaluated using the publicly available PlantDoc dataset. Experimental results demonstrate the superiority of PL-DINO over the related advanced approaches. Specifically, PL-DINO achieves a mean average precision of 70.3%, surpassing conventional object detection algorithms such as Faster R-CNN and YOLOv7 for leaf disease detection in natural environments. In brief, PL-DINO offers a practical technology for smart agriculture and ecological monitoring.
Why it matches plant phenotyping methods植物葉画像から病害状態を検出する画像解析手法を開発・評価しており、植物の病害表現型推定が中心です。
abstractwe propose a new object detection method named “Plant Leaf Detection transformer with Improved deNoising anchOr boxes (PL-DINO)”
Agriculture is the major occupation of people in India. Around 70% of actual population depends on agriculture. Potato is one of the major cash crops in agriculture industry and is used on a huge scale to produce clothes. Every year, many plants suffer damage due to diseases and infections, leading to the wastage of valuable resources. This research proposes a plant disease prediction system built on a deep learning and machine learning methodology in an effort to lessen this loss. This system will predict whether the plant or leaf is healthy or diseased and if the leaf or plant is diseased then it will suggest proper precautions and measures to prevent and cure the disease. By this the agricultural industry will get benefited and our country will move towards digital agricultural era. The method proposed in this paper makes use of deep learning’s power for feature extraction and machine learning classifiers for classification purposes. Convolutional neural networks are used to detect features, with a validation accuracy of 98.97%. These features are then fed to classifiers such as K-NN, SVM, Random Forest, MLP, and Naive Bayes. With an accuracy of 99.07%, the K-Nearest Neighbors classifier demonstrated remarkable performance. Even with its minor decrease, the Random Forest classifier managed to achieve an impressive accuracy of 98.30%. The SVM and MLP classifiers also demonstrated their capacity to accurately classify plant leaf diseases, with outstanding accuracy rates of 97.89% and 98.47%, respectively. The Naive Bayes classifier also proved to be effective, scoring an impressive 97.10% accuracy.
Why it matches plant phenotyping methods植物葉の画像から健全・罹病状態を推定する深層学習／機械学習手法が研究の中心であり、植物病害表現型の取得・分類に該当する。
abstractThis research proposes a plant disease prediction system built on a deep learning and machine learning methodology
The rice spike, a crucial part of rice plants, plays a vital role in yield estimation, pest detection, and growth stage management in rice cultivation. When using drones to capture photos of rice fields, the high shooting angle and wide coverage area can cause rice spikes to appear small in the captured images and can cause angular distortion of objects at the edges of images, resulting in significant occlusions and dense arrangements of rice spikes. These factors are unique challenges during drone image acquisition that may affect the accuracy of rice spike detection. This study proposes a rice spike detection method that combines deep learning algorithms with drone perspectives. Initially, based on an enhanced version of YOLOv5, the EMA (efficient multiscale attention) attention mechanism is introduced, a novel neck network structure is designed, and SIoU (SCYLLA intersection over union) is integrated. Experimental results demonstrate that RICE-YOLO achieves a mAP@0.5 of 94.8% and a recall of 87.6% on the rice spike dataset. During different growth stages, it attains an AP@0.5 of 96.1% and a recall rate of 93.1% during the heading stage, and a AP@0.5 of 86.2% with a recall rate of 82.6% during the filling stage. Overall, the results indicate that the proposed method enables real-time, efficient, and accurate detection and counting of rice spikes in field environments, offering a theoretical foundation and technical support for real-time and efficient spike detection in the management of rice growth processes.
Why it matches plant phenotyping methodsイネ穂の検出・計数という植物器官形質の画像ベース推定手法を、ドローン画像と改良YOLOv5により開発・評価しており、手法が研究の中心である。
abstractThis study proposes a rice spike detection method that combines deep learning algorithms with drone perspectives.
Multi-spectral imaging (MSI) collection by unoccupied aerial vehicles (UAV) is an important tool to measure growth of forage crops. Information from estimated growth curves can be used to infer harvest biomass and to gain insights in the relationship of growth dynamics and harvest biomass stability across cuttings and years. In this study, we used MSI to evaluate Alfalfa ( Medicago sativa L. subsp. sativa ) to understand the longitudinal relationship between vegetative indices (VIs) and forage/biomass, as well as evaluation of irrigation treatments and genotype by environment interactions (GEI) of different alfalfa cultivars. Alfalfa is a widely cultivated perennial forage crop grown for high yield, nutritious forage quality for feed rations, tolerance to abiotic stress, and nitrogen fixation properties in crop rotations. The direct relationship between biomass and VIs such as Normalized difference vegetation index (NDVI), green normalized difference vegetation index (GNDVI), red edge normalized difference vegetation index (NDRE), and Near infrared (NIR) provide a non-destructive and high throughput approach to measure biomass accumulation over subsequent alfalfa harvests. In this study, we aimed to estimate the genetic parameters of alfalfa VIs and utilize longitudinal modeling of VIs over growing seasons to identify potential relationships between stability in growth parameters and cultivar stability for alfalfa biomass yield across cuttings and years. We found VIs of GNDVI, NDRE, NDVI, NIR and simple ratios to be moderately heritable with median values for the field trial in Ithaca, NY to be 0.64, 0.56, 0.45, 0.45 and 0.40 respectively, Normal Irrigation (NI) trial in Leyendecker, NM to be 0.3967, 0.3813, 0.3751, 0.3239 and 0.3019 respectively, and Summer Irrigation Termination (SIT) trial in Leyendecker, NM to be of 0.11225, 0.1389, 0.1375, 0.2539 and 0.1343, respectively. Genetic correlations between NDVI and harvest biomass ranged from 0.52 - .99 in 2020 and 0.08 - .99 in 2021 in the NY trial. Genetic correlations for NI trial in NM for NDVI ranged from 0.72 - .98 in 2021 and SIT ranged from 0.34-1.0 in 2021. Genotype by genotype by interaction (GGE) biplots were used to differentiate between stable and unstable cultivars for locations NY and NM, and Random regression modeling approaches were used to estimate growth parameters for each cutting. Results showed high correspondence between stability in growth parameters and stability, or persistency, in harvest biomass across cuttings and years. In NM, the SIT trial showed more variation in growth curves due to stress conditions. The temporal growth curves derived from NDVI, NIR and Simple ratio were found to be the best phenotypic indices on studying the stability of growth parameters across different harvests. The strong correlation between VIs and biomass present opportunities for more efficient screening of cultivars, and the correlation between estimated growth parameters and harvest biomass suggest longitudinal modeling of VIs can provide insights into temporal factors influencing cultivar stability.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から植生指数とバイオマスを推定し、成長曲線・遺伝パラメータ・品種安定性を評価することが研究の中心であり、植物表現型取得と解析手法の実質的な応用に該当する。
abstractMulti-spectral imaging (MSI) collection by unoccupied aerial vehicles (UAV) is an important tool to measure growth of forage crops.
PeaGrowth chamberRootMorphology / geometry measurementRoot system architecture
Abstract Root system architecture (RSA) plays a central role in water and nutrient acquisition in plants. Plasticity and genetic variation in RSA can be used as an adaptive strategy to optimize plant performance under variable environments. We quantified phenotypic variation for seedling RSA among 44 diverse pea ( Pisum sativum L.) genotypes, including breeding lines and germplasm accessions, grown under controlled conditions for 14 days using two‐dimensional hydroponic root imaging. Root image analysis revealed significant genotypic variability among the lines for all root traits, namely root length (RL), root diameter (RD), root volume, root surface area, number of tips, network width (NW), network depth (ND), and network convex area. Significant positive correlations were observed among the evaluated root traits, ranging from 0.5 to 0.9. Pea lines were ranked based on estimated means for root traits, with lines E20, F1, and F8 showing high rankings, while E4 and F5 received low rankings for most traits. To associate root traits with nitrogen (N) fixation and field agronomic performance, we performed redundancy analysis (RDA). The quantified root traits accounted for significant variation in the agronomic traits ( R 2 = ∼30%, p
Why it matches plant phenotyping methods二次元根画像解析を用いた幼植物の根系形態形質の定量が研究の中心であり、遺伝子型間比較と農業形質との関連解析に用いられているため、画像ベースの表現型解析の実質的応用と判断します。
abstractRoot image analysis revealed significant genotypic variability among the lines for all root traits
When detecting tomato leaf diseases in natural environments, factors such as changes in lighting, occlusion, and the small size of leaf lesions pose challenges to detection accuracy. Therefore, this study proposes a tomato leaf disease detection method based on attention mechanisms and multi-scale feature fusion. Firstly, the Convolutional Block Attention Module (CBAM) is introduced into the backbone feature extraction network to enhance the ability to extract lesion features and suppress the effects of environmental interference. Secondly, shallow feature maps are introduced into the re-parameterized generalized feature pyramid network (RepGFPN), constructing a new multi-scale re-parameterized generalized feature fusion module (BiRepGFPN) to enhance feature fusion expression and improve the localization ability for small lesion features. Finally, the BiRepGFPN replaces the Path Aggregation Feature Pyramid Network (PAFPN) in the YOLOv6 model to achieve effective fusion of deep semantic and shallow spatial information. Experimental results indicate that, when evaluated on the publicly available PlantDoc dataset, the model's mean average precision (mAP) showed improvements of 7.7%, 11.8%, 3.4%, 5.7%, 4.3%, and 2.6% compared to YOLOX, YOLOv5, YOLOv6, YOLOv6-s, YOLOv7, and YOLOv8, respectively. When evaluated on the tomato leaf disease dataset, the model demonstrated a precision of 92.9%, a recall rate of 95.2%, an F1 score of 94.0%, and a mean average precision (mAP) of 93.8%, showing improvements of 2.3%, 4.0%, 3.1%, and 2.7% respectively compared to the baseline model. These results indicate that the proposed detection method possesses significant detection performance and generalization capabilities.
Why it matches plant phenotyping methodsトマト葉の病変を画像から検出・局在化する新規深層学習手法を開発し、複数データセットと既存モデルで性能評価しており、植物病害状態の表現型取得が中心である。
abstractthis study proposes a tomato leaf disease detection method based on attention mechanisms and multi-scale feature fusion.
Reproduction assets foundThe paper's tomato leaf disease dataset is assembled from three publicly available Roboflow Universe datasets explicitly cited by the authors (Bryan 2023, SREC 2023, projectdesign 2023), which are the image/annotation inputs used for the study's detection experiments. No author analysis code, trained model checkpoints,Dataset · publicBryan . ( 2023 ). Tomato leaf disease dataset [Open source dataset] . Roboflow Universe . Available at: https://universe.roboflow.com/bryan-b56jm/tomato-leaf-disease-ssoha .Open asset ↗Roboflow Universe · tomato-leaf-disease-ssohalines:563-606Dataset · publicSREC . ( 2023 ). Early- dataset [Open source dataset] . Roboflow Universe . Available at: https://universe.roboflow.com/srec/early .Open asset ↗Roboflow Universe · earlylines:695-785Dataset · publicprojectdesign . ( 2023 ). Tomato biotic stress classification dataset [Open source dataset] . Roboflow Universe . Available at: https://universe.roboflow.com/projectdesign-rw5fo/tomato-biotic-stress-classification .Open asset ↗Roboflow Universe · tomato-biotic-stress-classificationlines:607-694Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 7 Sept 2026
Abstract The two-spotted spider mite (TSSM), Tetranychus urticae, is among the most destructive piercing-sucking herbivores, infesting more than 1100 plant species, including numerous greenhouse and open-field crops of significant economic importance. Its prolific fecundity and short life cycle contribute to the development of resistance to pesticides. However, effective resistance loci in plants are still unknown. To advance research on plant-mite interactions and identify genes contributing to plant immunity against TSSM, efficient methods are required to screen large, genetically diverse populations. In this study, we propose an analytical pipeline utilizing high-resolution imaging of infested leaves and an artificial intelligence-based computer program, MITESPOTTER, for the precise analysis of plant susceptibility. Our system accurately identifies and quantifies eggs, feces and damaged areas on leaves without expert intervention. Evaluation of 14 TSSM-infested Arabidopsis thaliana ecotypes originating from diverse global locations revealed significant variations in symptom quantity and distribution across leaf surfaces. This analytical pipeline can be adapted to various pest and host species, facilitating diverse experiments with large specimen numbers, including screening mutagenized plant populations or phenotyping polymorphic plant populations for genetic association studies. We anticipate that such methods will expedite the identification of loci crucial for breeding TSSM-resistant plants.
Why it matches plant phenotyping methods高解像度画像とMITESPOTTERによるAI解析パイプラインを開発し、葉の損傷や症状を定量化して植物のダニ抵抗性を評価することが中心である。
abstractwe propose an analytical pipeline utilizing high-resolution imaging of infested leaves and an artificial intelligence-based computer program, MITESPOTTER, for the precise analysis of plant susceptibility.
Deep learning is a concept of artificial neural networks and a subset of machine learning. It deals with algorithms that train and process datasets to make inferences for future samples, imitating the human process of learning from experiences. In this study, the YOLOv5 and YOLOv6 object detection models were compared on a plant dataset in terms of accuracy and time metrics. Each model was trained to obtain specific results in terms of mean Average Precision (mAP) and training time. There was no considerable difference in mAP between both models, as their results were close. YOLOv5, having 63.5% mAP, slightly outperformed YOLOv6, while YOLOv6, having 49.6% mAP50-95, was better in detection than YOLOv5. Furthermore, YOLOv5 trained data in a shorter time than YOLOv6, since it has fewer parameters.
