Accurate and efficient monitoring of tea plant growth parameters via remote sensing is essential for precision plantation management. However, spectral indices relying solely on reflectance often exhibit limited sensitivity in capturing complex tea canopy characteristics. This study developed a data-driven framework integrating spectral reflectance, frequency-domain harmonic components, and spatial texture features to construct tri-feature fusion indices (TFIs) and establish machine learning and deep learning models for tea growth monitoring. Ten-band multispectral imagery was acquired using a UAV alongside synchronous field measurements of leaf and plant biomass and nitrogen accumulation. TFIs were constructed through exhaustive feature combinations and optimized via a data-driven search strategy. Subsequently, random forest (RF), multilayer perceptron (MLP), convolutional neural network (CNN), and transformer models were evaluated using a leave-one-site-out cross-validation (LOSO-CV) strategy. The selected TFIs showed strong associations with tea growth parameters within the investigated dataset, with R2 values up to 0.63 and 0.62 for leaf dry matter and leaf nitrogen accumulation, respectively. Models incorporating selected TFIs achieved cross-validated R2 values of 0.56 for leaf dry matter (MLP), 0.59 for plant dry matter (MLP), 0.73 for leaf nitrogen accumulation (MLP), and 0.68 for plant nitrogen accumulation (CNN). These models exhibited competitive predictive performance comparable to RF, although no statistically significant differences in mean absolute error were observed under site-held-out evaluation. Furthermore, model-derived spatial maps provided insights into fine-scale spatial heterogeneity and potential interannual variations in tea growth parameters across representative plantations from 2024 to 2025. Overall, this study provides a UAV-based framework for tea growth parameter estimation by integrating multi-domain information without requiring additional environmental observations.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から茶植物の乾物量・窒素蓄積を推定する特徴量融合および機械学習・深層学習フレームワークを開発し、サイト外交差検証で評価しており、植物形質の取得・推定手法が中心である。
abstractThis study developed a data-driven framework integrating spectral reflectance, frequency-domain harmonic components, and spatial texture features to construct tri-feature fusion indices (TFIs) and establish machine learning and deep learning models for tea growth monitoring.
Image-based plant disease identification is essential for advancing smart agriculture, particularly for staple crops such as rice and economically significant crops such as tea, which are cultivated under complex environmental conditions. Furthermore, these crop groups present distinct challenges: rice leaf disease data typically exhibits clear pathological structures but necessitates large-scale deployment on resource-limited devices, whereas tea leaf disease data is complicated by variable lighting, diverse backgrounds, and high biodiversity. Although current deep learning models achieve high accuracy, they predominantly utilize deep convolutional neural network (CNN) architectures with millions of parameters, which hinders practical deployment on edge devices and increases the risk of overfitting when field data is scarce. In response, this study introduces DisQuan, a hybrid architecture that integrates classical deep learning with quantum machine learning (QML) to balance accuracy and resource efficiency. In particular, DisQuan combines the lightweight DisNet feature-extraction network with a variablequantum neural network to compress and refine feature representations in quantum space, yielding a model with only 0.09 million parameters. Experimental results on rice and tea leaf disease datasets indicate that DisQuan achieves the highest accuracy on the rice dataset and performance comparable to deep CNN models with significantly more parameters on the tea dataset, while maintaining a compact and stable structure. Overall, these findings suggest that DisQuan provides a practical compromise between performance and model complexity, and highlight the potential of quantum-classical hybrid architectures for plant disease detection in real-world agricultural settings and on resource-constrained devices.
Why it matches plant phenotyping methods植物葉の病害状態を画像から識別する量子・古典ハイブリッド手法を開発し、複数データセットで性能とモデル規模を評価しており、表現型取得・推定が中心である。
abstractExperimental results on rice and tea leaf disease datasets indicate that DisQuan achieves the highest accuracy on the rice dataset and performance comparable to deep CNN models with significantly more parameters on the tea dataset
Existing reviews on AI in tea production are either agriculture-generic or limited to isolated tasks. This review thoroughly compares vision technologies (RGB, hyperspectral, near-infrared, thermal, Light Detection and Ranging (LiDAR), Unmanned Aerial Vehicle (UAV)) and establishes a task-oriented algorithm selection framework for the tea industry. For small-sample or near-linear problems, traditional machine learning (ML) (support vector machine (SVM); partial least squares regression (PLSR)) remains effective. For unstructured field tasks, deep learning achieves superior performance: pest detection accuracy exceeds 97%, tea bud detection reaches 96.8% with RGB images, and hyperspectral imaging predicts nitrogen content with R 2 > 0.90 and tea polyphenols with R 2 up to 0.925. Algorithm choice further differentiates by task granularity: lightweight convolutional neural networks (CNNs) balance speed and accuracy for edge deployment at 16 fps; You Only Look Once (YOLO) series detectors enable real-time localization on mobile platforms at 93.1% accuracy, 24 ms per target. No single algorithm dominates all tea tasks; selection is a trade-off among accuracy, speed, data availability, and computational constraints. These findings outline a structured analysis of the challenges and pathways for transitioning computer vision (CV) from laboratory research toward field-deployable tools.
Why it matches plant phenotyping methods茶作物の画像センシング技術と解析アルゴリズムを体系的に比較し、害虫検出や窒素含量予測など植物状態・形質の推定方法を扱う方法論レビューである。
abstractThis review thoroughly compares vision technologies (RGB, hyperspectral, near-infrared, thermal, Light Detection and Ranging (LiDAR), Unmanned Aerial Vehicle (UAV)) and establishes a task-oriented algorithm selection framework for the tea industry.
Accurate field detection of candidate tea shoots could support plantation monitoring, yield estimation, fresh-leaf assessment, and future selective-harvesting research. Wuyi rock-tea shoots are small and slender, have weak visual boundaries, and are easily confused with branches, petioles, and complex canopy backgrounds. Here, we developed YOLO11s-CSNG for candidate shoot detection in natural plantation scenes. The model combines a channel-spatial feature enhancement bottleneck, a normalized Wasserstein distance constraint for bounding-box regression, and ghost convolution layers in the detection head. We evaluated the model through detector comparisons, module ablations, and repeated training with five matched random seeds on a natural-scene dataset containing four Wuyi rock-tea cultivars. Across the five matched seeds, the mean mAP@0.5 increased from 67.37 ± 0.91% to 67.97 ± 0.90% on the validation set and from 61.29 ± 0.40% to 61.88 ± 0.66% on the internal test set. Neither paired difference was statistically significant: The 95% confidence intervals included zero, and the exact two-sided paired-permutation p values were 0.375 and 0.250, respectively. The mean mAP@0.5:0.95 did not improve. YOLO11s-CSNG retained a model size and model-only edge-inference time comparable to YOLO11s, providing a compact design for candidate shoot-region detection under the sampled field conditions.
Why it matches plant phenotyping methods茶芽という植物器官の画像検出手法を開発し、比較・アブレーション・反復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。
abstractHere, we developed YOLO11s-CSNG for candidate shoot detection in natural plantation scenes.
Understanding the dynamic regulation of endogenous metabolites in plants under environmental stress is essential for elucidating plant adaptive mechanisms and improving crop resilience. However, conventional analytical methods are typically destructive, time-consuming, and lack the capability for real-time monitoring, thereby limiting the investigation of in-vivo biochemical dynamics in plants. In particular, the in-situ, non-invasive detection of small-molecule regulators such as protocatechuic acid (PCA) remains a significant challenge. Herein, we report a wearable electrochemical sensing platform based on a Cu/ZIF-8-modified flexible printed electrode (FPE) for real-time, in-situ monitoring of PCA in plant leaves. The incorporation of Cu into the ZIF-8 framework enhances the electrical conductivity and electrocatalytic activity of the material while maintaining its porous structure, enabling sensitive detection of PCA. By integrating with reverse iontophoresis (RI), non-invasive extraction and continuous monitoring of PCA from living plant tissues are achieved. The dynamic behavior of PCA in green tea plants under light deprivation and drought stress is systematically investigated. The results reveal distinct stress-dependent response patterns, with PCA levels rapidly decreasing under both dark and drought conditions, highlighting its critical role in stress adaptation and metabolic regulation. This work establishes a versatile strategy for real-time tracking of endogenous plant metabolites and provides new insights into plant physiological responses under environmental stress. The proposed platform holds significant promise for applications in plant science, precision agriculture, and the development of stress-resilient crops.
Why it matches plant phenotyping methods植物葉内代謝物をリアルタイム・非侵襲的に取得するウェアラブル電気化学センサーと抽出・連続モニタリング系の開発が中心であり、植物の生理状態を測定する方法として適格です。
abstractHerein, we report a wearable electrochemical sensing platform based on a Cu/ZIF-8-modified flexible printed electrode (FPE) for real-time, in-situ monitoring of PCA in plant leaves.
Accurate assessment of crop water status is critical for precision irrigation and sustainable water management in agriculture. This study develops a UAV-based thermal infrared inversion framework for high-resolution canopy temperature retrieval and irrigation decision support in tea plantations. The proposed approach integrates multi-frame image mosaicking, threshold-based canopy extraction, and a gray-temperature calibration model to generate spatially continuous canopy temperature maps. Crop water stress was quantified using the Crop Water Stress Index (CWSI), and its reliability was further evaluated by analyzing its relationship with stomatal conductance. The framework further estimates soil moisture status and irrigation requirements based on a threshold-based irrigation strategy. The results show that the linear gray-temperature calibration model achieved a maximum absolute error of less than 0.3 °C and that the calculated CWSI and estimated irrigation requirement were strongly correlated with measured stomatal conductance, with R 2 up to 0.91. The proposed method provides a practical technical workflow from UAV thermal imagery acquisition to canopy temperature retrieval and quantitative irrigation decision-making, demonstrating its potential for precision irrigation management in tea plantations.
Why it matches plant phenotyping methodsUAV熱画像から茶園の樹冠温度と水ストレスを推定する取得・抽出・較正手法を開発し、気孔コンダクタンスとの関係で検証しており、植物状態の計測が中心である。
abstractThis study develops a UAV-based thermal infrared inversion framework for high-resolution canopy temperature retrieval and irrigation decision support in tea plantations.
Introduction The precise detection of microscopic tea leaf diseases is a prerequisite for sustainable precision agriculture. While recent deep learning advancements often favor architectural complexity, this "complexity bias" frequently introduces computational redundancy-a "complexity tax"-that destabilizes gradient flow and fails to resolve critical resolution bottlenecks for micro-lesion identification. Methods We propose Opti-YOLOv11n, a minimalist optimization paradigm prioritizing physical input fidelity and stabilized gradient dynamics. Utilizing a dataset of six pathological categories, our framework employs high-resolution scaling (832×832) combined with a momentum-based SGD optimizer and a cosine annealing schedule to reconstruct essential spatial textures. Results Opti-YOLOv11n achieved a peak Precision of 98.87% and a Recall of 95.97%, while reducing the parameter count to 2.35 M-a 9.2% decrease relative to the baseline-and maintaining a real-time inference speed of 104.7 FPS on edge-simulated hardware. Discussion Statistical verification via 5-fold cross-validation confirms superior generalization stability. These results substantiate that strategic structural pruning and physical input scaling provide a more robust technical benchmark for autonomous plant protection than the adoption of excessive architectural depth.
Why it matches plant phenotyping methods茶葉病害の微小病斑を画像から検出する深層学習手法を開発し、精度・計算量・推論速度・交差検証で技術評価しているため、植物病害フェノタイピング手法が中心である。
abstractWe propose Opti-YOLOv11n, a minimalist optimization paradigm prioritizing physical input fidelity and stabilized gradient dynamics.
The simultaneous diagnosis of diseases and evaluation of age quality grades in tea leaves are critical for precision agriculture and the economic valuation of tea products. Although deep learning has shown promise in agricultural vision tasks, current multi-task models often suffer from performance degradation due to feature conflicts: tea leaf disease recognition relies heavily on macro-structural lesions, whereas tea leaf-age quality grading depends on micro-textural features such as trichome density and color uniformity. To address this discrepancy, we propose a novel dual branch fusion network. Our architecture fundamentally decouples the feature extraction process by utilizing a dual branch mechanism. The first branch employs global average pooling to capture first-order spatial statistics; it can retain the global structural layout necessary for macro-lesion detection. The second branch introduces a dimensionality-reduced self-bilinear pooling module to compute second-order covariance matrices; it can effectively capture the fine-grained textural patterns essential for micro-grade classification. These decoupled features are subsequently fused and optimized through a weighted multi-task loss function. Experimental results on a comprehensive tea leaf dataset demonstrate that the proposed dual fusion framework significantly outperforms baseline models. The proposed network can rescue the disease classification accuracy drop observed in standard bilinear models while maintaining exceptional grading performance. Furthermore, the proposed network maintains a compact parameter footprint and low computational complexity. This balance renders it suitable for deployment on agricultural Internet of Things edge devices where inference speed is critical.