Why it matches plant phenotyping methods植物葉の病害を画像から検出するYOLOモデルを比較し、精度と処理時間を評価しているため、植物病徴の画像ベース表現型推定手法の技術検証が中心です。
abstractthe YOLOv5 and YOLOv6 object detection models were compared on a plant dataset in terms of accuracy and time metrics
In recent years, precision agriculture, driven by scientific monitoring, precise management, and efficient use of agricultural resources, has become the direction for future agricultural development. The precise identification and assessment of phenotypes, which serve as external representations of a crop's growth, development, and genetic characteristics, are crucial for the realization of precision agriculture. Applications surrounding phenotypic indices also provide significant technical support for optimizing crop cultivation management and advancing smart agriculture, contributing to the efficient and high-quality development of precision agriculture.This paper focuses on lettuce and employs common nutritional stress conditions during growth as experimental settings. By collecting RGB images throughout the lettuce's complete growth cycle, we developed a deep learning-based computational model to tackle key issues in the lettuce's growth and precisely identify and assess phenotypic indices. We discovered that some phenotypic indices, including custom ones defined in this study, are representative of the lettuce's growth status. By dynamically monitoring the changes in phenotypic traits during growth, we quantitatively analyzed the accumulation and evolution of phenotypic indices across different growth stages. On this basis, a predictive model for lettuce growth and development was trained.The model incorporates MSE, SSIM, and perceptual loss, significantly enhancing the predictive accuracy of the lettuce growth images and phenotypic indices. The model trained with the reconstructed loss function outperforms the original model, with the SSIM and PSNR improving by 1.33% and 10.32%, respectively. The model also demonstrates high accuracy in predicting lettuce phenotypic indices, with an average error less than 0.55% for geometric indices and less than 1.7% for color and texture indices. Ultimately, it achieves intelligent monitoring and management throughout the lettuce's life cycle, providing technical support for high-quality and efficient lettuce production.
Why it matches plant phenotyping methodsレタスのRGB画像から表現型指標を抽出・評価し、深層学習による指標推定と成長予測モデルを開発・検証しており、植物フェノタイピング手法が研究の中心である。
abstractBy collecting RGB images throughout the lettuce's complete growth cycle, we developed a deep learning-based computational model to tackle key issues in the lettuce's growth and precisely identify and assess phenotypic indices.
Rapid and accurate assessment of apple-tree leaf nitrogen content (LNC) plays an important role in smart orchards for accurate fertilization. Hyperspectral remote sensing technology provides a reliable, economical, and fast method to estimate LNC. However, high-dimensional spectral data contain redundant information that is irrelevant to the target parameters, necessitating the development of robust hyperspectral analysis techniques to estimate apple-tree LNC. Additionally, the role of phenological information in improving LNC estimates across multiple growth stages remains uncertain. The present study thus proposes a novel hyperspectral data-processing framework (Boruta-Iteration-DNN) to optimize estimates of apple-tree LNC and investigates the potential of phenological information to improve LNC estimates of multi-fertility apple trees. The proposed framework incorporates the Boruta feature-selection method for identifying important spectral bands and assessing how they affect model performance through iterative feature analysis. A deep neural network (DNN) regression model is then developed for LNC estimation. In addition, a widely used Pearson-DNN method is used for comparison to demonstrate the superiority of the proposed approach. Furthermore, the potential of incorporating phenological information (Day After Anthesis, DAA) into the estimation models is examined to evaluate its ability to better estimate LNC. The results demonstrate that the proposed framework not only enhances the accuracy of apple-tree LNC estimates with respect to the full-spectrum model (without DAA: validation R² improved from 0.69 to 0.75, NRMSE reduced from 11.92 % to 9.97 %; with DAA: validation R² improved from 0.72 to 0.79, NRMSE reduced from 11.09 % to 9.06 %), but also reduces the complexity and dimensionality of the models by eliminating 96 % of the redundant spectral bands (2015 bands). Moreover, the inferior results of the Pearson-Iteration-DNN framework further underscore the effectiveness of the Boruta method in selecting relevant spectral bands. Additionally, including the DAA phenological information enhances the accuracy of all models (the total R² of training and validation increased by 0.05 ∼ 0.12, and the total NRMSE reduced by 1.49 % ∼ 1.93 %). These findings highlight the ability of DNN models integrated with hyperspectral data and phenological information to accurately assess LNC in apple trees, thereby offering valuable guidance to orchard management for developing precise fertilization strategies.
Why it matches plant phenotyping methodsリンゴ葉窒素含量という植物形質を対象に、ハイパースペクトル情報の特徴選択とDNN推定を統合した新規測定・推定フレームワークを開発し、比較検証しているため。
abstractThe present study thus proposes a novel hyperspectral data-processing framework (Boruta-Iteration-DNN) to optimize estimates of apple-tree LNC
Timely and rapid monitoring of apple trees nutrition status is vital for accurate management of nutrient fertilizers in order to improve the yield and quality, as well as to reduce the risk of environmental degradation. As a most frequently used method, tissue analysis used to assess the nutritional status of apple tree leaves is laborious, costly, time-consuming, environmentally unfriendly, and destructive. Ground-based sensors are able to efficiently provide information on nutritional status using leaf spectra reflectance. This research aims to establish a novel cost-effective and non-destructive approach for rapidly estimating the status of nitrogen (N), phosphorus (P), and potassium (K) in apple tree leaves based on Visible/Near-infrared (Vis/NIR) spectroscopy (500–1000 nm) coupled with machine learning. The Vis/NIR spectra of apple trees’ leaves were acquired. Then, leaf chemical contents of NPK elements were considered as reference points. Different pre-processing techniques were used to pre-treat the spectra. Four different chemometrics analysis consist of support vector machine (SVM), Artificial neural network (ANN), Random Forest (RF) and partial least square (PLS) were applied to predict NPK contents in comparison to actual values. In order to simplify the models, the sensitive wavelengths were extracted using three wavelength selection approaches, variable importance in projection (VIP), partial least squares (PLS), and random frog (Rfrog). The extracted feature wavelengths from PLS, VIP, and Rfrog methods were widely distributed in the visible and near-infrared regions of the spectrum. The performance of the developed models was tested using Residual Prediction Deviation (RPD) and the Ratio of Performance to Interquartile Distance (RPIQ). The results demonstrated that among all models, the non-linear modeling methods were superior to the linear model. The best results for estimation of Nitrogen (N), Phosphorus (P), and Potassium (K) elements were achieved by the models of MSC + D₂-Rfrog-RF (rₚ = 0.985, RMSEP = 0.029%, RPD = 8.77, RPIQ = 7.72), SNV + D₂-Rfrog-RF (rₚ = 0.977, RMSEP = 0.0053%, RPD = 6.42, RPIQ = 5.09) and SNV + D₂-Rfrog-RF (rₚ = 0.978, RMSEP = 0.018%, RPD = 8.16, RPIQ = 7.01), respectively. The findings of the current approach may provide an efficient approach to predict in-situ NPK contents of apple trees based on leaf spectral reflectance.
Why it matches plant phenotyping methodsVis/NIRセンサーと波長選択・機械学習を組み合わせ、リンゴ葉のN・P・K含量を非破壊推定する方法の開発・性能評価が研究の中心である。
abstractThis research aims to establish a novel cost-effective and non-destructive approach for rapidly estimating the status of nitrogen (N), phosphorus (P), and potassium (K) in apple tree leaves based on Visible/Near-infrared (Vis/NIR) spectroscopy (500–1000 nm) coupled with machine learning.
Tobacco is a valuable crop, but its disease identification is rarely involved in existing works. In this work, we use few-shot learning (FSL) to identify abnormalities in tobacco. FSL is a solution for the data deficiency that has been an obstacle to using deep learning. However, weak feature representation caused by limited data is still a challenging issue in FSL. The weak feature representation leads to weak generalization and troubles in cross-domain. In this work, we propose a feature representation enhancement network (FREN) that enhances the feature representation through instance embedding and task adaptation. For instance embedding, global max pooling, and global average pooling are used together for adding more features, and Gaussian-like calibration is used for normalizing the feature distribution. For task adaptation, self-attention is adopted for task contextualization. Given the absence of publicly available data on tobacco, we created a tobacco leaf abnormality dataset (TLA), which includes 16 categories, two settings, and 1,430 images in total. In experiments, we use PlantVillage, which is the benchmark dataset for plant disease identification, to validate the superiority of FREN first. Subsequently, we use the proposed method and TLA to analyze and discuss the abnormality identification of tobacco. For the multi-symptom diseases that always have low accuracy, we propose a solution by dividing the samples into subcategories created by symptom. For the 10 categories of tomato in PlantVillage, the accuracy achieves 66.04% in 5-way, 1-shot tasks. For the two settings of the tobacco leaf abnormality dataset, the accuracies were achieved at 45.5% and 56.5%. By using the multisymptom solution, the best accuracy can be lifted to 60.7% in 16-way, 1-shot tasks and achieved at 81.8% in 16-way, 10-shot tasks. The results show that our method improves the performance greatly by enhancing feature representation, especially for tasks that contain categories with high similarity. The desensitization of data when crossing domains also validates that the FREN has a strong generalization ability.
Why it matches plant phenotyping methods植物葉の異常・病徴を画像から識別する few-shot 学習法を開発し、専用データセットを作成・検証しており、植物状態の取得・推定手法が中心である。
abstractIn this work, we use few-shot learning (FSL) to identify abnormalities in tobacco.
Reproduction assets foundThe authors created the tobacco leaf abnormality dataset (TLA) used in this paper and state it is publicly available via a Google Drive link in the data availability statement.Dataset · publicion of diseases is an important research direction. For multidisease identification, the classification method is not an optimal choice. Semantic segmentation is a good solution and worthy of study.
Data availability statement
The original contributions presented in the study are publicly available. This data can be found here: https://drive.google.com/drive/folders/1Qn5UjATDaDpRoF1dCTdp62tlnAXJv0MF?usp=sharing .
Author contributions
HL: Conceptualization, Data curation, Formal Analysis, Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing. ZQ: Conceptualization, Funding acquisitiOpen asset ↗lines:1208-1229Plant phenotyping relevance match · UnverifiedEurope PMC · checked 7 Sept 2026
Wheat is a staple food crop that provides a significant portion of the world's daily caloric intake, serving as a vital source of carbohydrates and dietary fiber for billions of people. Seed shape studies of wheat typically involve the use of digital image analysis software to quantify various seed shape parameters such as length, width, area, aspect ratio, roundness, and symmetry. This study presents a comprehensive investigation into the water-absorbing capacity of seeds from 120 distinct wheat lines, leveraging digital image analysis techniques facilitated by SmartGrain software. Water absorption is a pivotal process in the early stages of seed germination, directly influencing plant growth and crop yield. SmartGrain, a powerful image analysis tool, was employed to extract precise quantitative data from digital images of wheat seeds, enabling the assessment of various seed traits in relation to their water-absorbing capacity. The analysis revealed significant transformations in seed characteristics as they absorbed water, including changes in size, weight, shape, and more. Through statistical analysis and correlation assessments, we identified robust relationships between these seed traits, both before and after water treatment. Principal Component Analysis (PCA) and Agglomerative Hierarchical Clustering (AHC) were employed to categorize genotypes with similar trait patterns, providing insights valuable for crop breeding and genetic research. Multiple linear regression analysis further elucidated the influence of specific seed traits, such as weight, width, and distance, on water-absorbing capacity. Our study contributes to a deeper understanding of seed development, imbibition, and the crucial role of water absorption in wheat. These insights have practical implications in agriculture, offering opportunities to optimize breeding programs for improved water absorption in wheat genotypes. The integration of SmartGrain software with advanced statistical methods enhances the reliability and significance of our findings, paving the way for more efficient and resilient wheat crop production. Significant changes in wheat seed shape parameters were observed after imbibition, with notable increases in area, perimeter, length, width, and weight. The length-to-width ratio (LWR) and circularity displayed opposite trends, with higher values before imbibition and lower values after imbibition.
Why it matches plant phenotyping methodsSmartGrainによるデジタル画像解析で小麦種子の形態形質を定量抽出し、吸水前後の変化を評価することが研究の中心であるため、画像ベースの植物表現型解析として含める。
abstractThis study presents a comprehensive investigation into the water-absorbing capacity of seeds from 120 distinct wheat lines, leveraging digital image analysis techniques facilitated by SmartGrain software.
Agriculture is a vital component of any nation’s economy, and India is renowned for being an agro-based economy. One of the main objectives in agriculture is to cultivate robust crops that are free from diseases. Cotton has a crucial role in generating money in India. India is the world’s leading producer of cotton. Premature leaf abscission or the onset of diseases can have detrimental effects on cotton harvests. However, throughout generations, farmers and agricultural experts have consistently faced numerous problems and chronic issues in the realm of planting, including the prevalence of various cotton diseases. There is a pressing demand in the agricultural information sector for a rapid, efficient, cost-effective, and reliable technique to detect cotton infections. This is crucial since severe cotton diseases can result in a complete failure of grain harvest. Deep learning is utilized to address the challenges of image processing and classification due to its exceptional performance. This technique employs the MobileNet paradigm. Based on the experimental results, the model attains a training accuracy of 0.95 and a validation accuracy of 0.98.
Why it matches plant phenotyping methods綿花の病害を画像から深層学習で検出・分類する手法が研究の中心であり、植物の病害状態を直接推定しているため含める。
titleRecognition of Cotton Plant Diseases Using Deep Learning Architecture
Published11 Mar 20242024 5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV)Cited by 5 · OpenAlex ↗
The early detection and identification of plant diseases are pivotal for precision agriculture, aiming to mitigate crop losses and optimize yields. This study presents a novel approach to plant disease identification, leveraging Deep Learning (DL) techniques with a focus on transfer learning. Traditional methods often rely on complex image enhancement, disease region segmentation, and feature extraction, whereas our approach employs Convolutional Neural Networks (CNNs) for efficient and accurate disease detection. To enhance accessibility and diagnostic capabilities, we implement Hybrid DL Strategy, which consists of EfficientNetB0 and MobileNetV2 model, tailored for lightweight applications suitable for smartphone implementation. Efficient NetB0 model, which considers depth, width, and resolution during convolution, enhancing the model's capacity to capture intricate features critical for accurate disease diagnosis. The overall accuracy of proposed method is 98.44%, surpassing CNN, ResNet, and AlexNet. This high accuracy underscores the effectiveness of the proposed model in correctly classifying both diseased and healthy plant leaves.
Why it matches plant phenotyping methods植物葉の画像から病害状態を分類する深層学習手法の開発・比較が中心であり、植物フェノタイピング手法として採用する。
abstractThis study presents a novel approach to plant disease identification, leveraging Deep Learning (DL) techniques with a focus on transfer learning.
Traditional monitoring of asian soybean rust severity is a time- and labor-intensive task, as it requires visual assessments by skilled professionals in the field. Thus, the use of remote sensing and machine learning (ML) techniques in data processing has emerged as an approach that can increase efficiency in disease monitoring, enabling faster, more accurate and time- and labor-saving evaluations. The aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels; (iii) which spectral input provides the highest classification accuracy for the algorithms; (iv) to determine a sample size of leaves that guarantees the best accuracy for the algorithms. A field experiment was carried out in the 2022/2023 harvest in a randomized block design with a 6x3 factorial scheme (ML algorithms x severity levels) and four replications. Disease severity levels assessed were: healthy leaves, 25 % severity, and 50 % severity. Leaf hyperspectral analysis was carried out over a wide range from 350 to 2500 nm. From this analysis, 28 spectral bands were extracted, seeking to distinguish the spectral signature for each severity level with the least input dataset. Data was subjected to machine learning analysis using Artificial Neural Network (ANN), REPTree (DT) and J48 decision trees, Random Forest (RF), and Support Vector Machine (SVM) algorithms, as well as a traditional classification method (Logistic Regression - LR). Two different input datasets were tested for each algorithm: the full spectrum (ALL) provided by the sensor and the 28 spectral bands (SB). Tests with different sample sizes were also conducted to investigate the algorithms' ability to detect severity levels with a reduced sample size. Our findings indicate differences between the spectral curves for the severity levels assessed, which makes it possible to differentiate between healthy plants with low and high severity using hyperspectral sensing. SVM was the most accurate algorithm for classifying severity levels by using all the spectral information as input. This algorithm also provided high classification accuracy when using smaller leaf samples. This study reveals that hyperspectral sensing and the use of ML algorithms provide an accurate classification of different levels of Asian rust severity, and can be powerful tools for a more efficient disease monitoring process.
Why it matches plant phenotyping methodsハイパースペクトルセンシングと機械学習により、ダイズ葉のさび病重症度を推定・分類する手法が研究の中心であり、植物病害状態の定量的フェノタイピングに該当する。
abstractThe aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels;
Citrus black spot (CBS) is a fungal disease caused by Phyllosticta citricarpa that poses a quarantine threat and can restrict market access to fruits. It manifests as lesions on the fruit surface and can result in premature fruit drops, leading to reduced yield. Another significant disease affecting citrus is canker, which is caused by the bacterium Xanthomonas citri subsp. citri (syn. X. axonopodis pv. citri); it causes economic losses for growers due to fruit drops and blemishes. Early detection and management of groves infected with CBS or canker through fruit and leaf inspection can greatly benefit the Florida citrus industry. However, manual inspection and classification of disease symptoms on fruits or leaves are labor-intensive and time-consuming processes. Therefore, there is a need to develop a computer vision system capable of autonomously classifying fruits and leaves, expediting disease management in the groves. This paper aims to demonstrate the effectiveness of convolutional neural network (CNN) generated features and machine learning (ML) classifiers for detecting CBS infected fruits and leaves with canker symptoms. A custom shallow CNN with radial basis function support vector machine (RBF SVM) achieved an overall accuracy of 92.1% for classifying fruits with CBS and four other conditions (greasy spot, melanose, wind scar, and marketable), and a custom Visual Geometry Group 16 (VGG16) with the RBF SVM classified leaves with canker and four other conditions (control, greasy spot, melanoses, and scab) at an overall accuracy of 93%. These preliminary findings demonstrate the potential of utilizing hyperspectral imaging (HSI) systems for automated classification of citrus fruit and leaf diseases using shallow and deep CNN-generated features, along with ML classifiers.
Why it matches plant phenotyping methods柑橘の果実・葉に現れる病徴をハイパースペクトル画像とCNN/機械学習で自動分類する方法が研究の中心であり、植物病害状態の表現型推定に該当する。
abstractTherefore, there is a need to develop a computer vision system capable of autonomously classifying fruits and leaves, expediting disease management in the groves.
The efficient production of oil from oil palm trees is heavily dependent on their health status, reflected in the oil extraction rate (OER). The 17th frond of the oil palm trees contains a significant amount of organic compounds that directly influence the overall health of the tree. Achieving an optimal balance of essential nutrients such as nitrogen (N), phosphorus (P), and potassium (K) is crucial for classifying a tree as healthy, as it results in an increased oil to bunch and fruit to bunch ratio. To accurately assess the health level of oil palm trees, this study explores the application of Raman spectroscopy, a non-invasive technique in determining the molecular fingerprint of an organic sample. In this research, Raman spectroscopy is employed to determine the health level of oil palm trees, and a machine learning-based health level classification algorithm is developed. The algorithm analyzes the organic compounds found in oil palm leaves, which were collected from 20 different trees. The extracted spectral features from these leaves are used to classify them into two health levels: healthy and not healthy. For this purpose, 31 machine learning models are tested to identify the most accurate classifier. The findings reveal that the Tree and fine K-Nearest Neighbors (KNN) classifier demonstrates the highest overall accuracy of 95% using three significant features, namely the Raman intensity, Full Width at Half Maximum (FWHM), and area under the curve. This result signifies the potential of Raman spectroscopy as a reliable and promising method for non-invasively phenotyping oil palm leaves, enabling precise prediction of the health status of oil palm trees.
Why it matches plant phenotyping methodsラマン分光による油ヤシ葉の健康状態（植物状態）の非侵襲的推定と、スペクトル特徴量を用いた分類手法の開発が中心であるため、植物フェノタイピング手法として採用する。
abstractTo accurately assess the health level of oil palm trees, this study explores the application of Raman spectroscopy, a non-invasive technique in determining the molecular fingerprint of an organic sample.
Coffee Leaf Rust (CLR), caused by the fungus Hemileia vastatrix, poses a severe threat to global coffee production. Timely detection is critical for effective control measures. This study employs Convolutional Neural Networks (CNNs) to enhance CLR detection accuracy. Traditionally, this task relies on expert assessment. DL emerges as a promising approach, capable of autonomously extracting salient features. Our model, trained on a diverse dataset, accurately identifies CLR. Using 1365 meticulously curated images, the model undergoes rigorous preprocessing and augmentation. The DL-based approach achieves remarkable accuracy (98.89%), precision (99.00%), recall (98.07%), and an F1 score of (98.55%). These outcomes establish the CNN model as a proficient system for precise, real-time CLR diagnosis. This study contributes to the creation of an efficient system, safeguarding coffee orchard vitality and productivity.
Why it matches plant phenotyping methodsコーヒー葉の病徴を画像から検出・分類するCNN手法が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採用。
abstractThis study employs Convolutional Neural Networks (CNNs) to enhance CLR detection accuracy.
The number of seedlings is an important indicator that reflects the size of the wheat population during the seedling stage. Researchers increasingly use deep learning to detect and count wheat seedlings from unmanned aerial vehicle (UAV) images. However, due to the small size and diverse postures of wheat seedlings, it can be challenging to estimate their numbers accurately during the seedling stage. In most related works in wheat seedling detection, they label the whole plant, often resulting in a higher proportion of soil background within the annotated bounding boxes. This imbalance between wheat seedlings and soil background in the annotated bounding boxes decreases the detection performance. This study proposes a wheat seedling detection method based on a local annotation instead of a global annotation. Moreover, the detection model is also improved by replacing convolutional and pooling layers with the Space-to-depth Conv module and adding a micro-scale detection layer in the YOLOv5 head network to better extract small-scale features in these small annotation boxes. The optimization of the detection model can reduce the number of error detections caused by leaf occlusion between wheat seedlings and the small size of wheat seedlings. The results show that the proposed method achieves a detection accuracy of 90.1%, outperforming other state-of-the-art detection methods. The proposed method provides a reference for future wheat seedling detection and yield prediction.
Why it matches plant phenotyping methodsコムギ幼苗の検出・計数という植物個体数形質を対象に、アノテーション方式と深層学習モデルを開発・評価しており、表現型取得手法が研究の中心である。
abstractThis study proposes a wheat seedling detection method based on a local annotation instead of a global annotation.
Agriculture faces challenges in achieving high-yield production while minimizing the use of chemicals. The excessive use of chemicals in agriculture poses many problems. Accurate disease diagnosis is crucial for effective plant disease detection and treatment. Automatic identification of plant diseases using computer vision techniques offers new and efficient approaches compared to traditional methods. Transformers, a type of deep learning model, have shown great promise in computer vision, but as the technology is still new, many vision transformer models struggle to identify diseases by examining the entire leaf. This paper aims to utilize the vision transformer model in analyzing and identifying common diseases that hinder the growth and development of plants through the plant leave images. Besides, it aims to improve the model's stability by focusing more on the entire leaf than individual parts and generalizing better results on leaves not in the image center. Added features such as Shift Patch Tokenization, Locality Self Attention, and Positional Encoding help focus on the whole leaf. The final test accuracy obtained is 89.58%, with relatively slight variances in precision, accuracy, and F1 score across classes, as well as satisfactory model robustness towards changes in leaf orientation and position within the image. The model's effectiveness shows the vision transformer's potential for automated plant disease diagnosis, which can help farmers take timely measures to prevent losses and ensure food security.
Why it matches plant phenotyping methods葉画像から植物病害を自動識別し、全葉への注目や画像位置・向きの変化に対する頑健性を評価する手法開発であり、植物の病害状態推定が中心です。
abstractAutomatic identification of plant diseases using computer vision techniques offers new and efficient approaches compared to traditional methods.
Plant diseases appear to be posing a serious danger to the production and availability of food globally. The main factor affecting the quality and productivity of agricultural products is the health of the plants. In this paper, we describe a modified plant disease detection using deep convolutional neural networks in real time. By employing image processing techniques to enlarge the plant illness photos, the plant disease sets of data were initially produced. To recognise plant illnesses, a system called Convolutional Neural Network combined with Wolf Optimisation algorithm (CNN-WO) was used. Finally, the Whale Optimization algorithm (WO) is used to maximise and optimizes getting input. And it is given to CNN's learning rate for classification process. This paper presents an image segmentation and classification technique to automatically identify plant leaf diseases. The suggested strategy increased accuracy, sensitivity, precision, F1 measure, and specificity of plant disease detection. According to this study, HCNNWO real detectors have improved, which would require deep learning. It would be an effective method for determining plant illnesses and other diseases within plants. According to the evaluation report, the suggested method offers good reliability. To evaluate how well the suggested algorithm performs in comparison to cutting-edge techniques such as SVM, BPNN and CNN, experiments are conducted on datasets that are openly accessible
Why it matches plant phenotyping methods植物葉の画像から病害状態を自動検出・分類する画像処理および深層学習手法が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractThis paper presents an image segmentation and classification technique to automatically identify plant leaf diseases.
Food security is fundamental to a country. As the main risk factors, pests and diseases seriously restrict the normal growth of crops and the quality and safety of agricultural products. With the intensification of climate change and the continuous adjustment of farming methods, crop diseases and pests have become more frequent in recent years. Therefore, the agricultural production mode has gradually moved from family production to large-scale agricultural planting, and the production equipment has become more automated and intelligent. Agricultural intelligent robots can reduce labor costs in the process of agricultural production and improve the standardization of agricultural production. The application of computer vision in agriculture is rapidly becoming an important aspect of modern agricultural technology, especially in crop positioning and management. Through the use of advanced image processing algorithms and pattern recognition technology, computer vision systems are able to accurately identify and locate various crops in the field, enabling automated and precise management. This technology shows great potential for crop health monitoring, pest identification, and maturity assessment. For example, by analyzing images of plants, computer vision systems can spot signs of lesions or nutrient deficiencies in time and guide farmers to treat them accordingly. In addition, this technology can also be used to guide automated agricultural machinery, such as driverless tractors and harvesters, to improve the efficiency of crop harvesting and reduce labor costs. In general, the combination of computer vision and crops provides new technical means for the development of modern precision agriculture, which helps to improve the efficiency and sustainability of agricultural production.