Why it matches plant phenotyping methods茶葉の病害状態と葉齢品質を画像から推定する深層学習手法を開発し、データセット上でベースラインと比較評価しており、表現型取得・推定法が中心である。
abstractwe propose a novel dual branch fusion network
Reproduction assets foundThe paper's Data Availability Statement publicly releases the two tea leaf image datasets used for its phenotyping tasks (disease recognition and leaf-age quality grading) via Mendeley Data. The authors' analysis code and trained models are only promised 'upon acceptance' with no public URL, so they do not qualify.Dataset · publicThe tea leaf disease recognition dataset analyzed in this study is available from https://data.mendeley.com/datasets/744vznw5k2/3 (accessed on 11 February 2026)Open asset ↗744vznw5k2/3lines:514-565Dataset · publicthe tea leaf grading dataset is available from https://data.mendeley.com/datasets/7t964jmmy3/1 (accessed on 11 February 2026)Open asset ↗7t964jmmy3/1lines:514-565Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Reliable traits are needed for identification of tea ( Camellia sinensis ) cultivars, yet the stability of leaf morphology and color across leaf positions remains unclear. This study evaluated inter-cultivar variation and positional stability in leaf morphological, RGB color, and SPAD traits in six predominant cultivars. One-year-old shoots were sampled in a completely randomized design, and five fully expanded leaves below the apical bud were analyzed. SPAD values were measured with a chlorophyll meter, and scanned images were used to extract contour and RGB traits. Data were analyzed using ANOVA, correlation analysis, PCA, and discriminant analysis. Leaf morphology differed among cultivars and leaf positions, with significant cultivar-by-position interactions; however, the width-to-length ratio differed among cultivars but remained stable across positions in these cultivars. SPAD values increased with leaf position and were strongly associated with RGB components, being negatively correlated with R and G and positively correlated with B. Morphological traits explained 52.988% of total variance in PCA and yielded 64.6% overall classification accuracy, with LaoHan showing the highest accuracy (83.3%). Misclassification was concentrated among genetically similar cultivars. These findings suggest that stable leaf shape proportions and SPAD-RGB relationships provide useful descriptors, whereas genetic relatedness limits morphology-based cultivar identification under the present conditions.
Why it matches plant phenotyping methods茶品種識別のため、葉の形態・RGB・SPAD特性の取得と安定性、分類性能を中心に評価しており、画像由来形質抽出を含む実質的な表現型解析である。
abstractscanned images were used to extract contour and RGB traits
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 following supporting information can be downloaded at https://www.mdpi.com/article/10.3390/biology15151283/s1 , Table S1: Original data of leaf morphological traits, RGB values, and SPAD values from six tea cultivars in this study.Open asset ↗lines:368-409Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
The intelligent identification of tea diseases is crucial for ensuring tea quality and reducing economic losses in the tea industry. However, the deployment of deep learning models on edge devices remains challenging due to the conflict between detection accuracy and computational overhead. To address this, we propose CA-YOLOv8n, a lightweight object detection model tailored for tea disease diagnosis. Specifically, we introduce a Path-Decoupling strategy to streamline the network structure and integrate the Coordinate Attention (CA) mechanism to enhance the model's spatial awareness of subtle pathological features. Experimental results demonstrate that the proposed model achieves a mean Average Precision (mAP@50) of 98.89% while reducing the parameter count by 32.6% and FLOPs by 24.1% compared to the baseline YOLOv8n. The model was integrated into a diagnostic platform with an automated reporting interface, demonstrating that real-time tea disease identification is feasible on commodity CPU hardware in resource-constrained agricultural environments.
Why it matches plant phenotyping methods茶葉の病害を画像から検出する軽量深層学習モデルを開発・評価し、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。
titleSpatial-aware lightweight network for real-time tea disease detection: A coordinate attention-enhanced YOLOv8n approach with path-decoupling strategy.
Reproduction assets foundThe paper's tea-leaf disease image dataset (9,591 images, YOLO format) is publicly deposited on figshare under CC BY 4.0, as stated in the Data Availability statement and dataset description. No author analysis code or trained model checkpoints are explicitly deposited.Dataset · publicAll data underlying the findings of this study are publicly available on figshare at https://doi.org/10.6084/m9.figshare.32253357 (CC BY 4.0).Open asset ↗figshare · 10.6084/m9.figshare.32253357lines:1-122Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Jul 2026Microscopy and microanalysis : the official journal of Microscopy Society of America, Microbeam Analysis Society, Microscopical Society of CanadaCited by 0 · OpenAlex ↗
Fuzhou represents a critical center for tea genetic diversity, yet the micromorphological basis for differentiating its local landraces remains poorly understood. Scanning electron microscopy (SEM) was employed to investigate the foliar micromorphology of 28 tea landraces from Fuzhou and to characterize structural differences among them. Adaxial epidermal wax ornamentation, stomatal architecture, and nonglandular trichome patterns provided important taxonomic characters for germplasm classification. Our analysis reveals that stomata are consistently paracytic and randomly oriented on the abaxial surface. However, their dimensions exhibit high phenotypic plasticity, with mean areas ranging from 421.92 to 822.26 µm2. Leaf surface ornamentation showed high phenotypic variability, with three identifiable types: straight, wrinkled, and undulated. The length, width, and type of nonglandular trichomes varied among the landraces, with values of nonglandular trichome length ranging from 269.99 to 632.31 µm and diameter from 9.72 to 14.62 μm. The nonglandular trichome ornamentation was categorized as smooth, long-stripe, and short-stick. The study demonstrated that SEM-based analysis of foliar micromorphological traits provides a valuable tool for tea germplasm identification and cultivar improvement. Specifically, the combination of adaxial epidermal wax ornamentation and nonglandular trichome surface ornamentation provides stable and reliable diagnostic micromorphological markers for accurate differentiation and identification of Fuzhou tea landraces, filling a critical micromorphological gap in the systematic study of local tea germplasm.
Why it matches plant phenotyping methodsSEM画像に基づく葉の微細形態形質の取得・分類を中心に、茶遺伝資源の識別へ応用しており、単なる生物学的測定ではなく植物フェノタイピング手法として中心的です。
abstractScanning electron microscopy (SEM) was employed to investigate the foliar micromorphology of 28 tea landraces from Fuzhou and to characterize structural differences among them.
Abstract To address the challenges of high computational cost and strong background interference in automatic recognition of tea pests and diseases in complex tea garden scenarios, this paper proposes a detection method named MSDR-Net (Multi-Scale Dynamic Routing Network). First, to significantly reduce the model parameter count and computational complexity, a lightweight backbone is constructed using depthwise separable convolutions. Second, a parallel multi-scale feature extraction structure is designed to capture both the contours and details of small pests and large disease spots through differentiated branches. Finally, to suppress background interference and improve feature fusion efficiency, a SimpleRouter dynamic routing mechanism is introduced to enable adaptive filtering and weighted fusion of key features. Experimental results on a self-built real-world tea pest and disease dataset show that the model achieves a mean average precision (mAP@0.5) of 98.0\%, which is 0.3 percentage points higher than the baseline model YOLOv8n. Meanwhile, the parameter count, computational complexity, and model size are reduced to 1.89M, 7.0 GFLOPs, and 3.91 MB, representing reductions of 37.1\%, 13.6\%, and 34.6\%, respectively, compared to the baseline model. Furthermore, an intelligent monitoring system developed based on this model verifies its effectiveness and usability in practical applications.
Why it matches plant phenotyping methods茶の病害スポットを画像から検出するモデルを開発・評価しており、植物の病害状態の取得が中心的な技術貢献です。害虫検出も含みますが、病害スポット検出と実運用システムの検証があるため対象に含めます。
abstractthis paper proposes a detection method named MSDR-Net (Multi-Scale Dynamic Routing Network).
Introduction Traditional tea disease detection methods suffer from low efficiency and strong subjectivity, while existing deep learning approaches often demonstrate inadequate detection accuracy and poor real-time performance in complex and variable environments. Methods Here, we present an intelligent tea disease detection method based on an improved Real-Time Detection Transformer, named DSA-DET. We propose a backbone network based on dynamic attention spatial pyramid modeling to achieve more accurate collaborative modeling of local features and global context. We design an encoder combining polarized linear attention with parallel spatial enhancement networks and multi-scale adaptive enhancement to improve feature extraction capabilities. We further develop an upsampling module employing efficient spatial-channel upsampling and shift mixing mechanisms to enhance the quality of reconstructed features. Results Experimental results show that the improved model achieves a precision of 94.73%, a recall of 89.65%, and an mAP 50 of 93.68%. Compared to the baseline model RT-DETR-R18, its precision is improved by 3.56%, recall by 2.96%, and mAP 50 by 3.02%; meanwhile, the model maintains a lightweight parameter scale of 15.4M and a real-time detection speed of 71.5 FPS. Discussion The improvement scheme in this study successfully enhances detection accuracy while maintaining a good balance between model complexity and inference speed, providing a practical and reliable technical solution for the intelligent diagnosis of tea diseases.
Why it matches plant phenotyping methods茶葉の病害状態を画像等から検出する深層学習手法を開発し、精度・再現速度を比較検証しており、植物病害表現型の取得手法が中心である。
abstractHere, we present an intelligent tea disease detection method based on an improved Real-Time Detection Transformer, named DSA-DET.
Tea (Camellia sinensis) is the world's second most consumed beverage, enjoyed daily by more than two billion people. In Bangladesh, it serves as a cornerstone agricultural export and a major sector of the domestic economy. However, commercial tea cultivation remains highly vulnerable to fungal and pest-related diseases such as Blight, Red Rust, and Helopeltis which severely reduce crop yield and compromise leaf quality. While early detection is critical to preventing widespread outbreaks, traditional manual inspection is slow, subjective, and highly error-prone. Deep learning provides a scalable alternative, yet single-branch networks often struggle to capture both minute disease lesions and broader structural degradation simultaneously. To address this, we propose a Hybrid Feature Fusion architecture that runs two highly efficient feature extractors in parallel: EfficientNetV2-Small to isolate fine-grained local textures, and MobileNetV3-Small to capture the global structural context of the leaf. The models were trained and evaluated on a real-world dataset of 2,000 annotated images, evenly distributed across the four target classes (Blight, Red Rust, Helopeltis, and Healthy). Before training, the images underwent a standardized preprocessing pipeline including resizing to 224 × 224 pixels and normalization, supplemented by a dynamic augmentation strategy featuring random rotations, horizontal flips, and brightness adjustments to improve model robustness. The proposed hybrid framework achieved an outstanding peak classification accuracy of 96.80% alongside a macro Area Under the Curve (AUC) of 0.9980. To rigorously validate its performance, the hybrid model was benchmarked against six diverse architectures: a Vision Transformer (ViT-B16 at 76.40%), a Custom CNN (89.60%), MobileNetV3 (94.40%), ResNet50 (95.60%), DenseNet121 (96.40%), and EfficientNetV2-B3 (97.60%). Although EfficientNetV2-B3 achieved a marginally higher raw accuracy, the proposed dual-branch framework delivered a superior precision-recall balance and faster convergence stability. These findings demonstrate that the proposed hybrid methodology is highly reliable and computationally balanced, making it an ideal candidate for integration into Internet of Things (IoT) edge devices for real-time disease monitoring in precision agriculture.
Why it matches plant phenotyping methods茶葉の病徴を画像から分類する深層学習手法の開発と、注釈付きデータセットおよび複数モデルとのベンチマーク検証が中心であり、植物病害状態の表現型推定に該当する。
abstractwe propose a Hybrid Feature Fusion architecture
Reproduction assets foundThe paper's Data Availability statement explicitly deposits the curated 2000-image tea leaf dataset on Mendeley Data and the analysis code on GitHub, both with public URLs matching allowed_urls.Dataset · publicThe dataset comprising 2000 annotated tea leaf images was curated under real-world field conditions. It has been made available at https://data.mendeley.com/datasets/3x42rbj8yv/1.Open asset ↗3x42rbj8yv/1html-lines:465-480Code · publicThe computational code supporting the findings of this study is publicly accessible on GitHub: https://github.com/rayhankhan2192/Tea_Leaf_Disease_Model.Open asset ↗GitHub · rayhankhan2192/Tea_Leaf_Disease_Modelhtml-lines:465-480Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Background Accurate identification of visible disease symptoms is essential for the sustainable management of tea ( Camellia sinensis ) cultivation. However, balancing high diagnostic accuracy with the computational efficiency required for deployment on agricultural edge devices remains a significant challenge. Methods We propose GL-MobFormer, a lightweight hybrid deep learning framework. This architecture integrates the local feature extraction capabilities of MobileNetV3 with the global contextual modeling of a Transformer Encoder. To improve model robustness in unstructured field environments, we applied the CutMix data augmentation strategy. The framework was evaluated on a dataset comprising 5,278 tea leaf images across seven phytosanitary categories. Results Empirical evaluations demonstrate that GL-MobFormer achieved a classification accuracy of 95.13% and a Matthews Correlation Coefficient (MCC) of 0.9417. Crucially, this performance was maintained with a low computational footprint of merely 0.33 G FLOPs(Floating Point Operations). Importantly, an occlusion-based sensitivity protocol was implemented to provide quantitative grounding for model interpretability. Results revealed that systematically masking only the top 5% of critical activation regions led to an average reduction of 70.61% in classification confidence, empirically confirming that the model's diagnostic logic is faithfully anchored on pathologically relevant lesion features rather than background noise. Conclusion GL-MobFormer achieves an optimal trade-off between diagnostic precision and computational overhead. It provides a practical and highly efficient solution for on-site, real-time phytosanitary monitoring in precision agriculture.
Why it matches plant phenotyping methods茶葉の病斑画像から病害状態を推定する軽量CNN・Transformer手法を開発し、精度・計算量・解釈性を評価しており、植物フェノタイピング手法が中心です。
abstractWe propose GL-MobFormer, a lightweight hybrid deep learning framework.
Plant disease is a serious threat to agricultural productivity and food security worldwide. Traditional diagnostic methods such as manual observation and laboratory testing are time-consuming, labor-intensive and error prone. The emergence of artificial intelligence (AI) and deep learning (DL) offer scalable solutions for precision agriculture in plant disease detection using advanced computational techniques to process large datasets. Hybrid deep learning architecture integrates Convolutional Neural Networks (CNNs) along with Artificial Neural Networks (ANNs) can leverage both visual and contextual data to improve detection performance. The hybrid CNN-ANN model was developed to analyze visual data (plant images) and contextual data (environmental and soil metrics). The CNN module extracted spatial and textural features from plant images, while the ANN module processed environmental parameters. These outputs were fused into a unified feature vector for disease classification. A total of 15 plant species and their associated diseases were analyzed using 200-270 training samples and 150-190 testing samples for each disease across a total of 1000 images. The model was judged by metrics such as detection accuracy, AUC, sensitivity etc. Data augmentation, pre-trained architectures (e.g., ResNet50) and early stopping techniques were utilized to improvise model performance. The hybrid model saliently achieved detection accuracy consistently above 87% with majority of diseases surpassing 90%. Highperforming cases like Rice Blast (92.5%), Tomato Early Blight (93.8%), and Coffee Rust (93.0%), with AUC values of 0.93 or higher, sensitivity exceeding 94% and specifically above 90%. Diseases of Sugarcane Red Rot and Tea Blister Blight exhibited sensitivities of 92.4% and 92.1% and specificities of 91.1% and 90.5% respectively. Moderate accuracy for Coconut Bud Rot (87.5%) and Mustard Alternaria Blight (87.8%) was due to smaller training sample sizes.
Why it matches plant phenotyping methods植物画像から病害状態を分類するハイブリッドCNN-ANN手法を開発し、精度・AUC・感度などで評価しており、病害フェノタイピング手法が研究の中心である。
abstractThe hybrid CNN-ANN model was developed to analyze visual data (plant images) and contextual data (environmental and soil metrics).
Reproduction assets foundThe paper's plant disease detection model was trained on public plant image datasets: the PlantSeg dataset (Zenodo record 13958858, DOI 10.5281/zenodo.13293891) and the UCI Machine Learning Repository Plants dataset. Both are cited in Materials and Methods as sources of the visual data used for the CNN module. No code,Dataset · publicebao (ZiranKexueBan)/Journal of
Huazhong University of Science and Technology
(Natural Science Edition). 2021;49(8).
37. Ma C, Mu X, Sha D. Multi-Layers Feature Fusion of
Convolutional Neural Network for Scene
Classification of Remote Sensing. IEEE Access.
2019;7.
38. Hämäläinen W.Plants Dataset[Internet]. 2024.
Available from:
https://archive.ics.uci.edu/dataset/180/plants
39. WeiT. PlantSeg: A Large-Scale In-the-wild Dataset
for Plant Disease Segmentation [Internet]. 2018.
Available from: https://zenodo.org/records/13958858Open asset ↗180pdf-raw-page:15 lines:1-48Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Tea diseases, including brown and gray blight, result in significant yield and quality losses, especially in Longjing tea production. Traditional detection methods are prone to errors, while existing deep learning models often struggle to be robust under natural field conditions. To address these challenges, an improved lightweight detection model, asymmetric multi-level (AML) mechanism, dynamic snake convolution (DSC), and scalable intersection over union (SIoU) loss function-You Only Look Once (YOLO) (ADS-YOLO), was developed and validated. In the method, a dataset comprising 5694 smartphone-captured images of tea leaves was established under natural lighting. Enhancements were implemented in the YOLO11n baseline algorithm through incorporation of the SIoU loss function for better bounding box regression, DSC, which realizes adaptive feature extraction based on the dynamic spatial context, and an AML mechanism, which achieves lightweight feature fusion via adaptive multi-scale design. The results showed that ADS-YOLO achieved a precision of 0.935 and a recall of 0.870, compared to 0.894 and 0.818, respectively, when the baseline YOLO11n was used. Importantly, ADS-YOLO demonstrated a real-time performance of 137.1 frames per second (FPS), coupled with reduced computational costs. ADS-YOLO improved the mean average precision (mAP) at intersection over union threshold of 0.5 (mAP@0.5) by 6.4% compared with YOLOv5n and achieved up to 44.6% higher accuracy than YOLOv7t. In conclusion, ADS-YOLO achieved high accuracy, providing a scalable solution for real-time crop health monitoring and sustainable precision agriculture for tea production.
Why it matches plant phenotyping methods茶葉の病害症状を画像から検出する深層学習手法を開発・検証しており、植物の病害状態の取得が研究の中心である。
abstractan improved lightweight detection model, asymmetric multi-level (AML) mechanism, dynamic snake convolution (DSC), and scalable intersection over union (SIoU) loss function-You Only Look Once (YOLO) (ADS-YOLO), was developed and validated.
Abstract—The growing incidence of plant diseases in the cultivation of tea plants is considered to be an alarming threat to agricultural productivity and economic viability. The early and precise detection of plant diseases is considered to be vital in order to avoid crop damage and ensure quality crop production. However, the traditional method of manual inspection is considered to be time-consuming, subjective, and less reliable, especially in the case of large-scale farming. Keeping this in mind, the current work proposes an ensemble deep learning model using an AI-based approach for the automated detection of tea leaf diseases through image analysis. The proposed model uses multiple CNN models, namely CNN, VGG, and DenseNet, to extract distinct features from the images of the leaves. The predictions are combined using the ensemble method. The system utilizes preprocessing techniques like normalization and data augmentation to enhance generalization under different environmental conditions. The experimental results show that the proposed ensemble model has better accuracy than individual models, and the overall accuracy of the proposed model is 81.3%. In addition, it is further incorporated with a user-friendly interface for real-time disease prediction. The results show the effectiveness of different deep learning models using fusion techniques for intelligent agricultural disease management systems. Index Terms—Plant Disease Detection, Tea Leaf Classification, Ensemble Learning, Deep Learning, Image Analysis and Precision Agriculture.
Why it matches plant phenotyping methods茶葉画像から病害状態を推定する画像解析モデルを開発し、複数CNNとの精度比較・評価を行っており、植物病害表現型の取得手法が中心である。
abstractthe current work proposes an ensemble deep learning model using an AI-based approach for the automated detection of tea leaf diseases through image analysis.
Leaf Area Index (LAI) is a fundamental parameter for characterizing the growth of tea ( Camellia sinensis L.). However, in rugged mountainous regions, the combined effects of topographic relief and canopy structural heterogeneity severely constrain the accuracy of UAV-based multispectral LAI retrieval. This study develops an integrated framework combining topographic correction with interpretable machine learning to improve LAI estimation. We utilized a UAV multispectral dataset collected during the peak growing season from a typical tea-growing region in Fujian Province, China (altitude range: 58-186 m), comprising a total of 90 samples. Three topographic correction methods, including Sun-Canopy-Sensor (SCS), SCS with C correction (SCS+C), and Minnaert+SCS, were evaluated in combination with Linear Regression (LR), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models. Results indicated that the SCS+C algorithm outperformed other methods by effectively accounting for direct and diffuse radiation components, thereby reducing topographic dependence while maintaining radiometric consistency across heterogeneous surfaces. The XGBoost model combined with SCS+C correction achieved the highest performance (R 2 = 0.8930, RMSE = 0.6676, nRMSE = 7.93%, MAE = 0.4936, Bias = -0.0836). SHapley Additive exPlanations (SHAP) analysis revealed a structure-dominated retrieval mechanism, in which red-band textural features (Correlation_R) exhibited higher importance than conventional vegetation indices. Compared with previous studies that primarily focus on either topographic correction or model development, this study provides quantitative insights into the underlying retrieval mechanisms. This framework improves the precision of tea LAI retrieval in complex terrains and provides a robust methodological basis for digital management in mountainous agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像と地形補正・機械学習を用いた茶園LAI推定手法の開発および比較検証が研究の中心であり、植物形態特性を直接推定している。
abstractThis study develops an integrated framework combining topographic correction with interpretable machine learning to improve LAI estimation.
Leaf morphology in tea plants (Camellia sinensis L.) profoundly influences tea quality and agronomic value, yet its genetic basis remains elusive due to labor-intensive phenotyping, foliage architecture, and ecological sensitivity of traits. Moreover, traditional methods forfeit quantitative color gradients and population-level morphological complexity. To address this challenge, we developed coleaf, an open-source image recognition-based software that demonstrated 97.6% accuracy over conventional ImageJ measurements, while offering higher efficiency and color hues quantification. We then estimated 7 key morphological traits focusing on leaves from a collection of ~ 4,200 mature leaves and ~ 5,000 bud-leaf samples across 167 genetically diverse tea accessions by coleaf. While classical understanding suggests leaf shape differentiation between two varieties in genus sinensis assamica (CSA) and sinensis (CSS), our phenotypic clustering revealed incomplete congruence with phylogenetic relationships, suggesting the presence of additional genetic or environmental modulators beyond population divergence. Furthermore, we integrated phenotypic data with whole-genome resequencing for multi-model genome-wide association studies (GWAS). Candidate genes associated with leaf architecture were involved in plant development (e.g., CsFAS2), cell division and elongation (e.g., CsFIP1), and cellular morphogenesis (e.g., CsRLK), whereas those associated with leaf color, regulated pigment accumulation (e.g., ABC transporters, CsMYB113). In conclusion, this study establishes a standardized computational framework validating automated image recognition for plant leaf phenomics. The end-to-end framework from high-throughput phenotyping to gene discovery provides critical genetic targets for tea breeding, demonstrating transformative potential in accelerating the genetic improvement of tea plants.
Why it matches plant phenotyping methods茶葉形態の画像認識ソフトウェアを開発・検証し、高スループットな形質抽出フレームワークとして適用しており、植物フェノタイピング手法が研究の中心である。
abstractwe developed coleaf, an open-source image recognition-based software that demonstrated 97.6% accuracy over conventional ImageJ measurements
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 · publicAll codes and tools used in this study are described in Methods, coleaf is available on github (https://github.com/mengmeng-jiang/coleaf).Open asset ↗mengmeng-jiang/coleafhtml-lines:390-460Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Background: A major challenge to agricultural productivity in the tea industry is disease. that affects the quantity and quality of tea leaves produced. The extensive development of computational methods for treating diseases has been widely used due to fast and accurate detection. Methods: The proposed method uses sequential Convolutional Neural Network (CNN) computations with many hidden layers to classify diseased and healthy tea leaves into multiple groups. By enhancing feature identification, this structure increases the criteria for accurate disease detection. The data having 5 diseased and one healthy category is obtained from the Kaggle database. After preprocessing the data, it is split into 80:20 ratios for training and testing steps. CNN is constructed using the Keras Sequential API in Jupiter notebook using Anaconda environment. Result: The total accuracy of the ML neural network training for classification was 98.52%. After 50 epochs of training, the model performed well, achieving high accuracy on training and validation datasets. The examination of the confusion matrix showed that several tea leaf diseases may be identified with high accuracy and few misclassifications. In general, the model demonstrated remarkable precision in differentiating between unhealthy and undamaged tea leaves.
Why it matches plant phenotyping methods茶葉画像から病害状態をCNNで分類する手法が研究の中心であり、植物の病徴・健全性という状態を直接推定しているため、植物フェノタイピング手法として含める。
abstractThe proposed method uses sequential Convolutional Neural Network (CNN) computations with many hidden layers to classify diseased and healthy tea leaves into multiple groups.
Reproduction assets foundThe paper's tea leaf disease image dataset is publicly available on Kaggle, with an explicit dataset link in the references. No author code or trained model is publicly deposited; other data are available only upon request.Dataset · publical tealeaf disease recognition
using a convolutional neural network model. Symmetry.
11(3): 343. https://doi.org/10.3390/sym11030343.Cho, O.H., Na, I.S. and Koh, J.G. (2024). Exploring advanced machine
learning techniques for swift legume disease detection.
Legume Research. 47(7): 1221-1227. doi: 10.18805/LRF-789.
Dataset Link: https://www.kaggle.com/datasets/shashwatwork/identifying-disease-in-tea-leafs?select=tea+sickness+
dataset. (Accessed on 06/05/2024).
Datta, S. and Gupta, N. (2023). A novel approach for the detection
of tea leaf disease using deep neural network. Procedia
Computer Science. 218: 2273-2286. https://doi.org/10.1016/j.procs.2023.01.203.Deka, N. and Goswami, K. (2020). EcOpen asset ↗Kaggle · shashwatwork/identifying-disease-in-tea-leafspdf-raw-page:8 lines:1-75Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Intelligent recognition and rapid grading of tea buds are crucial for advancing tea-picking machinery; however, complex plantation backgrounds and inconsistent bud growth have limited traditional algorithms to merely identifying picking points, neglecting bud pose and grade, which restricts harvesting efficiency. To address these challenges, we propose YOLO-PC, a deep neural network designed for simultaneous tea bud pose estimation and classification, which incorporates a dynamic snake convolution (DSConv) module for enhanced shape feature extraction, an ELASPP-CSPC attention mechanism for improved spatial pooling, and EIoU loss to accelerate regression and boost localization accuracy. Experimental results demonstrate that the model achieves detection accuracies of 91.5% for one-bud-one-leaf and 93.2% for one-bud-two-leaf scenarios, with an average keypoint detection accuracy (Pose_mAP) of 89.7% and a Normalized Mean Error (NME) of 0.047; furthermore, compared to YOLOv7-pose, it increases mean average precision by 7.26% and pose accuracy by 9.65% while reducing parameters by 14.99 M. Ablation studies confirm the superior performance of the proposed model in tea bud detection, indicating its potential to provide robust practical support for adaptive and intelligent tea harvesting systems.