Why it matches plant phenotyping methods植物画像から病徴を識別する深層学習・コンピュータビジョン手法が題名と概要の中心であり、植物の病害状態を推定するフェノタイピング手法に該当する。
titleA deep learning-based algorithm for crop Disease identification positioning using computer vision
In India, agriculture serves as the primary income source for the majority of the population. Identifying crop diseases is a critical factor in mitigating production losses. To address this, deep learning techniques, specifically utilizing pre-trained Convolutional Neural Network (CNN) models such as ResNet-50, VGG-16, MobileNetV2, and InceptionV3, are employed for the detection of plant diseases. This study involves different key stages including dataset creation, preprocessing, data augmentation, and classification. The dataset comprises 3725 images of cotton plant leaves distributed across 11 classes. Here, the model performance is assessed based on classification accuracy, with ResNet-50 achieving the highest accuracy at 99.8% among the four approaches.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類する深層学習手法の比較・評価が研究の中心であり、植物の病害状態を直接推定するため、方法論文として採用する。
abstractdeep learning techniques, specifically utilizing pre-trained Convolutional Neural Network (CNN) models such as ResNet-50, VGG-16, MobileNetV2, and InceptionV3, are employed for the detection of plant diseases.
The detection of plant diseases is critical for maintaining crop health and maximizing agricultural yields. This research proposes a comprehensive approach to improve plant disease detection by addressing challenges related to unbalanced datasets and leveraging generative adversarial networks (GANs). This research focuses on enhancing the accuracy and generalization capabilities of disease recognition models. To address dataset bias, a larger and more diverse dataset is collected, comprising unhealthy plant leaves from various plants, regions, and disease types. The expanded dataset enables comprehensive training and validation, ensuring a representative depiction of leaf variations and diseases. Domain-specific knowledge and expert guidance are incorporated to capture realistic and characteristic attributes of diseased leaves. To overcome overfitting, the regularization technique is applied during training. These techniques promote the learning of generalized representations and mitigate the generation of unrealistic or repetitive images. The proposed approach is extensively evaluated using Plant Village dataset encompassing various plant species, and disease types. By implementing these solutions, this research enhances the accuracy, robustness, and generalization capabilities of plant disease detection systems. It establishes a foundation for reliable and effective detection methods, contributing to the sustainable management of plant diseases and improved agricultural outcomes.
Why it matches plant phenotyping methods植物葉の病害状態を画像から検出する手法の改善が研究の中心であり、データセット拡張、GAN、正則化、評価を含むため、植物フェノタイピング手法として採用する。
abstractThis research proposes a comprehensive approach to improve plant disease detection by addressing challenges related to unbalanced datasets and leveraging generative adversarial networks (GANs).
StrawberryFruitObject detectionGrowth / development / phenology
Identifying the ripeness of strawberries can be challenging due to their complex growth environment, interference from light intensity, and shading caused by strawberry aggregation. To address these issues, this study aims to develop an algorithm for accurately detecting and classifying ripe strawberries. This study proposed a novel LS-YOLOv8s model for detecting and grading the ripeness of strawberries, which is based on the YOLOv8s deep learning algorithm and incorporates the LW-Swin Transformer module. To improve the performance of the model, two new random variables were introduced in the contrast enhancement process to control the enhancement effect. The dataset was expanded from 1089 to 7515 images, which increased the diversity of the data and reduced the risk of over fitting the model. Additionally, the Swin Transformer module was added to the TopDown Layer2 during the feature fusion stage to capture long distance dependencies in the input data and improve the generalization capability of the model with the use of a multi-headed self-attention mechanism. Finally, a more efficient feature fusion network was achieved by introducing a residual network with learnable parameters and scaled normalization into the original residual structure of the Swin Transformer. To evaluate the effectiveness of LS-YOLOv8s for strawberry ripeness detection, we collected a dataset of strawberry images from a strawberry planting base. The dataset was split using the 5-fold cross-validation approach, which improved the model evaluation process. Experimental results showed that LS-YOLOv8s better than other models, with a 1.6 %, 33.5 %, and 3.4 % improvement in mAP0.5 on the validation set compared to YOLOv5s, CenterNet, and SSD, respectively. Moreover, LS-YOLOv8s achieved better detection precision and speed than YOLOv8m with only approximately 51.93 % of the number of parameters used, achieving 94.4 % detection precision and 19.23fps detection speed, improving by 0.5 % and 6.56fps, respectively. The LS-YOLOv8s model can provide reliable theoretical support for detecting strawberry targets, evaluating their ripeness, and automating the strawberry picking process for orchard management.
Why it matches plant phenotyping methodsイチゴ画像から成熟度という植物器官の状態を推定するYOLOベース手法を開発・評価しており、表現型取得・抽出手法が中心である。
abstractThis study proposed a novel LS-YOLOv8s model for detecting and grading the ripeness of strawberries
Plant diseases in tea trees can result in significant losses in both the quality and quantity of tea production. Regular monitoring can prevent the occurrence of large-scale diseases in tea plantations. However, existing methods face challenges such as a high number of parameters and low recognition accuracy, which hinder their application for monitoring tea gardens on edge devices. This paper presents a lightweight I-MobileNetV2 model for identifying diseases in tea leaves, with the goal of addressing these challenges. The proposed method embeds a coordinate attention mechanism module into the original MobileNetV2 network, enabling the model to accurately locate disease regions. Furthermore, a multi-branch parallel convolution module is employed to extract disease features across multiple scales, which improves the adaptability of the model to different disease scales. Then an automated pruning strategy is employed to compress the model and reduce computational complexity. The results indicate that algorithm proposed surpass the original MobileNetV2 by 1.91 percentage points with an average accuracy of 96.12% based on self-built tea disease dataset, the model parameters have been reduced by 40%, making it more suitable for practical application in tea garden environments.
Why it matches plant phenotyping methods茶葉の病斑領域・病害状態を画像から識別する軽量深層学習手法を開発し、精度と計算量を評価しているため、植物病害フェノタイピング手法が中心である。
abstractThis paper presents a lightweight I-MobileNetV2 model for identifying diseases in tea leaves
In order to realize the acquisition of plant leaf images by agricultural drones and perform regional segmentation and disease recognition on leaf cluster images over a wide area, this paper takes grape leaves as an example and designs a set of processing procedures combining the improved U-net and VGG-19 networks. This paper aims to address the difficulty of obtaining target leaves for recognition in complex environments due to the presence of multiple invalid leaves. First, the feature extraction process is performed on the training and validation datasets to reduce the input parameters of the network and increase the training speed. Second, the test data is divided into three datasets: low-light, jitter interference, and two-factor combination. After recovery processing, the Multi-fusion U-net network is fed to locate diseased leaves. Finally, the improved VGG-19 network was used again to locate and identify the disease. Experimental results show that the proposed procedure achieves satisfactory performance in UAV image processing. The average accuracy of segmentation reaches 71.91%, and the identification rate of disease location is increased by 12.33% after segmentation, which provides a strong practical basis for the implementation of unmanned smart ecological farms.
Why it matches plant phenotyping methodsUAV画像からブドウ葉の病変状態を分割・定位・認識するCNNベースの画像解析手法が研究の中心であり、植物病害表現型の取得・推定に該当する。
abstractdesigns a set of processing procedures combining the improved U-net and VGG-19 networks
The timely detection and management of plant diseases is critical in the agricultural industry. Among these, potato leaf diseases can have a major impact on crop productivity and quality. This research addresses the important requirement for rapid and reliable disease detection in potato plants. Using Convolutional Neural Networks (CNNs), a sophisticated deep learning approach, we gain considerable progress in automating the identification process. We demonstrate the models ability to distinguish diverse kinds of disease with an amazing accuracy rate of 98.8% through rigorous experimentation. The use of data augmentation techniques improves the models flexibility to a variety of environmental situations. This breakthrough has significant promise for shaping agricultural methods, providing a powerful tool for early disease intervention, and ensuring global food security. KEYWORDS - Deep learning, Convolutional Neural Network (CNN), potato diseases, TensorFlow, Streamlit.
Why it matches plant phenotyping methodsCNNによるジャガイモ葉の病徴・病害状態の画像分類手法を開発・評価しており、植物フェノタイピング手法が中心である。
abstractUsing Convolutional Neural Networks (CNNs), a sophisticated deep learning approach, we gain considerable progress in automating the identification process.
Agriculture plays a pivotal role in the economies of developing countries by providing livelihoods, sustenance, and employment opportunities in rural areas. However, crop diseases pose a significant threat to both farmers' incomes and food security. Furthermore, these diseases also show adverse effects on human health by causing various illnesses. Till date, only a limited number of studies have been conducted to identify and classify diseased cauliflower plants but they also face certain challenges such as insufficient disease surveillance mechanisms, the lack of comprehensive datasets that are properly labelled as well as are of high quality, and the considerable computational resources that are necessary for conducting thorough analysis. In view of the aforementioned challenges, the primary objective of this manuscript is to tackle these significant concerns and enhance understanding regarding the significance of cauliflower disease identification and detection in rural agriculture through the use of advanced deep transfer learning techniques. The work is conducted on the four classes of cauliflower diseases i.e. Bacterial spot rot, Black rot, Downy Mildew, and No disease which are taken from VegNet dataset. Ten deep transfer learning models such as EfficientNetB0, Xception, EfficientNetB1, MobileNetV2, EfficientNetB2, DenseNet201, EfficientNetB3, InceptionResNetV2, EfficientNetB4, and ResNet152V2, are trained and examined on the basis of root mean square error, recall, precision, F1-score, accuracy, and loss. Remarkably, EfficientNetB1 achieved the highest validation accuracy (99.90%), lowest loss (0.16), and root mean square error (0.40) during experimentation. It has been observed that our research highlights the critical role of advanced CNN models in automating cauliflower disease detection and classification and such models can lead to robust applications for cauliflower disease management in agriculture, ultimately benefiting both farmers and consumers.
Why it matches plant phenotyping methodsカリフラワー植物の病害状態を画像ベースの深層学習で検出・分類する方法が研究の中心であり、植物病害表現型の取得・推定に該当する。
abstractthe primary objective of this manuscript is to tackle these significant concerns and enhance understanding regarding the significance of cauliflower disease identification and detection
Wild rice, a natural gene pool for rice germplasm innovation and variety improvement, holds immense value in rice breeding due to its disease-resistance genes. Traditional disease resistance identification in wild rice heavily relies on labor-intensive and subjective manual methods, posing significant challenges for large-scale identification. The fusion of unmanned aerial vehicles (UAVs) and deep learning is emerging as a novel trend in intelligent disease resistance identification. Detecting diseases in field conditions is critical in intelligent disease resistance identification. In pursuit of detecting bacterial blight in wild rice within natural field conditions, this study presents the Xoo-YOLO model, a modification of the YOLOv8 model tailored for this purpose. The Xoo-YOLO model incorporates the Large Selective Kernel Network (LSKNet) into its backbone network, allowing for more effective disease detection from the perspective of UAVs. This is achieved by dynamically adjusting its large spatial receptive field. Concurrently, the neck network receives enhancements by integrating the GSConv hybrid convolution module. This addition serves to reduce both the amount of calculation and parameters. To tackle the issue of disease appearing elongated and rotated when viewed from a UAV perspective, we incorporated a rotational angle (theta dimension) into the head layer's output. This enhancement enables precise detection of bacterial blight in any direction in wild rice. The experimental results highlight the effectiveness of our proposed Xoo-YOLO model, boasting a remarkable mean average precision (mAP) of 94.95%. This outperforms other models, underscoring its superiority. Our model strikes a harmonious balance between accuracy and speed in disease detection. It is a technical cornerstone, facilitating the intelligent identification of disease resistance in wild rice on a large scale.
Why it matches plant phenotyping methodsUAV画像から野生イネの細菌性葉枯病を検出・定量する深層学習モデルを開発し、精度比較で検証している。植物の病害状態の取得が研究の中心である。
abstractthis study presents the Xoo-YOLO model, a modification of the YOLOv8 model tailored for this purpose.
Rapid and accurate prediction of crop yield is particularly important for ensuring national and regional food security and guiding the formulation of agricultural and rural development plans. Due to unmanned aerial vehicles' ultra-high spatial resolution, low cost, and flexibility, they are widely used in field-scale crop yield prediction. Most current studies used the spectral features of crops, especially vegetation or color indices, to predict crop yield. Agronomic trait parameters have gradually attracted the attention of researchers for use in the yield prediction in recent years. In this study, the advantages of multispectral and RGB images were comprehensively used and combined with crop spectral features and agronomic trait parameters (i.e., canopy height, coverage, and volume) to predict the crop yield, and the effects of agronomic trait parameters on yield prediction were investigated. The results showed that compared with the yield prediction using spectral features, the addition of agronomic trait parameters effectively improved the yield prediction accuracy. The best feature combination was the canopy height (CH), fractional vegetation cover (FVC), normalized difference red-edge index (NDVI_RE), and enhanced vegetation index (EVI). The yield prediction error was 8.34%, with an R 2 of 0.95. The prediction accuracies were notably greater in the stages of jointing, booting, heading, and early grain-filling compared to later stages of growth, with the heading stage displaying the highest accuracy in yield prediction. The prediction results based on the features of multiple growth stages were better than those based on a single stage. The yield prediction across different cultivars was weaker than that of the same cultivar. Nevertheless, the combination of agronomic trait parameters and spectral indices improved the prediction among cultivars to some extent.