Why it matches plant phenotyping methods茶芽の姿勢・等級という植物器官の状態を画像から推定する深層学習手法を開発し、精度比較・アブレーション評価まで行っており、単なる収穫対象の位置検出を超えたフェノタイピング手法が中心である。
abstractwe propose YOLO-PC, a deep neural network designed for simultaneous tea bud pose estimation and classification
TeaField / plotNeRF / 3D Gaussian SplattingLiDAR / point cloudLeafWhole plant / canopy / plot / fieldCountingObject detection2D/3D reconstructionSegmentation
Accurate perception of tea buds is a fundamental prerequisite for intelligent and precise tea harvesting planning. However, in real tea plantation environments, reliable harvesting-oriented perception at the planning level remains highly challenging due to the small size of tea buds, severe occlusion, complex background clutter, and the lack of accurate three-dimensional spatial information. To address these challenges, we propose TeaNeRF, an integrated three-dimensional visual perception pipeline designed for harvesting-oriented tea bud analysis. Instead of treating detection, segmentation, and spatial analysis as independent tasks, TeaNeRF integrates sequential two-dimensional recognition, monocular depth estimation, and neural radiance field reconstruction into a coherent perception pipeline, allowing accurate spatial understanding of tea buds in complex natural scenes. It should be noted that the proposed integration is conducted at the perception-output level, where multiple modular components are connected through fixed interfaces, rather than through joint optimization or an end-to-end trainable formulation. The proposed framework combines an enhanced YOLO-based detector, prompt-guided segmentation, and monocular depth priors to guide NeRF-based three-dimensional reconstruction. By incorporating depth supervision and semantic-aware neural fields, TeaNeRF generates dense and geometrically consistent point clouds with reliable semantic separation. Quantitative evaluations show consistent improvements in reconstruction fidelity, as reflected by increased PSNR and reduced LPIPS across multiple tea tree scenes. Based on the reconstructed semantic point cloud, a three-dimensional clustering and geometric fitting strategy is further developed to enable tea bud counting and harvesting-oriented candidate point estimation at the perception level. Experiments conducted on a real-world dataset of 4,700 tea plantation images demonstrate that TeaNeRF improves detection accuracy (mAP@50 = 91.7%), segmentation quality (IoU = 0.640), and overall three-dimensional perception performance. Case-level counting results on representative tea trees indicate that the proposed 3D semantic point cloud-based approach can provide feasible tea bud counting behavior and consistent spatial guidance cues for downstream harvesting planning. By providing structured three-dimensional spatial information, including tea bud locations, counts, and harvesting-oriented candidate points, TeaNeRF offers practical perception-level outputs for downstream planning in automated tea harvesting systems.
Why it matches plant phenotyping methods茶芽の検出・セグメンテーション・3D再構成を統合し、茶芽の計数と3D位置推定を行う知覚パイプラインが研究の中心であり、単なる収穫対象の局在化を超えた器官形質の抽出を含む。
abstractwe propose TeaNeRF, an integrated three-dimensional visual perception pipeline designed for harvesting-oriented tea bud analysis.
Pests cause much loss in tea (Camellia sinensis) production, but there is no appropriate method to detect them. In this work, gas sensors were employed to detect the attack time of tea plants having been attacked by Ectropis obliqua. The volatiles emitted by tea plants attacked by E. obliqua change during different periods of 1 day, and so detection results of the gas sensors are influenced by the detection time point. However, none of the previous studies about pest detection considered this time point. In this study, we determined the pest attack time of tea plants considering the detection time point. The classification performances of the gas sensors based on various detection time points were compared and the best one was determined. Besides, an extreme learning machine was employed for qualitative classification and quantitative regression analysis of tea plants with different pest attack times at the best detection time point. The results showed that the best detection time point of the gas sensors for tea plants was 12 noon, and the extreme learning machine for classification and prediction provided good results, which indicated the feasibility of the gas sensors for determining the pest attack time of tea plants.
Why it matches plant phenotyping methods茶樹が害虫被害を受けた状態と被害時期をガスセンサーで推定する手法が研究の中心であり、検出時点の比較と機械学習による分類・回帰も評価しているため、植物状態のセンサーフェノタイピングに該当する。
abstractgas sensors were employed to detect the attack time of tea plants having been attacked by Ectropis obliqua
Tea leaf diseases seriously affect its yield and quality, and consequently there is an urgent need for intelligent detection methods with high precision and edge deployment capabilities. To address low detection accuracy in complex backgrounds, overfitting due to limited data, and redundant parameters for existing methods, this paper proposes an improved lightweight detection model FCHE-YOLO based on the YOLO11, which aims to achieve rapid and accurate identification of tea leaf disease combining low altitude remote sensing with unmanned aerial vehicle (UAV). The model has made three key optimizations in the structure: Introduce the self-developed lightweight backbone module FC_C3K2, which significantly reduces computation and parameter count while enhancing the robustness of the model to complex scenarios; construct an efficient feature fusion structure HSFPN, optimizing multi-scale information integration and compressing model volume; design the detection head Efficient Head, integrating group convolution and lightweight attention mechanism to improve detection accuracy and suppress overfitting. The experimental results from the self built tea gardens show that the FCHE-YOLO improves the average accuracy (mAP) from 94.1% to 98.1% compared to the benchmark model YOLO11, with an improvement of 4.0 percentage points. Meanwhile, the inference speed of the model increases from 43.3 FPS to 47.5 FPS, with an increase of 9.0%, meeting the real-time detection requirements. More importantly, by network structure optimization, the model's computational complexity is significantly reduced: The floating-point operations per second (FLOPs) decreases from 6.4 G to 4.2 G, with a decrease of 34.3%, and the parameter count decreases from 2.59 M to 1.46 M, with the compression rate reaching 38.9%, which makes the model more suitable for deployment on resource-constrained UAV edge devices. The final test show that the FCHE-YOLO significantly reduces the missed-detection rate, owns better detection accuracy and deployment practicality, and is suitable for real-time monitoring scenarios of tea leaf diseases with UAVs.
Why it matches plant phenotyping methods茶葉の病害状態をUAV画像から検出する軽量深層学習手法を開発・評価しており、植物病害表現型の取得が中心的な技術貢献である。
abstractthis paper proposes an improved lightweight detection model FCHE-YOLO based on the YOLO11, which aims to achieve rapid and accurate identification of tea leaf disease combining low altitude remote sensing with unmanned aerial vehicle (UAV).
Reproduction assets foundThe paper's Data Availability Statement points to a public figshare repository containing the study's relevant data (UAV tea leaf disease imagery/dataset). No separate author code deposit is stated.Dataset · publicAll relevant data for this study are publicly available from the figshare repository (https://figshare.com/s/316807b23895bc3ba3ae).Open asset ↗figsharehtml-lines:693-736Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
ABSTRACT Sustainable agriculture urgently requires innovative, pesticide‐free strategies to mitigate herbivory and safeguard food security. Ultraviolet‐B (UV‐B) irradiation, with tunable intensity and cost‐effectiveness, has emerged as a promising non‐chemical method to enhance plant resistance, yet its underlying mechanisms remain elusive. Here, using tea plant ( Camellia sinensis ) and its major pest Ectropis obliqua as a model, we developed a multimodal framework that integrates AI‐enhanced electronic nose technology for real‐time volatile profiling with in situ hyperspectral stimulated Raman scattering (SRS) microscopy to characterize defense responses under precisely controlled UV‐B treatments. This approach identified herbivore‐induced volatiles—hexanal, (Z)‐3‐hexenol, octanal, and (Z)‐3‐hexenyl acetate—optimally induced at 1.2 kJ·m −2 UV‐B and linked to insect deterrence. SRS imaging further revealed elevated jasmonic acid derivatives and L‐phenylalanine, coupled with reduced protein levels and altered stomatal dynamics, all correlating with enhanced resistance. Transcriptomic and molecular analyses confirmed transcriptional regulation of these pathways. By bridging volatile detection, metabolic imaging, and molecular validation, this study pioneers a multimodal strategy that provides mechanistic insights into UV‐B–mediated plant defense and highlights the potential of multimodal methodologies as powerful tools for developing sustainable, pesticide‐free pest management solutions in precision agriculture.
Why it matches plant phenotyping methodsAI強化電子鼻とハイパースペクトルSRS顕微鏡を統合した植物防御応答のリアルタイム・多モーダル計測フレームワークが研究の中心であり、揮発性物質、代謝物、気孔動態などの植物状態を抽出している。
abstractwe developed a multimodal framework that integrates AI‐enhanced electronic nose technology for real‐time volatile profiling with in situ hyperspectral stimulated Raman scattering (SRS) microscopy to characterize defense responses
Timely and precise harvest scheduling is critical for maintaining tea quality and improving labor efficiency. This study aimed to develop an integrated Internet of Things (IoT) and artificial intelligence (AI) framework for automated monitoring and growth modeling of tea shoots, enabling data-driven plantation management. Solar-powered Plantation Monitoring Systems (PMS) were deployed to continuously capture canopy images and environmental data, reducing reliance on manual inspections. An enhanced YOLOv11 segmentation model, incorporating HSI color space conversion, monocular depth estimation, and shape-based temporal tracking, was used to detect pluckable tea shoots with high accuracy. The computed Tea Shoot Density Index (TSDI) showed strong agreement with ground truth measurements (RMSE = 2.542, R² = 0.931). Three sigmoid growth models − 3PL, 4PL, and Gompertz − were evaluated using growing degree days (GDD) as the time scale. The 4PL model achieved the best performance (RMSE = 0.698, R² = 0.897) and predicted optimal harvest timing with a mean absolute error (MAE) of 2.7 days, while offering interpretable parameters that reflect shoot retention, growth rate, and maturation dynamics. These parameters provided actionable insights for optimizing irrigation, fertilization, and harvest scheduling across different growth stages. The proposed system delivers a scalable and automated solution for precision tea agriculture, enhancing productivity, improving tea quality, and supporting the transition from experience-based to data-driven management.
Why it matches plant phenotyping methods茶園画像から摘採可能な新芽を検出し、密度指標と生育・成熟状態を推定するIoT・AI計測手法の開発と精度検証が研究の中心であるため。
abstractThis study aimed to develop an integrated Internet of Things (IoT) and artificial intelligence (AI) framework for automated monitoring and growth modeling of tea shoots
Tea shoot density monitoring is crucial for quality control and yield optimization in plantations. This study developed a UAV-based multispectral imaging framework integrating machine learning for automated tea shoot assessment. We collected 3,122 ground-truth samples across four categories (tea shoots, mature leaves, dry leaves, soil) using portable spectrometry, transformed five spectral bands into 23 vegetation indices, and applied feature selection to identify optimal predictors. A two-stage classification approach was implemented: Stage-1 eliminated non-tea background with 100% accuracy; Stage-2 classified growth stages using MLP, SVM, and XGBoost algorithms. MLP achieved superior performance with 97% F1-score for tea shoots and 96% for mature leaves, outperforming SVM (87%) and XGBoost (93%). Field validation across three plantations revealed distinct temporal patterns: reverse J-shape (early budding), bell-shape (active germination), to J-shape distributions (mature canopy). Spatial uniformity was quantified using the Tea Shoot Density Index (TSDI), with the most uniform plot showing Is = − 0.876 and NNI = 1.654. This framework enables rapid plantation-wide assessment, reducing manual sampling time from days to hours while providing actionable insights for precision fertilization and irrigation management, advancing sustainable tea production.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像と機械学習により茶芽の密度・生育段階を推定する手法を開発し、圃場検証も行っており、フェノタイピング手法が研究の中心である。
abstractThis study developed a UAV-based multispectral imaging framework integrating machine learning for automated tea shoot assessment.
To address the issue of drought level confusion in the detection of drought stress during the seedling stage of the Yunnan large-leaf tea variety using the traditional YOLOv13 network, this study proposes an improved version of the network, MC-YOLOv13-L, based on animal vision. With the compound eye's parallel sampling mechanism at its core, Compound-Eye Apposition Concatenation optimization is applied in both the training and inference stages. Simulating the environmental information acquisition and integration mechanism of primates' "multi-scale parallelism-global modulation-long-range integration," multi-scale linear attention is used to optimize the network. Simulating the retinal wide-field lateral inhibition and cortical selective convergence mechanisms, CMUNeXt is used to optimize the network's backbone. To further improve the localization accuracy of drought stress detection and accelerate model convergence, a dynamic attention process simulating peripheral search, saccadic focus, and central fovea refinement in primates is used. Inner-IoU is applied for targeted improvement of the loss function. The testing results from the drought stress dataset (324 original images, 4212 images after data augmentation) indicate that, in the training set, the Box Loss, Cls Loss, and DFL Loss of the MC-YOLOv13-L network decreased by 5.08%, 3.13%, and 4.85%, respectively, compared to the YOLOv13 network. In the validation set, these losses decreased by 2.82%, 7.32%, and 3.51%, respectively. On the whole, the improved MC-YOLOv13-L improves the accuracy, recall rate and mAP@50 by 4.64%, 6.93% and 4.2%, respectively, on the basis of only sacrificing 0.63 FPS. External validation results from the Laobanzhang base in Xishuangbanna, Yunnan Province, indicate that the MC-YOLOv13-L network can quickly and accurately capture the drought stress response of tea plants under mild drought conditions. This lays a solid foundation for the intelligence-driven development of the tea production sector and, to some extent, promotes the application of bio-inspired computing in complex ecosystems.
Why it matches plant phenotyping methods茶樹の干ばつストレス状態を画像から検出する改良YOLO手法を開発・検証しており、植物状態の取得・推定が研究の中心である。
abstractthis study proposes an improved version of the network, MC-YOLOv13-L, based on animal vision.
Reproduction assets foundThe paper's Data Availability Statement states the original code is openly available in IEEE DataPort at the allowed DOI URL, making the authors' analysis code a paper-specific public asset.Code · publicThe original code presented in the study are openly available in IEEE DataPort at https://dx.doi.org/10.21227/v32y-mv49.Open asset ↗IEEE DataPort · 10.21227/v32y-mv49html-lines:829-851Plant phenotyping relevance match · UnverifiedOpenAlex · checked 14 Sept 2026
The tea plant (Camellia sinensis) is economically and nutritionally important because of its bioactive compounds. Photosynthesis directly affects tea's growth and productivity, requiring a detailed study of its relationship with cultivation outcomes. We developed a novel computational pipeline for constructing three-dimensional (3D) canopy photosynthesis models of tea plant, leveraging multi-view stereo 3D reconstruction. The ISBNet architecture was optimized for precise leaf–stem segmentation from point cloud data, achieving 0.897 average precision (AP) for leaves and 0.793 AP for stems. We then created a plant leaf morphology-adapted meshing algorithm optimized for plant leaf morphology, achieving an average mesh reduction of approximately 96% while maintaining morphological fidelity compared with conventional meshing methods. We generated multiple tea plant canopies representing distinct planting patterns, and used a ray tracing algorithm to simulate the spatiotemporal distribution of light within these structures. Canopy photosynthesis simulation revealed significant cultivar-specific differences, with 'Yuehuang 1' exhibiting the highest photosynthetic activity. Dense planting (10 cm spacing) significantly enhanced canopy photosynthetic rates compared with wider spacing (20 cm), and a strong linear correlation (r = 0.99) was identified between total leaf area and daily canopy photosynthetic rate across cultivars. This work establishes a methodological foundation for precision agriculture optimization in perennial crops, providing quantitative guidance for maximizing tea plantations' productivity through optimal cultivar selection and spatial configuration.