Why it matches plant phenotyping methodsUAV画像から作物のキャノピー形質を抽出し、スペクトル特徴と融合して収量を予測するワークフローが中心であり、形質推定と技術評価を伴うため対象に含める。
abstractthe advantages of multispectral and RGB images were comprehensively used and combined with crop spectral features and agronomic trait parameters (i.e., canopy height, coverage, and volume) to predict the crop yield
High throughput phenotyping has wide applications to evaluate genetic traits, plant growth and development in different biotic and abiotic stress environments, as well as under different agriculture management strategies. Additionally, understanding product efficacy and identifying the mode of action prior to field testing would improve product pipeline development for agriculture manufacturers and distributors. WinField United is using multispectral imaging in different stress conditions within a controlled environment setting to evaluate product effectiveness. We have evaluated pesticide product efficacy in the presence and absence of adjuvants. Adjuvants are materials added to a pesticide to enhance performance by improving absorption, spreading, sticking, and penetration properties of the pesticide’s active ingredient(s). We have measured a statistically significant increase in pesticide efficacy with the addition of an adjuvant in multiple, independent case studies showing the increased plant health benefit. In one study, we observed a 31% decrease in diseased oat plant tissue [when defined as pixels with Normalized Difference Vegetation Index (NDVI) value <0.3] when an adjuvant was added to a commercial fungicide compared to the untreated control and a 23% improvement when compared to the fungicide alone. Multispectral imaging has also allowed us to build interactive, 3-D models that demonstrate product coverage and penetration. Combining quantitative measurements with interactive, illustrative models, we can more effectively communicate product efficacy results to retail owners and growers. Future directions include evaluating biological product efficacy in which more nuanced plant responses are observed in biotic and abiotic stress environments.
Why it matches plant phenotyping methodsマルチスペクトル画像を用いて植物の健康状態・病害組織を定量化し、農薬・アジュバント効果評価へ実質的に適用しているため、表現型取得法の応用研究として含める。
abstractWinField United is using multispectral imaging in different stress conditions within a controlled environment setting to evaluate product effectiveness.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 7 Sept 2026
Abstract Background Detection and counting of wheat heads are of crucial importance in the field of plant science, as they can be used for crop field management, yield prediction, and phenotype analysis. With the widespread application of computer vision technology in plant science, monitoring of automated high-throughput plant phenotyping platforms has become possible. Currently, many innovative methods and new technologies have been proposed that have made significant progress in the accuracy and robustness of wheat head recognition. Nevertheless, these methods are often built on high-performance computing devices and lack practicality. In resource-limited situations, these methods may not be effectively applied and deployed, thereby failing to meet the needs of practical applications. Results In our recent research on maize tassels, we proposed TasselLFANet, the most advanced neural network for detecting and counting maize tassels. Building on this work, we have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection. WheatLFANet features a more compact encoder-decoder structure and an effective multi-dimensional information mapping fusion strategy, allowing it to run efficiently on low-end devices while maintaining high accuracy and practicality. According to the evaluation report on the global wheat head detection dataset, WheatLFANet outperforms other state-of-the-art methods with an average precision AP of 0.900 and an R 2 value of 0.949 between predicted values and ground truth values. Moreover, it runs significantly faster than all other methods by an order of magnitude (TasselLFANet: FPS: 61). Conclusions Extensive experiments have shown that WheatLFANet exhibits better generalization ability than other state-of-the-art methods, and achieved a speed increase of an order of magnitude while maintaining accuracy. The success of this study demonstrates the feasibility of achieving real-time, lightweight detection of wheat heads on low-end devices, and also indicates the usefulness of simple yet powerful neural network designs.
Why it matches plant phenotyping methods小麦穂の検出・計数という植物器官形質の画像ベース推定手法を開発し、データセット上で精度・速度・汎化性能を評価しているため、方法が研究の中心である。
abstractwe have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection.
Computer vision and deep learning have made substantial progress in the areas of agriculture and smart farming, particularly for enhancing crop production using image segmentation techniques for crop yield prediction. Further improvements to crop yield prediction results can be achieved by developing accurate and efficient methods. In response to such demands, this paper proposes a novel convolutional neural network architecture, called densely connected SegNet (D-SegNet) and demonstrates its advantages on plant segmentation using a new morning glory plant dataset, and also on a complimentary publicly available dataset to promote research in this direction. The D-SegNet is evaluated using 10-fold cross validation. It achieves performance better than the state-of-the-art SegNet algorithm. The evaluated precision, recall and F1-score values are 98.20%, 90.64% and 94.26%, respectively, for the morning glory plant dataset. The intersection over union (IoU) value in the image segmentation tasks is 90.56%. A series of experiments on the morning glory plant dataset as well as on the publicly available dataset were conducted. The results show that the proposed method achieves accurate segmentation results and can be useful for assessing the plant weight during harvesting. In summary, this new plant segmentation network, D-SegNet, could form an important component of future cloud-based machine learning systems to predict crop yield from noisy smartphone images taken in the field.
Why it matches plant phenotyping methods植物画像のセマンティックセグメンテーション手法とベンチマークデータセットを開発・評価し、収穫時の植物重量推定という植物形質推定への利用を示しており、方法が中心である。
abstractthis paper proposes a novel convolutional neural network architecture, called densely connected SegNet (D-SegNet)
The devastating effect of plant disease infestation on crop production poses a significant threat to the attainment of the United Nations' Sustainable Development Goal 2 (SDG2) of food security, especially in Sub-Saharan Africa. This has been further exacerbated by the lack of effective and accessible plant disease detection technologies. Farmers' inability to quickly and accurately diagnose plant diseases leads to crop destruction and reduced productivity. The diverse range of existing plant diseases further complicates detection for farmers without the right technologies, hindering efforts to combat food insecurity in the region. This study presents a web-based plant diagnosis application, referred to as mobile-enabled Plant Diagnosis-Application (mPD-App). First, a publicly available image dataset, containing a diverse range of plant diseases, was acquired from Kaggle for the purpose of training the detection system. The image dataset was, then, made to undergo the preprocessing stage which included processes such as image-to-array conversion, image reshaping, and data augmentation. The training phase leverages the vast computational ability of the convolutional neural network (CNN) to effectively classify image datasets. The CNN model architecture featured six convolutional layers (including the fully connected layer) with phases, such as normalization layer, rectified linear unit (RELU), max pooling layer, and dropout layer. The training process was carefully managed to prevent underfitting and overfitting of the model, ensuring accurate predictions. The mPD-App demonstrated excellent performance in diagnosing plant diseases, achieving an overall accuracy of 93.91%. The model was able to classify 14 different types of plant diseases with high precision and recall values. The ROC curve showed a promising area under the curve (AUC) value of 0.946, indicating the model's reliability in detecting diseases. The web-based mPD-App offers a valuable tool for farmers and agricultural stakeholders in Sub-Saharan Africa, to detect and diagnose plant diseases effectively and efficiently. To further improve the application's performance, ongoing efforts should focus on expanding the dataset and refining the model's architecture. Agricultural authorities and policymakers should consider promoting and integrating such technologies into existing agricultural extension services to maximize their impact and benefit the farming community.
Why it matches plant phenotyping methods植物病害画像から病害状態を分類するCNNとモバイル診断アプリの開発・性能評価が研究の中心であり、植物病害フェノタイプの取得・推定に該当する。
abstractThis study presents a web-based plant diagnosis application, referred to as mobile-enabled Plant Diagnosis-Application (mPD-App).
Reproduction assets foundThe paper's CNN plant-disease diagnosis model was trained on the publicly available PlantVillage image dataset, which the authors explicitly retrieved from a public GitHub repository with a URL matching the allowed list. This is the paper-specific image input used for its phenotyping measurements. No author analysis代码,Dataset · publicThe implementation procedure of the mPD-App is further repository https://github.com/spMohanty/PlantVillage-DatasetOpen asset ↗spMohanty/PlantVillage-Datasetpdf-page:5 lines:1-49Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · checked 7 Sept 2026
Rapeseed is a significant oil crop, and the size and length of its pods affect its productivity. However, manually counting the number of rapeseed pods and measuring the length, width, and area of the pod takes time and effort, especially when there are hundreds of rapeseed resources to be assessed. This work created two state-of-the-art deep learning-based methods to identify rapeseed pods and related pod attributes, which are then implemented in rapeseed pots to improve the accuracy of the rapeseed yield estimate. One of these methods is YOLO v8, and the other is the two-stage model Mask R-CNN based on the framework Detectron2. The YOLO v8n model and the Mask R-CNN model with a Resnet101 backbone in Detectron2 both achieve precision rates exceeding 90%. The recognition results demonstrated that both models perform well when graphic images of rapeseed pods are segmented. In light of this, we developed a coin-based approach for estimating the size of rapeseed pods and tested it on a test dataset made up of nine different species of Brassica napus and one of Brassica campestris L. The correlation coefficients between manual measurement and machine vision measurement of length and width were calculated using statistical methods. The length regression coefficient of both methods was 0.991, and the width regression coefficient was 0.989. In conclusion, for the first time, we utilized deep learning techniques to identify the characteristics of rapeseed pods while concurrently establishing a dataset for rapeseed pods. Our suggested approaches were successful in segmenting and counting rapeseed pods precisely. Our approach offers breeders an effective strategy for digitally analyzing phenotypes and automating the identification and screening process, not only in rapeseed germplasm resources but also in leguminous plants, like soybeans that possess pods.
Why it matches plant phenotyping methodsナタネ莢の画像セグメンテーション、計数、長さ・幅・面積推定手法を開発し、手動測定との相関で検証しているため、植物フェノタイピング手法が中心である。
abstractThis work created two state-of-the-art deep learning-based methods to identify rapeseed pods and related pod attributes
The evolutionary histories of species have been shaped by genomic, environmental, and morphological variation. Understanding the interactions among these sources of variation is critical to infer accurately the biogeographic history of lineages. Here, using the geographically widely distributed plum genus (Prunus, Rosaceae) as a model, we investigate how changes in genomic and environmental variation drove the diversification of this group, and we quantify the morphological features that facilitated or resulted from diversification. We sequenced 587 nuclear loci and complete chloroplast genomes from 99 species representing all major lineages in Prunus, with a special focus on the understudied tropical racemose group. The environmental variation in extant species was quantified by synthesizing bioclimatic variables into principal components of environmental variation using thousands of georeferenced herbarium specimens. We used machine learning algorithms to classify and measure morphological variation present in thousands of digitized herbarium sheet images. Our phylogenomic and biogeographic analyses revealed that ancient hybridization and/or allopolyploidy spurred the initial rapid diversification of the genus in the early Eocene, with subsequent diversification in the north temperate zone, neotropics, and paleotropics. This diversification involved successful transitions between tropical and temperate biomes, an exceedingly rare event in woody plant lineages, accompanied by morphological changes in leaf and reproductive morphology. The machine learning approach detected morphological variation associated with ancient hybridization and quantified the breadth of morphospace occupied by major lineages within the genus. The paleotropical lineages of Prunus have diversified steadily since the late Eocene/early Oligocene, while the neotropical lineages diversified much later. Critically, both the tropical and temperate lineages have continued to diversify. We conclude that the genomic rearrangements created by reticulation deep in the phylogeny of Prunus may explain why this group has been more successful than other groups with tropical origins that currently persist only in either tropical or temperate regions, but not both.
Why it matches plant phenotyping methods機械学習を用いて標本画像から植物の形態変異を分類・測定し、葉および生殖形態の表現型を定量化しており、形態計測ワークフローが研究の中心的要素である。
abstractWe used machine learning algorithms to classify and measure morphological variation present in thousands of digitized herbarium sheet images.
Reproduction assets foundThe paper's herbarium image data and supplementary material are deposited in Dryad; trained Prunus ML classifiers are on Hugging Face; author Jupyter notebooks for the ML workflow are on GitHub. All are paper-specific, public, and actionable.Dataset · public1126 Data Availability
1127
1128 Data available from the Dryad Digital Repository: DOI: 10.5061/dryad.x95x69pwr; Reviewer
1129 URL: http://datadryad.org/share/L-QUcxrgnpTr6l0Td3MxdfJDCUT1iRbPmT4SzA2LwMA.
1130
1131 Supplementary material, image data, and DNA sequence matrices are available from the Dryad
1132 Digital Repository. Raw sequence data were submitted to NCBI GenBank (SUB13638423).
1133 Machine learning models are hosted on Hugging Face with temporary URLs
1134 (https://huggingface.co/richiehodel/Prunus_lineage_classiOpen asset ↗Dryad Digital Repository · 10.5061/dryad.x95x69pwrpdf-layout-page:54 lines:1-31Plant phenotyping relevance match · UnverifiedOpenAlex · checked 14 Sept 2026
Climate change has negatively affected agriculture worldwide, including soybean production. Studies have shown that rising temperatures and extreme weather events like droughts and floods significantly reduce soybean yields. Developing flood-tolerant soybean genotypes is crucial for ensuring food security. Conventional breeding programs are limited by laborious and imprecise visual rating methods for flooding tolerance identification. High-throughput platforms for plant phenotyping using imaging techniques offer potential solutions, but they lack information on underlying physiological mechanisms. Non-photochemical quenching (NPQ) is a molecular adaptation in photosynthesis that dissipates excess light energy, protecting plants from damage. This study aimed to integrate NPQ measurements into high-throughput phenotyping procedures to identify flooding-tolerant soybean genotypes. The study evaluated 160 soybean genotypes for flooding tolerance, identifying those with higher grain yield potential. Subsequently, ten genotypes were selected for monitoring NPQ responses under flooded conditions. Results showed that genotypes with higher grain yields also exhibited superior NPQ performance, suggesting a positive correlation between flooding tolerance and energy dissipation capacity. Among these genotypes, 58I60 RSF IPRO, 64HO130 I2X and BRS 525 displayed superior potential and could be further exploited in breeding efforts, considering their grain yield capacity, plant leaf area, and photoprotective capacity under flooding conditions. These findings suggest that integrating NPQ measurements into high-throughput phenotyping platforms can aid in identifying flood-tolerant soybean genotypes for breeding programs, leading to more resilient crops in the face of climate change. Further field studies are warranted to validate these hypotheses and improve crop models for future climate scenarios.