Why it matches plant phenotyping methods茶樹キャノピーの3D再構築、葉・茎セグメンテーション、形態適応メッシュ化、光線追跡による光合成推定を統合した方法開発が中心であり、植物形態・光合成状態の定量化に直接つながる。
abstractWe developed a novel computational pipeline for constructing three-dimensional (3D) canopy photosynthesis models of tea plant, leveraging multi-view stereo 3D reconstruction.
Background In Shandong Province of China, where annual precipitation is below 800 mm, tea plants face persistent drought stress exacerbated by global warming. Breeding drought-tolerant tea cultivars is one of the effective ways to cope with this challenge. However, traditional breeding approaches are still limited by prolonged cycles, low efficiency, and subjective evaluation. To overcome these limitations, the development of rapid and objective germplasm evaluation methods has become critical. Results In this study, hyperspectral images of leaves from 12 widely cultivated 'Lucha series' tea cultivars in Shandong Province during different drought periods were collected, and the drought-related physiological indicators were measured simultaneously. Then, a tea drought tolerance index (TDTI) with enhanced accuracy was established by integrating the rate of change of indicators with temporal weights and indicator weights. Subsequently, we developed a novel lightweight Transformer-based hybrid integrated architecture to establish prediction models for the physiological indicators and TDTI. The Transformer-based models synergistically combined a Transformer encoder with XGBoost and LightGBM within a lightweight framework that leverages ensemble learning, data augmentation, and regularization to ensure robustness on limited datasets. Finally, we compared the performance of Transformer-based models against traditional machine learning models. The optimal models for MRP, MDA, Pro, SS, ChlT and TDTI were identified as 1D-CARS-TF, 2D-UVE-SVM, 2D-UVE-BRR, 2D-CARS-SVM, 1D-UVE-TF-CNN, and 2D-UVE-TF, respectively, achieving determination coefficient (R²) of 0.8992, 0.8307, 0.8929, 0.8373, 0.7894, and 0.7614, on an independent test set. The results demonstrated that the lightweight Transformer-based models equipped with multi-head self-attention mechanism exhibited outstanding capabilities in processing indicators requiring multi-band correlation mining. Simultaneously, feature selection algorithms and overfitting-mitigation optimization strategies played a critical role in enhancing both the accuracy and stability of the Transformer-based models.. Conclusions This study established a robust technical foundation for rapid, accurate, and non-destructive comprehensive evaluation of drought tolerance for tea plant germplasm resources. However, it should be noted that they were based on a specific set of greenhouse-cultivated samples, and further validation under field conditions with expanded germplasm resources would strengthen generalizability. Anyway, the demonstrated potential of the Transformer-based model in our study advances phenomics of tea plants toward greater intelligence and efficiency.
Why it matches plant phenotyping methods茶植物葉のハイパースペクトル画像から生理指標と干ばつ耐性指数を推定するモデルを開発・独立検証しており、植物フェノタイピング手法が中心である。
abstractwe developed a novel lightweight Transformer-based hybrid integrated architecture to establish prediction models for the physiological indicators and TDTI
In this study, we present a combined image dataset created from two distinct plant species: Hibiscus and Tea leaf. The dataset consists of high-resolution images of leaves from both species, captured using a SONY α7 II DSLR camera and a OnePlus 7T lubricant Tea Leaf dataset includes images categorized into five disease classes: Algal Leaf Spot, Brown Blight, Grey Blight, Red Leaf Spot, and Healthy, while the Hibiscus Leaf dataset includes images labeled across eight conditions, including citrus spot, fungal infection, mild edge damage, and healthy foliage. To ensure balanced representation and address class imbalances, extensive data augmentation techniques-such as flipping, rotation, zooming, shifting, noise addition, and brightness adjustment-were applied, resulting in a total of 1,413 combined original images and 13,000 augmented images. The ConvNextTiny deep learning model was fine-tuned on this combined dataset to classify the various leaf conditions, achieving an overall accuracy of 96%. This demonstrates the model's robust performance and high discriminatory power across the diverse set of leaf diseases and conditions. This experiment highlights the utility of combining multiple plant species into a single dataset and utilizing a lightweight yet effective model like ConvNextTiny for plant disease classification. The resulting dataset, along with the model and training scripts, is publicly available to facilitate further research in plant pathology, computer vision, and smart farming applications, enabling more accurate and efficient early-stage disease detection for both Hibiscus and Tea plants.
Why it matches plant phenotyping methods植物葉の病害・健全状態を画像から分類するデータセットを構築し、分類モデルで性能評価しているため、植物フェノタイピング手法・ベンチマークが中心です。
abstractwe present a combined image dataset created from two distinct plant species: Hibiscus and Tea leaf
Reproduction assets foundThe paper's combined Hibiscus and Tea leaf disease image dataset is publicly deposited on Mendeley Data (DOI 10.17632/5bzy89brkv.4), and the authors' augmentation/training scripts are on a public GitHub repository; both are paper-specific, public, and directly actionable.Dataset · publicRepository name: Mendeley Data
Data identification number: 10.17632/5bzy89brkv.4
Direct URL to data: https://data.mendeley.com/datasets/5bzy89brkv/4Open asset ↗Mendeley Data · 10.17632/5bzy89brkv.4lines:1-46Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 6 Sept 2026
Accurate estimation of chlorophyll contents from spectral reflectance is necessary for monitoring plant physiological status and for supporting precision agriculture. This study, which uses four machine learning models (1D Convolutional Neural Network (1D-CNN), Self-Supervised Learning (SSL), Vision Transformer (ViT), and Conformer), elucidates the effects of four preprocessing techniques on the performance of chlorophyll content prediction: Original Reflectance (OR), Continuum Removal (CR), De-trending (DT), and Standard Normal Variate (SNV). Reflectance data were collected from tea leaves (Camellia sinensis) and were analysed using ten-fold cross-validation. Correlation analysis revealed that SNV and DT enhanced the spectral sensitivity to chlorophyll content, particularly around the chlorophyll absorption regions (450-500 nm and 650-700 nm), whereas CR emphasized negative correlation in the visible spectrum. Prediction results demonstrated that the SSL model combined with SNV preprocessing achieved the highest accuracy (R² = 0.82, RPD = 2.37), outperforming other model-preprocessing combinations. The 1D-CNN model performed best with DT, leveraging local spectral features, whereas ViT and Conformer models benefited most from CR, which emphasizes absorption depth and spectral shape. These results highlight that the optimal preprocessing method depends on the model architecture, and that proper pairing between preprocessing and modelling approaches is crucially important for maximizing prediction performance. The study results underscore the importance of customized preprocessing strategies for hyperspectral analysis and provide practical insights for improving biochemical trait estimation in plant phenotyping.
Why it matches plant phenotyping methods茶葉のスペクトル反射からクロロフィル含量を推定する植物表現型測定法について、前処理と複数の深層学習モデルを比較・検証しており、方法論が研究の中心です。
abstractAccurate estimation of chlorophyll contents from spectral reflectance is necessary for monitoring plant physiological status
Tea flowers play a crucial role in taxonomic research and hybrid breeding of tea plants. As traditional methods of observing tea flower traits are labor-intensive and inaccurate, TflosYOLO and Tea Flowering Stage Classification (TFSC) models were proposed for tea flowering quantification, which enable the estimation of flower count and flowering period. In this study, a highly representative and diverse dataset was constructed by collecting flower images from 29 tea accessions in 2 years. Based on this dataset, the TflosYOLO model was built on the YOLOv5 architecture and enhanced with the Squeeze-and-Excitation (SE) network, Adaptive Rectangular Convolution, and Attention Free Transformer, which is the first model to offer a viable solution for detecting and counting tea flowers. The TflosYOLO model achieved a mean Average Precision at 50% IoU (mAP50) of 0.844, outperforming YOLOv5, YOLOv7, and YOLOv8. Furthermore, the TflosYOLO model was tested on 31 datasets encompassing 26 tea accessions and five flowering stages, demonstrating high generalization and robustness. The correlation coefficient (R 2 ) between the predicted and actual flower counts was 0.964. Additionally, the TFSC model-a seven-layer neural network-was designed for the automatic classification of the flowering period. The TFSC model was evaluated for 2 years and achieved an accuracy of 0.738 and 0.899. Using the TflosYOLO+TFSC model, the tea flowering dynamics were monitored, and the changes in flowering stages were tracked across various tea accessions. The framework provides crucial support for tea plant breeding programs and the phenotypic analysis of germplasm resources.
Why it matches plant phenotyping methods茶花画像から花数と開花期を推定するモデルを開発・検証しており、植物表現型の取得・抽出手法が研究の中心である。
abstractTflosYOLO and Tea Flowering Stage Classification (TFSC) models were proposed for tea flowering quantification, which enable the estimation of flower count and flowering period.
Reproduction assets foundThe paper's data availability statement explicitly deposits the tea flower datasets and models in a public GitHub repository (sufie-mi/tea-flower-model), which directly supports this paper's tea flower phenotyping measurements and models. The labelImg repository is a generic third-party annotation tool, not a paper-ownDataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://github.com/sufie-mi/tea-flower-model .Open asset ↗https://github.com/sufie-mi/tea-flower-model · tea-flower-modellines:764-781Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · checked 6 Sept 2026
Introduction The cigar leaves moisture content (CLMC) is a critical parameter for controlling curing barn conditions. Along with the continuous advancement of deep learning (DL) technologies, convolutional neural networks (CNN) have provided a way of thinking for the non-destructive estimation of CLMC during the air-curing process. Nevertheless, relying merely on single-perspective imaging makes it difficult to comprehensively capture the complementary morphological features of the front and back sides of cigar leaves during the air-curing process. Methods This study constructed a dual-view image dataset covering the air-curing process, and proposes a regression framework named CADFFNet (channel attention weight-based dual-branch feature fusion network) for the non-destructive estimation of CLMC during the curing process based on dual-view RGB images. Firstly, the model utilizes two independent and parallel ResNet as its backbone structure to capture the heterogeneous features of dual-view images. Secondly, the Dual Efficient Channel Attention (DECA) module is introduced to dynamically adjust the channel attention weights of the features, thereby facilitating interaction between the two branches. Lastly, a Multi-scale convolutional feature fusion (MSCFF) module is designed for the deep fusion of features from the front and back images to aggregate multi-scale features for robust regression. Results On five-fold cross-validation, CADFFNet attains R2 of 0.974±0.007 and mean absolute error (MAE) of 3.80±0.37%. On an independent cross-region, cross-variety testing set, it maintains strong generalization (R2=0.899, MAE=5.82%), compared with the classic CNN models ResNet18, GoogLeNet, VGG19Net, DenseNet121, and MobileNetV2, its R2 value has increased by 0.047, 0.041, 0.055, 0.098, and 0.090 respectively. Discussion Generally, the proposed CADFFNet offers an efficient and convenient method for non-destructive detection of CLMC, providing a theoretical basis for automating the air-curing process. It also provides a new perspective for moisture content prediction during the drying process of other crops, such as tea, asparagus, and mushrooms.
Why it matches plant phenotyping methods葉の水分含量という植物状態を、二視点RGB画像と新規深層学習回帰モデルで非破壊推定する手法を開発し、交差検証および独立試験で性能評価しており、植物フェノタイピング手法が中心である。
abstractproposes a regression framework named CADFFNet (channel attention weight-based dual-branch feature fusion network) for the non-destructive estimation of CLMC during the curing process based on dual-view RGB images.
Accurate estimation of chlorophyll content in tea leaves is essential for evaluating plant health, managing fertilization, and optimizing harvest timing in precision agriculture. This study investigates the use of hyperspectral reflectance data (400–850 nm, 5 nm intervals; 91 bands) to estimate chlorophyll content in tea leaves (Camellia sinensis) using three deep learning models: a one-dimensional convolutional neural network (1D–CNN) tailored for spectral regression, a vision transformer (ViT) adapted for one-dimensional inputs, and a self-supervised learning (SSL) model with regression. The key innovation of this study is the introduction of a self-supervised learning framework specifically adapted for spectral data, in which an autoencoder is first trained on unlabeled spectra to learn compact and noise-tolerant representations. These pretrained features are then used in a downstream regression task to predict chlorophyll content, allowing effective use of limited labeled data. To our knowledge, this is the first application of SSL in chlorophyll estimation using high–resolution leaf–level spectral measurements. Among the three models, the SSL approach achieved the highest accuracy, with a root mean square error (RMSE) of 3.33 μg/cm², outperforming both the 1D–CNN (5.05 μg/cm²) and ViT (4.28 μg/cm²). These findings demonstrate that SSL is particularly effective for capturing subtle spectral patterns and improving prediction performance, especially when labeled data are scarce. This study highlights the potential of combining hyperspectral sensing with advanced representation learning to non–destructively monitor chlorophyll dynamics in tea cultivation, supporting more sustainable and data–driven agricultural practices.