Why it matches plant phenotyping methodsNPQ測定をハイスループット植物フェノタイピング手順に統合し、洪水耐性という植物生理状態の評価へ適用することが研究の中心的目的であるため。
abstractThis study aimed to integrate NPQ measurements into high-throughput phenotyping procedures to identify flooding-tolerant soybean genotypes.
Rwandan coffee holds significant importance and immense value within the realm of agriculture, serving as a vital and valuable commodity. Additionally, coffee plays a pivotal role in generating foreign exchange for numerous developing nations. However, the coffee plant is vulnerable to pests and diseases weakening production. Farmers in cooperation with experts use manual methods to detect diseases resulting in human errors. With the rapid improvements in deep learning methods, it is possible to detect and recognize plan diseases to support crop yield improvement. Therefore, it is an essential task to develop an efficient method for intelligently detecting, identifying, and predicting coffee leaf diseases. This study aims to build the Rwandan coffee plant dataset, with the occurrence of coffee rust, miner, and red spider mites identified to be the most popular due to their geographical situations. From the collected coffee leaves dataset of 37,939 images, the preprocessing, along with modeling used five deep learning models such as InceptionV3, ResNet50, Xception, VGG16, and DenseNet. The training, validation, and testing ratio is 80%, 10%, and 10%, respectively, with a maximum of 10 epochs. The comparative analysis of the models’ performances was investigated to select the best for future portable use. The experiment proved the DenseNet model to be the best with an accuracy of 99.57%. The efficiency of the suggested method is validated through an unbiased evaluation when compared to existing approaches with different metrics.
Why it matches plant phenotyping methodsコーヒー葉の病害状態を画像から認識・分類する深層学習手法とデータセットを中心に開発・比較・検証しており、植物病害フェノタイプの取得が中心である。
abstractThis study aims to build the Rwandan coffee plant dataset
Monitoring plant growth is a crucial agricultural duty. In addition, the prevention of plant diseases is an essential component of the agricultural infrastructure. This technique must be automated to keep up with the rising food demand caused by increasing population expansion. This work evaluates this business, specifically the production of maize, which is a significant source of food worldwide. Ensure that Mazie's yields are not damaged is a crucial endeavour. Diseases affecting maize plants, such as Common Rust and Blight, are a significant production deterrent. To reduce waste and boost production and disease detection efficiencies, the automation of disease detection is a crucial strategy for the agricultural sector. The optimal solution is a self-diagnosing system that employs machine learning and computer vision to distinguish between damaged and healthy plants. The workflow for machine learning consists of data collection, data preprocessing, model selection, model training and testing, and evaluation.
Why it matches plant phenotyping methodsトウモロコシの病害状態を画像と機械学習で自動判別する方法が研究の中心であり、植物病害の表現型推定に該当する。
abstractemploys machine learning and computer vision to distinguish between damaged and healthy plants
TeaMultispectral / hyperspectralClassificationGrowth / development / phenology
Recognizing and identifying tea plant ( Camellia sinensis ) cultivar plays a significant role in tea planting and germplasm resource management, particularly for oolong tea. There is a wide range of high-quality oolong tea with diverse varieties of tea plants that are suitable for oolong tea production. The conventional method for identifying and confirming tea cultivars involves visual assessment. Machine learning and computer vision-based automatic classification methods offer efficient and non-invasive alternatives for rapid categorization. Despite advancements in technology, the identification and classification of tea cultivars still pose a complex challenge. This paper utilized machine learning approaches for classifying 18 oolong tea cultivars based on 27 multispectral characteristics. Then the SVM classification model was executed using three optimization algorithms, namely genetic algorithm (GA), particle swarm optimization (PSO), and grey wolf optimizer (GWO). The results revealed that the SVM model optimized by GWO achieved the best performance, with an average discrimination rate of 99.91%, 93.30% and 92.63% for the training set, test set and validation set, respectively. In addition, based on the multispectral information (h, s, r, b, L, Asm, Var, Hom, Dis, σ, S, G, RVI, DVI, VOG), the germination period of oolong tea cultivars can be completely evaluated by Fisher discriminant analysis. The study indicated that the practical protection of tea plants through automated and precise classification of oolong tea cultivars and germination periods is feasible by utilizing multispectral imaging system.
Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習を用いて茶品種および発芽期を自動分類する方法が研究の中心であり、発芽期という植物状態の推定を含むため、植物フェノタイピング手法として適格です。
abstractMachine learning and computer vision-based automatic classification methods offer efficient and non-invasive alternatives for rapid categorization.
Rice is one of the most widely consumed foods all over the world. Various diseases and deficiency disorders impact the rice crop's growth, thereby hampering the rice yield. Therefore, proper crop monitoring is very important for the early diagnosis of diseases or deficiency disorders. Diagnosis of diseases and disorders requires specialized manpower, which is not scalable and accessible to all farmers. To address this issue, machine learning and deep learning (DL)-driven automated systems are designed, which may help the farmers in diagnosing disease/deficiency disorders in crops so that proper care can be taken on time. Various studies have used transfer learning (TL) models in the recent past. In recent studies, further improvement in rice disease and deficiency disorder diagnosis system performance is achieved by performing the ensemble of various TL models. However, in all these DL-based studies, the segmentation of the region of interest is not done beforehand and the infected-region extraction is left for the DL model to handle automatically. Therefore, this article proposes a novel framework for the diagnosis of rice-infected leaves based on DL-based segmentation with bitwise logical AND operation and DL-based classification. The rice diseases covered in this study are bacterial leaf blight, brown spot, and leaf smut. The rice nutrient deficiencies like nitrogen (N), phosphorous (P), and potassium (K) were also included. The results of the experiment conducted on these datasets showed that the performance of DeepBatch was significantly improved as compared to the conventional technique.
Why it matches plant phenotyping methodsイネ葉の病害・栄養欠乏という植物状態を対象に、感染領域のセグメンテーションと分類を組み合わせた画像解析手法を開発・評価しており、表現型取得が中心である。
abstractthis article proposes a novel framework for the diagnosis of rice-infected leaves based on DL-based segmentation with bitwise logical AND operation and DL-based classification.
Reproduction assets foundThe paper's rice leaf disease and nutrient deficiency image datasets are publicly available on Kaggle, explicitly linked in the data availability statement. No author analysis code or trained models are publicly deposited (available only on request).Dataset · publicarma M; writing – review & editing: Kumar CJ, Talukdar J, Dhiman G, Singh TP, Sharma A.
Conflict of interest: Authors state no conflict of interest.
Data availability statement: The three different types of diseased rice leaf images that were utilized in this experiment are accessible at the following links provided as follows: https://www.kaggle.com/datasets/vbookshelf/rice-leafdiseases , https://www.kaggle.com/guy007/nutrientdeficiencysymptomsinrice . The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
Contributor Information
Mayuri Sharma, Email: mayurisarmah71@gmail.com.
Chandan Jyoti Kumar, Email: chanOpen asset ↗Kaggle · vbookshelf/rice-leafdiseaseslines:561-586Dataset · publicn G, Singh TP, Sharma A.
Conflict of interest: Authors state no conflict of interest.
Data availability statement: The three different types of diseased rice leaf images that were utilized in this experiment are accessible at the following links provided as follows: https://www.kaggle.com/datasets/vbookshelf/rice-leafdiseases , https://www.kaggle.com/guy007/nutrientdeficiencysymptomsinrice . The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
Contributor Information
Mayuri Sharma, Email: mayurisarmah71@gmail.com.
Chandan Jyoti Kumar, Email: chandan14944@gmail.com.
Jyotismita Talukdar, Email: jyoti4@tezu.ernOpen asset ↗Kaggle · guy007/nutrientdeficiencysymptomsinricelines:561-586Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Rice is the most important cereal food crop in the world, and half of the world's population uses rice as a staple food for its energy source. The yield production qualities and quantities are affected by biotic and abiotic factors namely viruses, soil fertility, bacteria, pests, and temperature. Rice plant disease is the most crucial factor behind communal, economic, and agricultural losses in the agricultural field. Farmers detect and identify diseases through the naked eye, which takes more time and resources, leading to crop loss and unhealthy farming. To overcome these issues, this paper presents a novel rice plant disease detection approach named the crossover boosted artificial hummingbird algorithm based AX-RetinaNet (CAHA-AXRNet) approach. This current research paper mainly concentrates on the effectiveness of rice plant disease detection and classification. The hyperparameters of the AX-RetinaNet model are optimized through the CAHA optimization model. In this paper, three types of disease detection datasets namely rice plant dataset, rice leaf dataset, and rice disease dataset are included to classify rice plants as healthy or unhealthy. The most essential performance metrics are precision, F1-score, accuracy, specificity, and recall, employed to validate the effectiveness of disease detection. The proposed CAHA-AXRNet approach demonstrates its effectiveness compared to other existing rice plant disease detection methods and achieved an accuracy rate of 98.1%.
Why it matches plant phenotyping methodsイネ葉・植物の病害状態を画像データから検出・分類する手法を開発し、複数データセットと性能指標で評価しており、植物フェノタイピング手法が研究の中心である。
abstractthis paper presents a novel rice plant disease detection approach named the crossover boosted artificial hummingbird algorithm based AX-RetinaNet (CAHA-AXRNet) approach.
Reproduction assets foundThe paper uses three public rice disease image datasets (Kaggle rice leaf, GitHub rice disease, Kaggle rice plant) as its phenotyping inputs; no author code or model release is stated (data availability is on-request only).Dataset · publicom the Indira
Gandhi Agricultural University, Raipur, Chhattisgarh,
India. The images were captured during the daytime
through Gionee, Canon Powershot SX530HS digital
camera and LYF mobile set. This image background
can reduce the computational cost as well as back-
ground complexity and this rice disease data are cho-
sen from https://github.com/aldrin233/RiceDiseases-DataSet. In the rice plant dataset, there are 5932
images are used to find the unhealthy and healthy
plants from the agricultural field. The most danger-
ous disease in the rice plant is rice blast fungal gen-
erated from the seed of the plant which affects the
entire plant of the field. This data was collected by
https://www.Open asset ↗github.com/aldrin233/RiceDiseases-DataSetpdf-raw-page:13 lines:1-100Dataset · public/RiceDiseases-DataSet. In the rice plant dataset, there are 5932
images are used to find the unhealthy and healthy
plants from the agricultural field. The most danger-
ous disease in the rice plant is rice blast fungal gen-
erated from the seed of the plant which affects the
entire plant of the field. This data was collected by
https://www.kaggle.com/datasets/rajkumar898/rice-plant-dataset. The sample images for each dataset are
delineated in Table 3.
Evaluation measures
The evaluation measures namely precision (RPprecision),
F1-score (RPF1−score), accuracy (RPaccuracy), recall
(RPrecall), specificity (RPspecificity), AUC/ROC and loss
are analyzed by using true positive values (RPTP), false
Open asset ↗kaggle.com/datasets/rajkumar898/rice-plant-datasetpdf-raw-page:13 lines:1-100Plant phenotyping relevance match · UnverifiedCrossref · checked 8 Sept 2026
Fruit is often bruised during picking, transportation, and packaging, which is an important post-harvest issue especially when dealing with fresh fruit. This paper is aimed at the early, automatic, and non-destructive ternary (three-class) detection and classification of bruises in kiwifruit based on local spatio-spectral near-infrared (NIR) hyperspectral (HSI) imaging. For this purpose, kiwifruit samples were hand-picked under two ripening stages, either one week (7 days) before optimal ripening (unripe) or at the optimal ripening time instant (ripe). A total of 408 kiwi fruit, i.e., 204 kiwifruits for the ripe stage and 204 kiwifruit for the unripe stage, were harvested. For each stage, three classes were considered (68 samples per class). First, 136 HSI images of all undamaged (healthy) fruit samples, under the two different ripening categories (either unripe or ripe) were acquired. Next, bruising was artificially induced on the 272 fruits under the impact of a metal ball to generate the corresponding bruised fruit HSI image samples. Then, the HSI images of all bruised fruit samples were captured either 8 (Bruised-1) or 16 h (Bruised-2) after the damage was produced, generating a grand total of 408 HSI kiwifruit imaging samples. Automatic 3D-convolutional neural network (3D-CNN) and 2D-CNN classifiers based on PreActResNet and GoogLeNet models were used to analyze the HSI input data. The results showed that the detection of bruising conditions in the case of the unripe fruit is a bit easier than that for its ripe counterpart. The correct classification rate (CCR) of 3D-CNN-PreActResNet and 3D-CNN-GoogLeNet for unripe fruit was 98% and 96%, respectively, over the test set. At the same time, the CCRs of 3D-CNN-PreActResNet and 3D-CNN-GoogLeNet for ripe fruit were both 86%, computed over the test set. On the other hand, the CCRs of 2D-CNN-PreActResNet and 2D-CNN-GoogLeNet for unripe fruit were 96 and 95%, while for ripe fruit, the CCRs were 91% and 98%, respectively, computed over the test set, implying that early detection of the bruising area on HSI imaging was consistently more accurate in the unripe fruit case as compared to its ripe counterpart, with an exception made for the 2D-CNN GoogLeNet classifier which showed opposite behavior.
Why it matches plant phenotyping methodsキウイフルーツの打撲状態という植物器官の状態を、ハイパースペクトル画像とCNNで非破壊・自動推定する方法が研究の中心であり、植物フェノタイピング手法に該当する。
abstractThis paper is aimed at the early, automatic, and non-destructive ternary (three-class) detection and classification of bruises in kiwifruit based on local spatio-spectral near-infrared (NIR) hyperspectral (HSI) imaging.