Why it matches plant phenotyping methods茶葉のクロロフィル含量という植物形質を、ハイパースペクトル計測と深層学習で推定する方法が研究の中心であり、SSL手法の開発・比較検証も行っている。
abstractThis study investigates the use of hyperspectral reflectance data (400–850 nm, 5 nm intervals; 91 bands) to estimate chlorophyll content in tea leaves (Camellia sinensis) using three deep learning models
To address the challenges of variable target scale, complex background, blurred image, and serious occlusion in the yield detection of Yunnan large-leaf tea tree, this study proposes a deep learning network DE-YOLOv13-S that integrates the visual mechanism of primates. DynamicConv was used to optimize the dynamic adjustment process of the effective receptive field and channel the gain of the primate visual system. Efficient Mixed-pooling Channel Attention was introduced to simulate the observation strategy of 'global gain control and selective integration parallel' of the primate visual system. Scale-based Dynamic Loss was used to simulate the foveation mechanism of primates, which significantly improved the positioning accuracy and robustness of Yunnan large-leaf tea tree yield detection. The results show that the Box Loss, Cls Loss, and DFL Loss of the DE-YOLOv13-S network decreased by 18.75%, 3.70%, and 2.54% on the training set, and by 18.48%, 14.29%, and 7.46% on the test set, respectively. Compared with YOLOv13, its parameters and gradients are only increased by 2.06 M, while the computational complexity is reduced by 0.2 G FLOPs, precision, recall, and mAP are increased by 3.78%, 2.04% and 3.35%, respectively. The improved DE-YOLOv13-S network not only provides an efficient and stable yield detection solution for the intelligent management level and high-quality development of tea gardens, but also provides a solid technical support for the deep integration of bionic vision and agricultural remote sensing.
Why it matches plant phenotyping methods茶樹の収量を画像から検出する深層学習モデルを開発・評価しており、植物形質の取得手法が研究の中心である。
abstractthis study proposes a deep learning network DE-YOLOv13-S
Reproduction assets foundThe paper's Data Availability Statement explicitly states the original code is openly available in IEEE DataPort with a DOI link, making the authors' analysis code a public, paper-specific asset.Code · publicData Availability Statement: The original code presented in the study are openly available in IEEE
DataPort at https://dx.doi.org/10.21227/drd6-b843.Open asset ↗10.21227/drd6-b843pdf-page:18 lines:1-57Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · checked 6 Sept 2026
The tea industry plays a vital role in China's green economy. Tea trees (Melaleuca alternifolia) are susceptible to numerous diseases and pest threats, making timely pathogen detection and precise pest identification critical requirements for agricultural productivity. Current diagnostic limitations primarily arise from data scarcity and insufficient discriminative feature representation in existing datasets. This study presents a new tea disease and pest dataset (TDPD, 23-class taxonomy). Five lightweight convolutional neural networks (LCNNs) were systematically evaluated through two optimizers, three learning rate configurations and six distinct scheduling strategies. Additionally, an enhanced MnasNet variant was developed through the integration of SimAM attention mechanisms, which improved feature discriminability and increased the accuracy of tea leaf disease and pest classification. Model validation employs both our proprietary TDPD dataset and an open-access dataset, with performance evaluation metrics including average accuracy, F1 score, recall, and parameter size. The experimental results demonstrated the superior classification performance of the model, which achieved accuracies of 98.03% based on TDPD and 84.58% based on the public dataset. This research outlines an effective paradigm for automated tea disease and pest detection, with direct applications in precision agriculture through integration with UAV-mounted imaging systems and mobile diagnostic platforms. This study provides practical implementation pathways for intelligent tea plantation management.
Why it matches plant phenotyping methods茶葉画像から病害・害虫状態を推定するCNN、データセット構築、モデル比較・検証が研究の中心であり、植物の病害状態を対象とする実質的なフェノタイピング手法研究である。
titleA lightweight convolutional neural network for tea leaf disease and pest recognition
Tea leaf blight (TLB) is a common tea disease, and accurate detection of the different stages of TLB helps in tea disease control. The color and shape of TLB spots at different stages vary greatly and are easily confused with complex backgrounds; hence, the accuracy of existing methods for detecting TLB at different stages is not high. In this study, a dual-branch TLB detection network (DBTDNet) combining spatial domain and frequency domain information was designed for the accurate detection of TLB at different stages. The dense depthwise separable (DDS) module and wavelet-based feature extraction (WBFE) Bottleneck were introduced into the spatial feature extraction (SFE) branch and frequency feature extraction (FFE) branch of DBTDNet to extract spatial domain features and frequency domain features, respectively, and enhance the localization and recognition of TLB spots at different stages. A multiscale wavelet transform convolution (MSWTC) module was also added to the FFE branch to separate the multi-scale frequency information and obtain clearer shape and texture features of TLB spots. A linear layer was introduced between the dual-branch structures to reduce the gradient information loss. In addition, to better capture TLB spots of different sizes, this study designed a multidimensional neural network (MNNet) structure in the feature fusion part of DBTDNet for fusing the information of different scale feature maps from the output of the dual branch. The experimental results showed that the proposed DBTDNet could more accurately detect TLB spots at different stages than the existing state-of-the-art network models. The mAP@0.5 values of its detection results for yellow TLB spots in the early stage, white TLB spots in the middle and late stages, and total TLB spots were 74.5%, 75.3%, and 75%, respectively, which were 13.2%, 7.5%, and 10.5% higher, respectively, than the baseline model YOLOv9 detection results.
Why it matches plant phenotyping methods茶葉の病斑という植物の病害状態を画像から検出・認識する深層学習手法を開発し、既存モデルと性能比較しているため、植物フェノタイピング手法が中心である。
abstracta dual-branch TLB detection network (DBTDNet) combining spatial domain and frequency domain information was designed for the accurate detection of TLB at different stages.
Tea diseases cause significant economic losses to the tea industry every year, and thus developing a rapid and accurate tea disease detector is of great significance for assisting farmers in preventing diseases and increasing their income. Therefore, this paper proposes a lightweight and efficient detector called TDDet to quickly and accurately detect tea diseases. TDDet is mainly composed of two key innovations: feature extraction and feature aggregation. For feature extraction, we use lightweight depthwise separable convolution to reduce the computational load and enhance the ability to extract key local features in images of tea diseases. In addition, attention mechanisms including channel-, spatial-, and self-attentions, are employed to enable the model to focus on the most important parts of tea diseases, thereby improving the performance of the model. For feature aggregation, we propose a novel Cross-scale Feature Fusion (CFF) module to focus on tea disease areas, boosting the model’s sensitivity to feature details. Based on CFF, TDDet repeatedly fuses multiscale features of different levels in a top-down and bottom-up manner, enhancing feature representation capability. Besides, a lightweight and efficient upsampling module, called Dysample, is used to reduce computational costs and improve model performance by dynamically adjusting the sampling rate of feature maps. Experimental results demonstrate that TDDet with fewer parameters outperforms other state-of-the-art object detection models, enabling fast and accurate identification of tea diseases. Our code and dataset are available at https://github.com/hpguo1982/TDDet.
Why it matches plant phenotyping methods茶葉の病害画像から病害を検出する軽量モデルを開発し、性能比較も行っており、植物病害状態の取得手法が研究の中心である。
abstractthis paper proposes a lightweight and efficient detector called TDDet to quickly and accurately detect tea diseases
Sustainable agriculture urgently requires innovative, pesticide-free strategies to mitigate herbivory and safeguard food security. Ultraviolet-B (UV-B) irradiation, with tunable intensity and cost-effectiveness, has emerged as a promising non-chemical method to enhance plant resistance, yet its underlying mechanisms remain elusive. Here, using tea plant ( Camellia sinensis ) and its major pest Ectropis obliqua as a model, we developed a multimodal framework that integrates AI-enhanced electronic nose technology for real-time volatile profiling with in situ hyperspectral stimulated Raman scattering (SRS) microscopy to characterize defense responses under precisely controlled UV-B treatments. This approach identified herbivore-induced volatiles—hexanal, (Z)-3-hexenol, octanal, and (Z)-3-hexenyl acetate—optimally induced at 1.2 kJ·m -2 UV-B and linked to insect deterrence. SRS imaging further revealed elevated jasmonic acid derivatives and L-phenylalanine, coupled with reduced protein levels and altered stomatal dynamics, all correlating with enhanced resistance. Transcriptomic and molecular analyses confirmed transcriptional regulation of these pathways. By bridging volatile detection, metabolic imaging, and molecular validation, this study pioneers a multimodal strategy that provides mechanistic insights into UV-B–mediated plant defense and highlights the potential of multimodal methodologies as powerful tools for developing sustainable, pesticide-free pest management solutions in precision agriculture.
Why it matches plant phenotyping methodsAI強化電子鼻とSRS顕微鏡を統合した植物防御応答の取得・解析フレームワークが研究の中心であり、揮発性物質、代謝、気孔動態などの植物状態を測定しているため。
abstractwe developed a multimodal framework that integrates AI-enhanced electronic nose technology for real-time volatile profiling with in situ hyperspectral stimulated Raman scattering (SRS) microscopy to characterize defense responses
Tea tree seeds are highly sensitive to dehydration and cannot be stored for extended periods, making surface defect detection crucial for preserving their germination rate and overall quality. To address this challenge, we propose Cgc-YOLO, an enhanced YOLO-based model specifically designed to detect small-scale and complex surface defects in tea seeds. A high-resolution imaging system was employed to construct a dataset encompassing five common types of tea tree seeds, capturing diverse defect patterns. Cgc-YOLO incorporates two key improvements: (1) GhostBlock, derived from GhostNetV2, embedded in the Backbone to enhance computational efficiency and long-range feature extraction; and (2) the CPCA attention mechanism, integrated into the Neck, to improve sensitivity to local textures and boundary details, thereby boosting segmentation and localization accuracy. Experimental results demonstrate that Cgc-YOLO achieves 97.6% mAP50 and 94.9% mAP50-95, surpassing YOLO11 by 2.3% and 3.1%, respectively. Furthermore, the model retains a compact size of only 8.5 MB, delivering an excellent balance between accuracy and efficiency. This study presents a robust and lightweight solution for nondestructive detection of tea seed defects, contributing to intelligent seed screening and storage quality assurance.
Why it matches plant phenotyping methods茶種子表面欠陥という植物器官の状態を、高解像度画像と改良YOLOモデルで検出・評価する手法開発および性能検証が研究の中心である。
abstractwe propose Cgc-YOLO, an enhanced YOLO-based model specifically designed to detect small-scale and complex surface defects in tea seeds.
Accurate, real-time, and non-destructive monitoring of fresh tea leaf quality is essential for achieving high standards in tea cultivation. This study aimed to develop robust predictive models for key quality components—tea polyphenols, free amino acids, and the polyphenol-to-amino acid ratio (TP/AA)—by integrating hyperspectral reflectance data and meteorological variables. Hyperspectral data were collected from tea canopy using an ASD HandHeld 2 spectrometer across six representative tea gardens in Jiangsu Province, China, during spring, summer, and autumn. Simultaneously, fresh leaf samples were analyzed for biochemical composition, and corresponding meteorological data were recorded. Sensitive spectral features were extracted using harmonic and wavelet transformations, and feature-based hyperspectral indices were constructed via two- and three-feature combination strategies. Three machine learning algorithms—Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Partial Least Squares Regression (PLSR)—were employed to build predictive models. The results revealed significant seasonal variation in quality components, with tea polyphenols and TP/AA peaking in summer and amino acids in spring. Harmonic and wavelet features outperformed raw reflectance in correlating with quality indicators. Models integrating these features achieved high predictive accuracy for tea polyphenols (R² = 0.59–0.71), free amino acids (R² = 0.65–0.79), and TP/AA (R² = 0.60–0.77) across different periods, which further improved (up to R² = 0.86) using RF and LASSO with the inclusion of meteorological variables. The best model performance was observed in autumn, followed by summer and spring. This research proposes an effective machine learning–based remote sensing approach for non-destructive tea quality assessment, offering practical value for precision management and optimized harvest scheduling in high-quality tea production.
Why it matches plant phenotyping methods茶葉キャノピーのハイパースペクトルから生葉の品質成分を非破壊推定する特徴抽出・機械学習手法を開発し、複数季節・茶園で精度評価しており、表現型取得手法が中心である。
abstractSensitive spectral features were extracted using harmonic and wavelet transformations, and feature-based hyperspectral indices were constructed via two- and three-feature combination strategies.
Focusing on the characteristic tea resource Zijuan tea, this study addresses the difficulty of grading on production lines and the complexity of quality evaluation. On the basis of the fusion of near-infrared (NIR) spectroscopy and visual features, a novel method is proposed for classifying different tenderness levels and quantitatively assessing key anthocyanin components in Zijuan tea fresh leaves. First, NIR spectra and visual feature data were collected, and anthocyanin components were quantitatively analyzed using UHPLC-Q-Exactive/MS. Then, four preprocessing techniques and three wavelength selection methods were applied to both individual and fused datasets. Tenderness classification models were developed using Particle Swarm Optimization-Support Vector Machine (PSO-SVM), Random Forest (RF), and Convolutional Neural Networks (CNNs). Additionally, prediction models for key anthocyanin content were established using linear Partial Least Squares Regression (PLSR), nonlinear Support Vector Regression (SVR) and RF. The results revealed significant differences in NIR spectral characteristics across different tenderness levels. Model combinations such as TEX + Medfilt + RF and NIR + Medfilt + CNN achieved 100% accuracy in both training and testing sets, demonstrating robust classification performance. The optimal models for predicting key anthocyanin contents also exhibited excellent predictive accuracy, enabling the rapid and nondestructive detection of six major anthocyanin components. This study provides a reliable and efficient method for intelligent tenderness classification and the rapid, nondestructive detection of key anthocyanin compounds in Zijuan tea, holding promising potential for quality control and raw material grading in the specialty tea industry.