Introduction Accurate grading identification of tea buds is a prerequisite for automated tea-picking based on machine vision system. However, current target detection algorithms face challenges in detecting tea bud grades in complex backgrounds. In this paper, an improved YOLOv7 tea bud grading detection algorithm TBC-YOLOv7 is proposed. Methods The TBC-YOLOv7 algorithm incorporates the transformer architecture design in the natural language processing field, integrating the transformer module based on the contextual information in the feature map into the YOLOv7 algorithm, thereby facilitating self-attention learning and enhancing the connection of global feature information. To fuse feature information at different scales, the TBC-YOLOv7 algorithm employs a bidirectional feature pyramid network. In addition, coordinate attention is embedded into the critical positions of the network to suppress useless background details while paying more attention to the prominent features of tea buds. The SIOU loss function is applied as the bounding box loss function to improve the convergence speed of the network. Result The results of the experiments indicate that the TBC-YOLOv7 is effective in all grades of samples in the test set. Specifically, the model achieves a precision of 88.2% and 86.9%, with corresponding recall of 81% and 75.9%. The mean average precision of the model reaches 87.5%, 3.4% higher than the original YOLOv7, with average precision values of up to 90% for one bud with one leaf. Furthermore, the F1 score reaches 0.83. The model's performance outperforms the YOLOv7 model in terms of the number of parameters. Finally, the results of the model detection exhibit a high degree of correlation with the actual manual annotation results ( R2 =0.89), with the root mean square error of 1.54. Discussion The TBC-YOLOv7 model proposed in this paper exhibits superior performance in vision recognition, indicating that the improved YOLOv7 model fused with transformer-style module can achieve higher grading accuracy on densely growing tea buds, thereby enables the grade detection of tea buds in practical scenarios, providing solution and technical support for automated collection of tea buds and the judging of grades.
Why it matches plant phenotyping methods茶芽の等級を画像から検出・分類する改良YOLOv7手法を開発し、手動アノテーションとの相関や精度を検証しており、植物器官の状態・品質形質の取得が中心である。
abstractIn this paper, an improved YOLOv7 tea bud grading detection algorithm TBC-YOLOv7 is proposed.
The foundation of the global and Indian economies is agriculture. Since agriculture started millions of years ago, many environments, civilizations, and technical developments have fostered and defined the evolution of agricultural technology. In this study, we examine how we may analyze images of plants and soil to better keep tabs on their health, as well as how we can determine how much water each kind of plant needs. Images of the plants and soil are first taken using a digital camera with the necessary resolution. The form and geometric characteristics are extracted from the plant images using the inner distance shape context-based descriptor and geometrical descriptors. The soil images are also used to extract features and color properties. The botanical plant species dictionary is used to identify the plant type using the contour elements of the plant photos. Gradient structured random forest (GS-RF) classification is used to forecast leaf diseases. Principal Component Analysis (PCA) and Hierarchical Gradient Deep Neural Network (HG-DNN) classification techniques are used to determine the causes of a given plant disease based on the characteristics of soil images and plant disease images. The findings are communicated to the growers through text messages sent to their mobile phones on a daily and seasonal basis, along with any potential recommendations for preventative actions.
Why it matches plant phenotyping methods植物画像から葉の形状・幾何特性を抽出し、画像に基づく葉病害の分類・予測手法を開発しているため、植物状態の取得・推定が中心です。
abstractThe form and geometric characteristics are extracted from the plant images using the inner distance shape context-based descriptor and geometrical descriptors.
A large number of countries worldwide depend on the agriculture, as agriculture can assist in reducing poverty, raising the country’s income, and improving the food security. However, the plan diseases usually affect food crops and hence play a significant role in the annual yield and economic losses in the agricultural sector. In general, plant diseases have historically been identified by humans using their eyes, where this approach is often inexact, time-consuming, and exhausting. Recently, the employment of machine learning and deep learning approaches have significantly improved the classification and recognition accuracy for several applications. Despite the CNN models offer high accuracy for plant disease detection and classification, however, the limited available data for training the CNN model affects seriously the classification accuracy. Therefore, in this paper, we employed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets. In addition, we developed an efficient plant disease classification approach, where we adopt the CycleGAN architecture in order to enhance the classification accuracy. The obtained results showed an average enhancement of 7% in the classification accuracy.
Why it matches plant phenotyping methods植物病害画像を対象に、CycleGANによるデータ拡張・分類手法を開発し、分類精度を評価しているため、病害状態の画像ベース表現型推定が中心です。
abstractwe employed a Cycle Generative Adversarial Network (CycleGAN) to overcome the limitations of over-fitting and the limited size of the available datasets.
Reproduction assets foundThe paper uses the public DiaMOS pear leaf/fruit image dataset as its phenotyping input and explicitly states its availability on Zenodo. No author analysis code, trained models, or generated CycleGAN image dataset is reported as publicly deposited.Dataset · publicData availability: The dataset that has been used in this study is available
in https://zenodo.org/record/5557313.Open asset ↗zenodo · 5557313pdf-page:15 lines:1-40Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Abstract This study focuses on the remarkable progress made by the agricultural sector in utilizing image processing techniques for early detection and classification of leaf plant diseases. Timely identification of diseases is crucial, but it often poses a challenge for the human eye to discern subtle differences. To address this issue, the researchers propose a novel approach that employs EfficientNet, a deep learning model, to accurately recognize various diseases affecting tomato plant leaves. Transfer learning is applied to three different datasets comprising 3000, 8000, and 10,000 images of diseased tomato leaves. The experimental results demonstrate impressive overall accuracies of 97.3%, 99.2%, and 99.5% when using 3000, 8000, and 10,000 images, respectively, for the detection of common tomato plant diseases. This research underscores the effectiveness of image processing and deep learning techniques in achieving precise and efficient detection of tomato leaf diseases. It significantly contributes to the advancement of precision agriculture and enhanced crop management practices.
Why it matches plant phenotyping methodsトマト葉の病害状態を画像から認識・分類する深層学習手法が研究の中心であり、植物病害フェノタイピングに該当する。
abstractthe researchers propose a novel approach that employs EfficientNet, a deep learning model, to accurately recognize various diseases affecting tomato plant leaves
Automated disease inspection of greenhouse vegetables is less limited by the visibility of heavily infected leaves and more so by the reliable location of early lesions covering only a few dozen pixels. SE-YOLOv8 is a small-object-enhanced detector in this study that maintains a high-resolution P2 path, performs adaptive bidirectional cross-scale fusion, adds a lightweight coordinate attention module, and uses a scale-balanced localization objective. A greenhouse dataset with 12,480 images of tomato, cucumber, pepper and lettuce was divided into five disease categories plus a healthy background, and 31,762 annotated lesions were included. Under a fixed 640 × 640 input, the proposed model achieved 94.8% precision, 92.6% recall, 95.7% , and 72.4% . Relative to YOLOv8s, recall for lesions smaller than 32 × 32 pixels increased by 8.9 percentage points while parameters rose from 11.2 M to 12.7 M. The model sustained 48.6 frames/s on an NVIDIA Jetson Orin NX and reduced the expected calibration error from 6.8% to 3.9%. Ablation and robustness experiments show that the high-resolution branch contributes the most to the gain, and adaptive fusion and coordinate attention improve discrimination under glare, leaf overlap and clutter. Therefore, by maintaining fine spatial information and regulating cross-scale flow of information, early disease localisation can be achieved without reducing the throughput of practical greenhouses.
Why it matches plant phenotyping methods温室作物の病斑を画像から検出・位置推定する深層学習手法を開発し、比較、アブレーション、頑健性、速度、較正を評価しており、植物病害状態の表現型取得が中心である。
abstractSE-YOLOv8 is a small-object-enhanced detector in this study that maintains a high-resolution P2 path, performs adaptive bidirectional cross-scale fusion, adds a lightweight coordinate attention module, and uses a scale-balanced localization objective.
The rapid identification of plant stem diseases is crucial for implementing timely intervention and minimizing crop loss. While previous research has primarily focused on leaf-based disease detection, this paper proposes an automated stem disease detection and classification model using digital image processing and machine learning techniques. A dataset comprising 3789 images of diseased and healthy stems, categorized into five classes (stem rot, gummy blight, blackleg, didymella, and healthy), was split into training (80%) and testing (20%) sets. Our experiments were conducted on multiple platforms, including Google Colab, Jupyter Notebook, and OpenCV, and compared the performance of four classification techniques: Support Vector Machine (SVM), Random Forest, K-Nearest Neighbor (KNN), and Impact Learning. Various performance metrics, such as accuracy, precision, recall, and F1 score, were employed to evaluate the classifiers. Our findings reveal that SVM outperformed the other classifiers, achieving an average accuracy of 87%, followed by Random Forest (79%), KNN (75%), and Impact Learning (70%). This research offers valuable insights for farmers and the agricultural industry, paving the way for future studies exploring disease detection in other plant parts using similar techniques.
Why it matches plant phenotyping methods植物の茎を画像から観察し、病害状態を分類する画像処理・機械学習手法が研究の中心であり、性能比較と評価も実施しているため、植物フェノタイピング手法として含める。
abstractthis paper proposes an automated stem disease detection and classification model using digital image processing and machine learning techniques.
Abstract Background Quantitative, accurate, and high-throughput phenotyping of crop diseases is needed for breeding programs and plant-pathogen interaction investigations. However, difficulties in the transferability of available numerical tools encourage maintaining visual assessment of disease symptoms, although this is laborious, time-consuming, requires expertise, and rater dependent. Deep learning has produced interesting results for plant disease evaluation, but has not yet been used to quantify the severity of Septoria tritici blotch (STB) caused by Zymoseptoria tritici, a frequently occurring and damaging disease on wheat crops. Results We developed a Python-coded image analysis script, called SeptoSympto, in which deep learning models based on the U-net and YOLO architectures were used to quantify necrosis and pycnidia, respectively. Small datasets of different sizes (containing 50, 100, 200, and 300 leaves) were trained to create deep learning models and to facilitate the transferability of the tool, and five different datasets were tested to develop a robust tool for the accurate analysis of STB symptoms. The results revealed that (i) the amount of annotated data does not influence the good performance of the models, (ii) the outputs of SeptoSympto are highly correlated with those of the experts, with a similar magnitude to the correlations between experts, and that (iii) the accuracy of SeptoSympto allows precise and rapid quantification of necrosis and pycnidia on both durum and bread wheat leaves inoculated with different strains of the pathogen, scanned with different scanners and grown under different conditions. Conclusions Although running SeptoSympto takes longer than visual assessment to evaluate STB symptoms, it allows the data to be stored and evaluated by everyone in a more accurate and unbiased manner. Furthermore, the methods used in SeptoSympto were chosen to be not only powerful but also the most frugal, easy to use and adaptable. This study therefore demonstrates the potential of deep learning to assess complex plant disease symptoms such as STB.
Why it matches plant phenotyping methodsSeptoSymptoは小麦葉の壊死・ピクニディアを画像から定量する深層学習手法として開発・検証されており、植物病害表現型の取得が研究の中心です。
abstractWe developed a Python-coded image analysis script, called SeptoSympto, in which deep learning models based on the U-net and YOLO architectures were used to quantify necrosis and pycnidia, respectively.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicWe developed an image analysis script, named SeptoSympto ( https://github.com/maximereder/septo-sympto ), in which deep learning models based on the U-net and YOLO architectures were trained on small datasetsOpen asset ↗maximereder/septo-symptolines:61-99Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production, which benefits food production. Object detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating diseases. However, existing methods are still limited to single crop disease diagnosis. More importantly, the existing model has a large number of parameters, which is not conducive to deploying it to agricultural mobile devices. Nonetheless, reducing the number of model parameters tends to cause a decrease in model accuracy. To solve these problems, we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops. In detail, we design 2 strategies to build 4 different lightweight models as student models: the YOLOR-Light-v1, YOLOR-Light-v2, Mobile-YOLOR-v1, and Mobile-YOLOR-v2 models, and adopt the YOLOR model as the teacher model. We develop a multistage knowledge distillation method to improve lightweight model performance, achieving 60.4% mAP @ .5 in the PlantDoc dataset with small model parameters, outperforming existing methods. Overall, the multistage knowledge distillation technique can make the model lighter while maintaining high accuracy. Not only that, the technique can be extended to other tasks, such as image classification and image segmentation, to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart agriculture. Our code is available at https://github.com/QDH/MSKD.
Why it matches plant phenotyping methods植物病害を画像から検出・診断する軽量モデルと知識蒸留法を開発しており、植物の病害状態の推定が中心的な技術貢献である。
abstractwe propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops.