Why it matches plant phenotyping methodsNIR分光と画像特徴量を融合し、茶葉の硬さ（tenderness）分類とアントシアニン含量推定を行う取得・解析手法が研究の中心であり、植物器官の形質測定法として適格。
abstracta novel method is proposed for classifying different tenderness levels and quantitatively assessing key anthocyanin components in Zijuan tea fresh leaves
Tea is an extremely popular beverage around the world due to its exquisite taste and flavor. Unfortunately, it is prone to different types of illness, which can reduce the amount of harvest along with its standard. Among these, leaf infections are a serious concern since they negatively affect the quality of tea leaves. As a consequence, tea producers often encounter a great deal of obstacles and financial losses. Keeping this in mind, a thorough dataset has been compiled, which contains 5278 images of diseased and healthy leaves. The purpose of this dataset is to improve our knowledge of how these conditions impact cultivating tea plants and tea production. These images are collected from a variety of locations and meteorological circumstances, which provide an extensive knowledge of the disease patterns unique to tea leaves. The pictures have been captured with the help of some high-quality devices from different angles and in high resolution to ensure the standard and increase the usability of the dataset. Rigorous steps were followed when preparing the dataset that would be of great help in building a precise artificial intelligence model. The dataset carefully determined and classified six tea leaf diseases: Tea algal leaf spot, Brown Blight, Gray Blight, Helopeltis, Red spider, and Green mirid bug. There is one more class in the dataset containing images of healthy leaves. These illnesses are known for their devastating impact on tea leaves. An automated disease classification system can be made utilizing deep learning techniques that will enable estate managers to take timely action to stop the spread of the disease, and this meticulously collected dataset will immensely help to train that model.
Why it matches plant phenotyping methods茶葉の健全・病害状態を画像で取得し、疾患分類用データセットとして構築した研究であり、植物の病害表現型データの整備が中心である。
abstracta thorough dataset has been compiled, which contains 5278 images of diseased and healthy leaves
Efficient harvesting and field management of tea is closely related to the mechanical properties of tea stems; however, there have no research on variables and models that can be used to predict them. In this paper, the relationship between factors (number of segments, diameter, stem length, density, moisture content, moment of inertia, and fracture deflection) affecting the mechanical properties (tensile and bending strength) of tea stems was analysed using a combination of partial least squares regression and ridge regression analyses, using three tea varieties, namely, Jinxuan, Yinghong, and Liannan, as the research subjects. Ultra depth of field electron microscopy was used to aid in the interpretation of the mechanical properties. The regression fitting results showed that the R² values of the prediction models for the tensile and flexural strengths of Jinxuan tea stems were 0.9361 and 0.9054, respectively, and the root mean square errors of prediction (RMSEP) were 0.7709 MPa and 1.9083 MPa, respectively. The R² values of the tensile and bending strengths of Liannan tea stems were 0.9161 and 0.9240, respectively, and the RMSEP were 0.3948 MPa and 1.2973 MPa, respectively. The R² values of Yinghong tea stems were 0.9292 and 0.9196, and the RMSEP values were 1.3207 MPa and 1.7489 MPa, respectively. The RPD of all the prediction models was greater than 3, indicating high prediction accuracy. The results of the comprehensive orthogonal test using four factors and three levels showed that the factors affecting the shear strength of tea stems were in the following order: stem segment, variety, moisture content, and shear speed. The results of the study will help to understand the biomechanical properties of tea stems, improve their resource utilisation and provide a reference for the optimal design of industrial cutting devices.
Why it matches plant phenotyping methods茶茎の tensile／bending strength という植物器官特性を、形態・物性変数からPLSR-Ridge回帰で予測するモデルを開発・評価しており、特性推定法が研究の中心である。
abstractthere have no research on variables and models that can be used to predict them.
In recent times, deep learning has been widely used in agriculture fields to identify diseases in crops, weather prediction, and crop yield prediction. However, designing efficient deep learning models that are lightweight, cost-effective, and suitable for deployment on small devices remains a challenge. This paper addresses this gap by proposing a Convolutional Neural Network (CNN) architecture optimized using a Genetic Algorithm (GA) to automate the selection of critical hyperparameters, such as the number and size of filters, ensuring high performance with minimal computational overhead. In this work, we have built our own tea leaf disease dataset consisting of three different tea leaf diseases, two diseases caused by pests, and one due to pathogens (infectious organisms) and environmental conditions. The proposed genetic algorithm-based CNN achieved an accuracy rate of 97.6% on the tea leaf disease dataset. To further validate its robustness, the model was tested on two additional datasets, namely PlantVillage and Rice leaf disease dataset, achieving accuracies of 96.99% and 99%, respectively. Performances of the proposed model are also compared with several state-of-the-art deep learning models, and the results show that the proposed model outperforms several DL architectures with fewer parameters.
Why it matches plant phenotyping methods茶葉などの植物病害を画像から分類するCNNを遺伝的アルゴリズムで設計し、複数データセットで性能検証しており、植物病害状態の取得・推定手法が中心である。
abstractproposing a Convolutional Neural Network (CNN) architecture optimized using a Genetic Algorithm (GA) to automate the selection of critical hyperparameters
Tea disease detection is of great significance to the tea industry. In order to solve the problems such as mutual occlusion of leaves, light disturbance, and small lesion area under complex background, YOLO-SSM, a tea disease detection model, was proposed in this paper. The model introduces the SSPDConv convolution module in the backbone of YOLOv8 to enhance the global information perception of the model under complex backgrounds; a new ESPPFCSPC module is proposed to replace the original spatial pyramid pool SPPF module, which optimizes the multi-scale feature expression; and the MPDIoU loss function is introduced to optimize the problem that the original CIoU is insensitive to the change of target size, and the positioning ability of small targets is improved. Finally, the map values of 89.7% and 68.5% were obtained on a self-made tea data set and a public tea disease data set, which were improved by 3.9% and 4.3%, respectively, compared with the original benchmark model, and the reasoning speed of the model was 164.3 fps. Experimental results show that the proposed YOLO-SSM algorithm has obvious advantages in accuracy and model complexity and can provide reliable theoretical support for efficient and accurate detection and identification of tea leaf diseases in natural scenes.
Why it matches plant phenotyping methods茶葉病害の画像検出モデルを開発・評価し、病斑を含む植物の病害状態を直接推定しているため、植物フェノタイピング手法が中心である。
abstracta tea disease detection model, was proposed in this paper
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
To achieve an efficient, non-destructive, and intelligent identification of tea plant seedlings under high-temperature stress, this study proposes an improved YOLOv11 model based on chlorophyll fluorescence imaging technology for intelligent identification. Using tea plant seedlings under varying degrees of high temperature as the research objects, raw fluorescence images were acquired through a chlorophyll fluorescence image acquisition device. The fluorescence parameters obtained by Spearman correlation analysis were found to be the maximum photochemical efficiency (Fv/Fm), and the fluorescence image of this parameter is used to construct the dataset. The YOLOv11 model was improved in the following ways. First, to reduce the number of network parameters and maintain a low computational cost, the lightweight MobileNetV4 network was introduced into the YOLOv11 model as a new backbone network. Second, to achieve efficient feature upsampling, enhance the efficiency and accuracy of feature extraction, and reduce computational redundancy and memory access volume, the EUCB (Efficient Up Convolution Block), iRMB (Inverted Residual Mobile Block), and PConv (Partial Convolution) modules were introduced into the YOLOv11 model. The research results show that the improved YOLOv11-MEIP model has the best performance, with precision, recall, and mAP50 reaching 99.25%, 99.19%, and 99.46%, respectively. Compared with the YOLOv11 model, the improved YOLOv11-MEIP model achieved increases of 4.05%, 7.86%, and 3.42% in precision, recall, and mAP50, respectively. Additionally, the number of model parameters was reduced by 29.45%. This study provides a new intelligent method for the classification of high-temperature stress levels of tea seedlings, as well as state detection and identification, and provides new theoretical support and technical reference for the monitoring and prevention of tea plants and other crops in tea gardens under high temperatures.
Why it matches plant phenotyping methods高温ストレス下の茶苗について、クロロフィル蛍光画像からFv/Fmを用いてストレス状態を分類・検出するYOLOモデルを開発・改良しており、植物状態の画像ベース表現型取得が中心である。
abstractthis study proposes an improved YOLOv11 model based on chlorophyll fluorescence imaging technology for intelligent identification
Tea is one of the most widely consumed non-alcoholic beverages globally, yet its yield and quality are significantly impacted by herbivory from tea geometrids. To accurately detect herbivory stress in tea leaves, this study integrated metabolomics with visible-near-infrared spectroscopy (VIS-NIRS) to explore its in situ capabilities and underlying mechanisms. The results demonstrated that metabolomic data, combined with PCA-based linear dimensionality reduction, could effectively distinguish between tea leaves subjected to herbivory by different densities of tea geometrids. VIS-NIRS successfully identified herbivore-damaged leaves, achieving an optimal average classification accuracy of 0.857. Furthermore, VIS-NIRS was able to differentiate leaves subjected to herbivory on different days. The application of appropriate preprocessing techniques significantly enhanced temporal classification, achieving the highest average classification accuracy of 0.773. By integrating metabolomics and spectral band analysis, the spectral range of 800–2500 nm was found to more accurately identify leaves exposed to herbivory for a prolonged period. Compared to using the full spectrum, the model built within this wavelength range improved classification accuracy by 10%. In conclusion, this study provides a solid theoretical foundation for the in situ, rapid detection of tea geometrid herbivory stress in the field using VIS-NIRS, offering key technical support for future applications.
Why it matches plant phenotyping methodsVIS-NIRSを用いて茶葉の食害ストレスを直接推定し、前処理・波長選択・分類精度を評価する手法研究であり、植物状態の取得方法が中心的です。
abstractTo accurately detect herbivory stress in tea leaves, this study integrated metabolomics with visible-near-infrared spectroscopy (VIS-NIRS) to explore its in situ capabilities and underlying mechanisms.
TeaRaman / spectroscopyLeafPhysiological trait estimationWater status / transpiration
Moisture significantly affects tea plants' growth and quality. Traditional methods of leaf moisture detection are usually destructive to samples, slow and labour-intensive. In this study, visible-near infrared (VIS-NIR) spectroscopy was used to detect the moisture content of tea leaves quickly and accurately in the spectral range of 500-870 nm. The experimental materials are "Longjing 43″, which are divided into two batches. The first batch consists of 135 tea samples collected in April 2022, and the second batch includes 349 tea samples collected in April 2024.The FD + SNV + CARS + ε-SVR model had the best prediction effect on the moisture content of tea leaf in 2024, with the prediction effects of R c , R p , RMSEC, RMSEP and RPD being 0.9676, 0.903, 0.0221, 0.04 and 2.3367, respectively. However, the prediction result R P of the constructed model applied to the 2022 data was only 0.138. In order to improve the generalisation of the model, this study proposes stacking ensemble learning and instance-based transfer learning. In particular, the transfer learning model only needed 55 transfer samples, and the R P was the highest at 0.851. Compared with the stacking ensemble, which required 60 samples, the R P was the highest at 0.85, which realised the use of fewer samples to achieve a better prediction effect. These studies not only confirmed the potential of VIS-NIR spectroscopy to assess the moisture content of tea leaves but also investigated the transfer optimisation of the model, which was helpful to improve the generalisation ability of the model.
Why it matches plant phenotyping methodsVIS-NIR分光法と転移学習モデルにより茶葉の水分含量という植物形質を非破壊推定し、モデル性能と汎化を検証しているため、表現型取得・推定手法が中心である。
abstractvisible-near infrared (VIS-NIR) spectroscopy was used to detect the moisture content of tea leaves quickly and accurately
Tea is an extremely popular beverage around the world due to its exquisite taste and flavor. Unfortunately, it is prone to different types of illness, which can reduce the amount of harvest along with its standard. Among these, leaf infections are a serious concern since they negatively affect the quality of tea leaves. As a consequence, tea producers often encounter a great deal of obstacles and financial losses. Keeping this in mind, a thorough dataset has been compiled, which contains 5278 images of diseased and healthy leaves. The purpose of this dataset is to improve our knowledge of how these conditions impact cultivating tea plants and tea production. These images are collected from a variety of locations and meteorological circumstances, which provide an extensive knowledge of the disease patterns unique to tea leaves. The pictures have been captured with the help of some high-quality devices from different angles and in high resolution to ensure the standard and increase the usability of the dataset. Rigorous steps were followed when preparing the dataset that would be of great help in building a precise artificial intelligence model. The dataset carefully determined and classified six tea leaf diseases: Tea algal leaf spot, Brown Blight, Gray Blight, Helopeltis, Red spider, and Green mirid bug. There is one more class in the dataset containing images of healthy leaves. These illnesses are known for their devastating impact on tea leaves. An automated disease classification system can be made utilizing deep learning techniques that will enable estate managers to take timely action to stop the spread of the disease, and this meticulously collected dataset will immensely help to train that model.
Why it matches plant phenotyping methods茶葉の健全・病害状態を画像で収集・分類した再利用可能なデータセットであり、植物病害状態の画像ベース表現型計測を中心とする。
abstracta thorough dataset has been compiled, which contains 5278 images of diseased and healthy leaves
Reproduction assets foundThe paper's own teaLeafBD image dataset (5278 tea leaf images, 7 classes) is publicly deposited on Mendeley Data with an explicit DOI and direct URL, making it a paper-specific, publicly actionable asset.Dataset · public24.30795976, longitude: 91.73760171),
7.
Finlay Tea Estate in Sreemangal (latitude: 24.30357177, longitude: 91.74245382),
8.
Jungle Bari Tea Estate in Sreemangal (latitude: 24.25329433, longitude: 91.77409053)
Data accessibility
Repository name: Mendeley Data
Data identification number: 10.17632/744vznw5k2.4
Direct URL to data: https://data.mendeley.com/datasets/744vznw5k2/4
Related research article
None
1.
Value of the Data
•
The dataset was collected from tea harvesting areas in Bangladesh, which is one of the top tea-producing regions in the world, supplying tea globally. A total of 5278 images were captured by the camera from eight tea gardens, and they were annotated by human experts.