Reproduction assets foundThe authors explicitly state they released their code and data publicly on GitHub, which contains the MSKD multistage knowledge distillation implementation for plant disease detection.Code · publicWe released our code and data at https://github.com/QDH/MSKD .Open asset ↗QDH/MSKDlines:683-695Code / dataset availability confirmedOpenAlex · Europe PMC · checked 7 Sept 2026
KEY MESSAGE: Genotype-by-environment interactions of secondary traits based on high-throughput field phenotyping are less complex than those of target traits, allowing for a phenomic selection in unreplicated early generation trials. Traditionally, breeders' selection decisions in early generations are largely based on visual observations in the field. With the advent of affordable genome sequencing and high-throughput phenotyping technologies, enhancing breeders' ratings with such information became attractive. In this research, it is hypothesized that G[Formula: see text]E interactions of secondary traits (i.e., growth dynamics' traits) are less complex than those of related target traits (e.g., yield). Thus, phenomic selection (PS) may allow selecting for genotypes with beneficial response-pattern in a defined population of environments. A set of 45 winter wheat varieties was grown at 5 year-sites and analyzed with linear and factor-analytic (FA) mixed models to estimate G[Formula: see text]E interactions of secondary and target traits. The dynamic development of drone-derived plant height, leaf area and tiller density estimations was used to estimate the timing of key stages, quantities at defined time points and temperature dose-response curve parameters. Most of these secondary traits and grain protein content showed little G[Formula: see text]E interactions. In contrast, the modeling of G[Formula: see text]E for yield required a FA model with two factors. A trained PS model predicted overall yield performance, yield stability and grain protein content with correlations of 0.43, 0.30 and 0.34. While these accuracies are modest and do not outperform well-trained GS models, PS additionally provided insights into the physiological basis of target traits. An ideotype was identified that potentially avoids the negative pleiotropic effects between yield and protein content.
Why it matches plant phenotyping methodsドローン画像から植物高・葉面積・分げつ密度を推定し、これらを用いたフェノミック選抜モデルを評価しており、形質取得と解析ワークフローが研究の中心である。
abstractThe dynamic development of drone-derived plant height, leaf area and tiller density estimations was used to estimate the timing of key stages, quantities at defined time points and temperature dose-response curve parameters.
Reproduction assets foundThe paper's Data availability statement explicitly deposits the study's datasets (phenotypic/trait data from drone-based wheat phenotyping) in the ETH Research Collection and the phenomics data processing source code in a public ETH GitLab repository. Both are paper-specific, public, and actionable.Dataset · publicThe datasets generated and analyzed during the current study are openly available in the ETH Research Collection repository, http://doi.org/10.3929/ethz-b-000566864 .Open asset ↗ETH Research Collection · 10.3929/ethz-b-000566864lines:210-223Code · publicSource code for the phenomics data processing methods used in this study are openly available in the ETH gitlab repository, https://gitlab.ethz.ch/crop_phenotyping/htfp_data_processing .Open asset ↗ETH gitlab · crop_phenotyping/htfp_data_processinglines:210-223Plant phenotyping relevance match · UnverifiedEurope PMC · checked 7 Sept 2026
Corn leaf diseases lead to significant losses in agricultural production, posing challenges to global food security. Accurate and timely detection and diagnosis are crucial for implementing effective control measures. In this research, a multi-task deep learning-based system for enhanced precision detection and diagnosis of corn leaf diseases (MTDL-EPDCLD) is proposed to enhance the detection and diagnosis of corn leaf diseases, along with the development of a mobile application utilizing the Qt framework, which is a cross-platform software development framework. The system comprises Task 1 for rapid and accurate health status identification (RAHSI) and Task 2 for fine-grained disease classification with attention (FDCA). A shallow CNN-4 model with a spatial attention mechanism is developed for Task 1, achieving 98.73% accuracy in identifying healthy and diseased corn leaves. For Task 2, a customized MobileNetV3Large-Attention model is designed. It achieves a val_accuracy of 94.44%, and improvements of 4-8% in precision, recall, and F1 score from other mainstream deep learning models. Moreover, the model attains an area under the curve (AUC) of 0.9993, exhibiting an enhancement of 0.002-0.007 compared to other mainstream models. The MTDL-EPDCLD system provides an accurate and efficient tool for corn leaf disease detection and diagnosis, supporting informed decisions on disease management, increased crop yields, and improved food security. This research offers a promising solution for detecting and diagnosing corn leaf diseases, and its continued development and implementation may substantially impact agricultural practices and outcomes.
Why it matches plant phenotyping methodsトウモロコシ葉の健康状態・疾病を画像から検出および診断する深層学習手法とモバイルシステムを開発・評価しており、植物病害状態のフェノタイピングが中心である。
abstracta multi-task deep learning-based system for enhanced precision detection and diagnosis of corn leaf diseases (MTDL-EPDCLD) is proposed
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 15 Sept 2026
Soil salinity can impose substantial stress on plant growth and cause significant yield losses. Crop varieties tolerant to salinity stress are needed to sustain yields in saline soils. This requires effective genotyping and phenotyping of germplasm pools to identify novel genes and QTL conferring salt tolerance that can be utilised in crop breeding schemes. We investigated a globally diverse collection of 580 wheat accessions for their growth response to salinity using automated digital phenotyping performed under controlled environmental conditions. The results show that digitally collected plant traits, including digital shoot growth rate and digital senescence rate, can be used as proxy traits for selecting salinity-tolerant accessions. A haplotype-based genome-wide association study was conducted using 58,502 linkage disequilibrium-based haplotype blocks derived from 883,300 genome-wide SNPs and identified 95 QTL for salinity tolerance component traits, of which 54 were novel and 41 overlapped with previously reported QTL. Gene ontology analysis identified a suite of candidate genes for salinity tolerance, some of which are already known to play a role in stress tolerance in other plant species. This study identified wheat accessions that utilise different tolerance mechanisms and which can be used in future studies to investigate the genetic and genic basis of salinity tolerance. Our results suggest salinity tolerance has not arisen from or been bred into accessions from specific regions or groups. Rather, they suggest salinity tolerance is widespread, with small-effect genetic variants contributing to different levels of tolerance in diverse, locally adapted germplasm.
Why it matches plant phenotyping methods自動デジタルフェノタイピングによる生育速度・老化速度の抽出が塩耐性評価の主要な測定基盤であり、580系統への大規模適用を通じて植物形質を取得しているため。
abstractusing automated digital phenotyping performed under controlled environmental conditions
Oil palm is a high value crop with an estimated 5% yearly replanting rate. To dispatch high quality seeds, stringent culling upon the germinated seeds is necessary. The shape of germinated part of an oil palm seed is a key manual criterion for distinguishing good seeds from bad ones. Accurate segmentation of the germinated part would serve as an important preprocessing step for automatic phenotypic analysis and quality classification of germinated oil palm seeds. In this paper, we pioneer the study of semantic segmentation of germinated oil palm seeds by convolutional neural networks (CNNs). Leveraging the state-of-the-art ‘SE-ResNext + U-Net’ architecture for image segmentation, we propose two modifications to address the difficulty of accurately segmenting the germinated part of a seed since it is much smaller compared to the seed body. Firstly, we design local spatial channel attention (LS-SE) to replace the Squeez-Excitation (SE) module to retain local information of a feature channel. Then we pass the features generated by the encoder to the same level of the decoder part twice along the decoding direction (DC-UNet) to retain the original features. This helped address the problem where the edge segmentation details of oil palm seeds require higher-resolution detail information to improve the segmentation accuracy. In addition, the number of parameters of the proposed DC-UNet is much smaller than that of other state-of-the art U-Net variants such as Unet++, significantly reducing the training time. Our proposed DC-UNet with LS-SE obtained an MIOU that is 1.2% higher than U-Net, with a clearly better visual segmentation around the boundaries of the germinated parts.
Why it matches plant phenotyping methods発芽種子の発芽部位という植物器官形質を画像から抽出するセグメンテーション手法を開発・評価しており、フェノタイピング解析の前処理手法が中心である。
abstractAccurate segmentation of the germinated part would serve as an important preprocessing step for automatic phenotypic analysis and quality classification of germinated oil palm seeds.
Plant electrophysiology carries a strong potential for assessing the health of a plant. Current literature for the classification of plant electrophysiology generally comprises classical methods based on signal features that portray a simplification of the raw data and introduce a high computational cost. The Deep Learning (DL) techniques automatically learn the classification targets from the input data, overcoming the need for precalculated features. However, they are scarcely explored for identifying plant stress on electrophysiological recordings. This study applies DL techniques to the raw electrophysiological data from 16 tomato plants growing in typical production conditions to detect the presence of stress caused by a nitrogen deficiency. The proposed approach predicts the stressed state with an accuracy of around 88%, which could be increased to over 96% using a combination of the obtained prediction confidences. It outperforms the current state-of-the-art with over 8% higher accuracy and a potential for a direct application in production conditions. Moreover, the proposed approach demonstrates the ability to detect the presence of stress at its early stage. Overall, the presented findings suggest new means to automatize and improve agricultural practices with the aim of sustainability.
Why it matches plant phenotyping methods植物の電気生理データから窒素欠乏ストレス状態を深層学習で推定する手法の開発・性能比較が中心であり、植物の生理状態を直接対象とするため採用。
abstractThe Deep Learning (DL) techniques automatically learn the classification targets from the input data, overcoming the need for precalculated features.
Identifying potato leaf diseases at an early stage is a difficult task due to the variability in crop species, crop disease symptoms, and environmental factors. To overcome this challenge, machine learning techniques have been developed. However, current models are limited to specific regions and cannot detect diseases in various crop species. This research proposes a multi-level deep learning model to recognize potato leaf diseases. The model uses a unique convolutional neural network to detect early blight and late blight potato infections from leaf images after extracting potato leaves from plant images using ResNet50 image segmentation. The model is trained and tested using a potato leaf disease dataset, achieving 99.75 percent accuracy. Furthermore, it outperforms state-of-the-art models in terms of accuracy and computational cost.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定する深層学習モデルと葉抽出手法を開発・評価しており、植物病害フェノタイピングが中心である。
abstractThis research proposes a multi-level deep learning model to recognize potato leaf diseases.
Characterizing phenotypes is a fundamental aspect of biological sciences, although it can be challenging due to various factors. For instance, the liverwort ( Marchantia polymorpha ), a model system for plant biology, exhibits morphological variability, making it difficult to identify and quantify distinct phenotypic features using objective measures. To address this issue, we utilized a deep learning-based image classifier that can handle plant images directly without manual extraction of phenotypic features, and analyzed bright-field images of M. polymorpha . This dioicous plant species exhibits morphological differences between male and female wild accessions at an early stage of gemmaling growth, although it remains elusive whether the differences are attributable to sexual dimorphism or autosomal genetic variation. To dissect the genomic factors, we established a male and female set of recombinant inbred lines (RILs) from a set of male and female wild accessions. We then trained deep-learning models to classify the sexes of the RILs and the wild accessions. Our results showed that the trained classifiers accurately classified male and female gemmalings of wild accessions in the first week of growth, confirming the intuition of plant researchers in a reproducible and objective manner. In contrast, the RILs were less distinguishable, indicating that the differences between the parental wild accessions arose from autosomal variations instead of sexual dimorphism. Furthermore, we validated our trained models by an “explainable AI” technique that highlights image regions relevant to the classification. Our findings demonstrate that the classifier-based approach provides a powerful tool for analyzing plant species that lack standardized phenotyping metrics.
Why it matches plant phenotyping methods植物画像から性別・形態差を客観的に分類する深層学習手法の開発と検証が研究の中心であり、植物表現型解析手法として適格。
abstractwe utilized a deep learning-based image classifier that can handle plant images directly without manual extraction of phenotypic features
Plantain tree is the most popular crop grown all over the world and banana (Musa spp.) is the most marketable fruit. It is the leading food in many countries, especially in developing countries. Plant diseases are significant aspects that result in a serious reduction in the quantity and quality of fruit crops. Plantain tree cultivation is affected by various diseases such as Black Sigatoka/Yellow sigatoka, Panama, Bunchy top, Moko, chlorosis, etc. Rapid and novel approaches for the apt discovery of diseases help farmers in developing better decisions and efficient control measures. Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN) have been proved their efficiency in several fields and it has recently moved in the field of crop disease classification and detection. The objective of this research work is to create a Deep Learning Model for the disease classification and its early prediction to support farmers in plantain tree cultivation. A new sequential image classification model is proposed to detect the diseases by combining RNN and CNN, which is named as Gated-Recurrent Convolutional Neural Network (G-RecConNN). The input to the proposed model is the sequences of plant images. The experiments are carried out in real-time datasets collected from the state named Tamil Nadu situated in the Southern part of India. This method aims at numerous advantages such as reduced pre-processing of the data, easy online performance evaluation and advancements with less real data, etc. The experimental results inspired the utilization of the G-RecConNN model with farmer support systems that will process continuous banana tree images as part or whole for the early detection of banana tree diseases.
Why it matches plant phenotyping methodsバナナ葉・樹体画像から病害状態を推定する深層学習画像分類法の開発が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThe objective of this research work is to create a Deep Learning Model for the disease classification and its early prediction to support farmers in plantain tree cultivation.
Plant phenotyping is a central task in agriculture, as it describes plants' growth stage, development, and other relevant quantities. Robots can help automate this process by accurately estimating plant traits such as the number of leaves, leaf area, and the plant size. In this paper, we address the problem of joint semantic, plant instance, and leaf instance segmentation of crop fields from RGB data. We propose a single convolutional neural network that addresses the three tasks simultaneously, exploiting their underlying hierarchical structure. We introduce task-specific skip connections, which our experimental evaluation proves to be more beneficial than the usual schemes. We also propose a novel automatic post-processing, which explicitly addresses the problem of spatially close instances, common in the agricultural domain because of overlapping leaves. Our architecture simultaneously tackles these problems jointly in the agricultural context. Previous works either focus on plant or leaf segmentation, or do not optimise for semantic segmentation. Results show that our system has superior performance compared to state-of-the-art approaches, while having a reduced number of parameters and is operating at camera frame rate.
Why it matches plant phenotyping methods植物および葉のインスタンス分割手法を開発し、葉数・葉面積・植物サイズなどの形質推定に用いる中心的な画像解析研究である。
abstractWe propose a single convolutional neural network that addresses the three tasks simultaneously, exploiting their underlying hierarchical structure.