•Open asset ↗Mendeley Data · 10.17632/744vznw5k2.4lines:1-60Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Tea diseases can significantly impact crop yield and quality, necessitating accurate and efficient recognition methods. This study presents WaveLiteNet, a lightweight model designed for tea disease recognition, addressing the challenge of inadequate disease feature extraction in existing approaches. By integrating 2D discrete wavelet transform (DWT) with MobileNetV3, the model enhances noise suppression and feature extraction through an adaptive thresholding strategy in the 2D DWT. The extracted frequency-domain features are fused with depth features from the Bneck structure, enabling a more comprehensive representation of disease characteristics. To further optimize feature extraction, a convolutional block attention module (CBAM) is incorporated within the Bneck structure, refining the network's ability to assign optimal weights to feature channels. A focal loss function also replaces traditional cross-entropy loss to mitigate sample category imbalance, improving recognition accuracy across varying distributions. Experimental results show that WaveLiteNet achieves a 98.70% recognition accuracy on five types of tea leaf diseases, with a parameter count of 3.16 × 10⁶. Compared to MobileNetV3, this represents a 2.15 percentage point improvement in accuracy while reducing the parameter count by 25.12%. These findings underscore WaveLiteNet's potential as a highly efficient and lightweight real-time crop disease recognition solution, particularly in resource-constrained agricultural environments.
Why it matches plant phenotyping methods茶葉の葉に現れる病徴を画像から認識するCNN手法の開発・評価が中心であり、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 presents WaveLiteNet, a lightweight model designed for tea disease recognition, addressing the challenge of inadequate disease feature extraction in existing approaches.
In this study, we introduce a groundbreaking deep learning (DL) model designed for the precise task of classifying common diseases in tea leaves, leveraging advanced image analysis techniques. Our model is distinguished by its complex multi-layer architecture, crafted to adeptly handle 256 × 256 pixel images across three color channels (RGB). Beginning with an input layer complemented by a Zero Padding 2D layer to preserve spatial dimensions, our model ensures the retention of crucial geographical information across its depth. The innovative use of a convolutional layer with 64 7 × 7 filters, followed by batch normalization and Rel U activation, allows for the extraction and representation of intricate patterns from the input data. Key to our model's design is the incorporation of residual blocks, facilitating the learning of deeper networks by alleviating the vanishing gradient problem. These blocks combine Conv2D layers, batch normalization, activation layers, and shortcut connections, ensuring robust and efficient feature extraction at various levels of abstraction. The GlobalAveragePooling2D layer towards the model's end succinctly summarizes the extracted features, preparing the model for the final classification stage. This stage features a dropout layer for regularization, a dense layer with 512 units for further pattern learning, and a final dense layer with 8 units and a soft max activation function, producing a probability distribution across different disease classes. Our model's architecture is not just a testament to the sophistication of modern deep learning techniques but also highlights the novelty of applying such complex structures to the challenges of agricultural disease detection. We utilized a datasets consisting of 4000 high-resolution images of tea leaves, encompassing both diseased and healthy states, meticulously captured in the tea gardens of Pathantula, Sylhet, Bangladesh. Employing the Canon EOS 250d Camera ensured detailed representation crucial for training a robust deep learning model for disease detection in tea plants. By achieving remarkable accuracy in identifying diseases in tea leaves, this research not only sets a new benchmark for precision in agricultural diagnostics but also opens avenues for future innovations in the field of precision agriculture.
Why it matches plant phenotyping methods茶葉画像から病害状態をCNNで分類する手法の開発が中心であり、植物の病害状態を直接推定する画像ベース・フェノタイピング研究である。
titleTowards precision agriculture tea leaf disease detection using CNNs and image processing.
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.
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 · UnverifiedEurope PMC · checked 15 Sept 2026
The diseases of tea leaves have a significant impact on their quality and yield, making the rapid identification of leaf diseases in tea crucial for prevention and control. We propose an LBPAttNet model, incorporating a lightweight coordinate attention mechanism into ResNet18 to enhance disease localization and reduce background interference. Furthermore, we employ the local binary patterns (LBP) algorithm to further extract local structural and textural features of tea leaf diseases, and integrate deep features to obtain a more comprehensive feature representation. Additionally, we utilize the focal loss function to alleviate the issues of class imbalance and varying difficulty levels in tea leaf disease, thereby further enhancing the accuracy of tea disease recognition. Our model achieves an accuracy of 92.78% and 98.13% on two publicly available tea disease datasets, surpassing ResNet18 by 3.84% and 2.59% respectively. Compared to traditional algorithms such as AlexNet, GoogleNet, MobileNet, VGG16, and other tea disease recognition algorithms, our model also shows significant improvements. These results highlight the superior performance and robustness of our model.
Why it matches plant phenotyping methods茶葉の病徴を画像から認識するCNNと特徴抽出手法を開発し、公開データセットで性能評価しているため、植物病害状態のフェノタイピング手法が中心である。
abstractWe propose an LBPAttNet model, incorporating a lightweight coordinate attention mechanism into ResNet18 to enhance disease localization and reduce background interference.
Rapid and accurate plant phenotyping is vital to plant breeding and monitoring. Hyperspectral imaging (HSI) is the popular phenotypic technique to acquire spectral and spatial information of plants. However, the close-range HSI of plant canopies is greatly affected by the complex interaction of canopy geometry with illumination, which leads to biased or contaminated spectral information. Thus, the mitigation of these effects is imperative but challenging. In this study, a three-dimensional (3D) spectral compensation method on close-range canopy HSI was proposed, to correct the reflectance of canopies affected by imaging distance and leaf angle. First, the hyperspectral and depth images of canopies were registered and fused to generate hyperspectral 3D point clouds. Next, the full-spectrum reflectance on canopies was compensated based on the depth and angle information provided by the hyperspectral 3D point clouds. Then, the performance of spectral compensation results was evaluated by cluster analysis, spectral curve validation, and chlorophyll regression. Results on two plant types (perilla and tea seedlings) showed that after spectral compensation, the reflectance variations within canopies reduced greatly, the reflectance of whole canopies became more homogeneous, with a dominant cluster accounting for over 67% pixels of canopies. And using the mean reflectance curves of in vitro flattened leaves as the reference, the canopy reflectance after compensation were closer to the reference level, that the Euclidean Distance (ED) between them reduced by 50.6%. The determination coefficient (R²) for chlorophyll regression after compensation reached 0.75, increasing about 17% compared to that before compensation. The overall results demonstrated that the proposed 3D spectral compensation method was effective in mitigating the effects of imaging distance and leaf angle on plant canopies in close-range HSI. This could further facilitate the revelation of plant optical characteristics, which is of high significance for the accurate close-range plant phenotyping.
Why it matches plant phenotyping methods植物キャノピーの近接ハイパースペクトル画像に対する3Dスペクトル補償法を開発し、複数の評価で性能検証しており、表現型取得・抽出手法が研究の中心である。
abstractIn this study, a three-dimensional (3D) spectral compensation method on close-range canopy HSI was proposed, to correct the reflectance of canopies affected by imaging distance and leaf angle.
Rapid and non-destructive detection methods for the withering degree of fresh tea leaves are crucial for ensuring high-quality tea production. Therefore, this study proposes a fresh tea withering degree detection model based on image classification confidence. The moisture percentage of fresh tea leaves is calculated by developing a weighted method that combines confidence levels and moisture labels, and the degree of withering is ultimately determined by incorporating the standard for wilted moisture content. To enhance the feature extraction ability and classification accuracy of the model, we introduce the Receptive-Field Attention Convolution (RFAConv) and Cross-Stage Feature Fusion Coordinate Attention (C2f_CA) modules. The experimental results demonstrate that the proposed model achieves a classification accuracy of 92.7%. Compared with the initial model, the detection accuracy was improved by 0.156. In evaluating the predictive performance of the model for moisture content, the correlation coefficients (Rp), root mean square error (RMSEP), and relative standard deviation (RPD) of category 1 in the test set were 0.9983, 0.006278, and 39.2513, respectively, and all performance were significantly better than PLS and CNN methods. This method enables accurate and rapid detection of tea leaf withering, providing crucial technical support for online determination during processing.
Why it matches plant phenotyping methods画像分類の信頼度から茶葉の萎凋度と含水率を推定する手法を開発・評価しており、植物器官の状態を画像から定量化する方法が中心です。
abstractthis study proposes a fresh tea withering degree detection model based on image classification confidence.
Tea (Camellia sinensis L.) holds agricultural economic value and forestry carbon sequestration potential, with Taiwan’s annual tea production exceeding TWD 7 billion. However, climate change-induced stressors threaten tea plant growth, photosynthesis, yield, and quality, necessitating an accurate real-time monitoring system to enhance plantation management and production stability. This study surveys tea plantations at low, mid-, and high elevations in Nantou County, central Taiwan, collecting data from 21 fields using conventional farming methods (CFMs), which emphasize intensive management, and agroecological farming methods (AFMs), which prioritize environmental sustainability. This study integrates leaf area index (LAI), photochemical reflectance index (PRI), and quantum yield of photosystem II (ΦPSII) data with unmanned aerial vehicles (UAV)-derived visible-light and multispectral imagery to compute color indices (CIs) and multispectral indices (MIs). Using feature ranking methods, an optimized dataset was developed, and the predictive performance of eight regression algorithms was assessed for estimating tea plant physiological parameters. The results indicate that LAI was generally lower in AFMs, suggesting reduced leaf growth density and potential yield differences. However, PRI and ΦPSII values revealed greater environmental adaptability and potential long-term ecological benefits in AFMs compared to CFMs. Among regression models, MIs provided greater stability for tea plant physiological parameters, whereas feature ranking methods had minimal impact on accuracy. XGBoost outperformed all models in predicting parameters, achieving optimal results for (1) LAI: R2 = 0.716, RMSE = 1.01, MAE = 0.683, (2) PRI: R2 = 0.643, RMSE = 0.013, MAE = 0.009, and (3) ΦPSII: R2 = 0.920, RMSE = 0.048, MAE = 0.013. Overall, we highlight the effectiveness of integrating gradient boosting models with multispectral data to capture tea plant physiological characteristics. This study develops generalizable predictive models for tea plant physiological parameter estimation and advances non-contact crop physiological monitoring for tea plantation management, providing a scientific foundation for precision agriculture applications.
Why it matches plant phenotyping methodsUAV画像・マルチスペクトルデータと機械学習により、茶植物のLAI、PRI、ΦPSIIを推定する非接触フェノタイピング手法を開発・評価しており、方法が研究の中心です。
abstractUsing feature ranking methods, an optimized dataset was developed, and the predictive performance of eight regression algorithms was assessed for estimating tea plant physiological parameters.
In-situ rapid detection of biophysical parameters in tea leaves using spectral data is essential for enhancing the quality and yield of tea. However, a major challenge with the current application of spectral technology is its inability to completely distinguish between old leaves and picked leaves within the field of view, which affects the accurate correspondence of biochemical elements. Therefore, this study achieved precise matching of biophysical parameters with spectral information by focusing on the spectra of picked leaves. By combining the Excess Green minus Excess Red (ExGR) with the image segmentation methods of Otsu and P75, the spectral features of picked leaves were effectively identified from complex backgrounds. Additionally, the vegetation indices (VIs) closely associated with the biophysical parameters of tea were selected, and a partial least squares regression (PLSR) model was applied for parameter inversion. Results demonstrated that the VIs calculated using Otsu (VI_OtsuPix) and P75 (VI_P75Pix) exhibited significantly improved correlations with the biophysical parameters of tea compared with those calculated using ExGR > 0 (GreenPix). The PLSR model based on VI_OtsuPix performed well in estimating the total polyphenols (TPP), achieving a coefficient of determination (R²) of 0.39 and a root mean square error (RMSE) of 32.24 mg g⁻¹. In predicting free amino acids (FAA), VI_P75Pix demonstrated the best inversion accuracy (R² = 0.53, RMSE = 3.41 mg g⁻¹). These findings not only confirmed the potential of integrated image technology in the non-destructive assessment of biophysical components in picked leaves but also provide the tea production and processing industry with a fast and cost-effective method for quality monitoring.
Why it matches plant phenotyping methods茶葉の抽出・分割とスペクトル情報を統合し、葉の生理・生化学的形質を推定する画像ベース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含める。
abstractBy combining the Excess Green minus Excess Red (ExGR) with the image segmentation methods of Otsu and P75, the spectral features of picked leaves were effectively identified from complex backgrounds.
The economic development of many countries largely depends on tea plantations that suffer from diseases adversely affecting their productivity and quality. This study presents a high-resolution dataset aimed at advancing precision agriculture for managing tea garden diseases. The size of the dataset is 3960 images and pixel dimension is (1024 × 1024) of the images were collected by using smartphones. This dataset contains detailed images of Tea Leaf Blight, Tea Red Leaf Spot and Tea Red Scab maladies inflicted on tea leaves as well as environmental statistics and plant health. The images were captured and stored in JPG format. The main aim of this dataset is to provide tool for detection and classification of different types of tea garden disease. Applying this dataset will enable the development of early detection systems, best-practice care regimens, and enhanced general garden upkeep. A range of images presenting the most prevalent diseases afflicting tea plants are paired with images of healthy leaves to provide a comprehensive overview of all the circumstances that can arise in a tea plantation. Therefore, it can be used to automate diseases tracking, targeted pesticide spraying, and even the making of smart farm tools with development of smart agricultural tools hence enhancing sustainability and efficiency in tea production. This dataset not only provides a strong foundation for applying precision techniques in tea cultivation in agriculture, but also can become an invaluable asset to scientists studying the issues of tea production.
Why it matches plant phenotyping methods茶葉の病害状態を画像で記録したデータセットであり、植物病害の画像ベース表現型評価を支えるデータ資源が中心です。
abstractThis study presents a high-resolution dataset aimed at advancing precision agriculture for managing tea garden diseases.
Reproduction assets foundThe paper is a Data in Brief article describing a tea leaf disease image dataset (3960 original images, 4000 augmented) publicly deposited on Mendeley Data with an explicit DOI and direct URL. This is a paper-specific, public, actionable plant-phenotyping asset (plant images used for disease classification phenotyping)Dataset · publicar, Sylhet, Bangladesh. The project was conducted under the supervision of an expert from Bangladesh's Ministry of Agriculture.
Data source location
Location: Moulvi Bazar tea garden,Sylhet
Country: Bangladesh
Data accessibility
Repository name: Mendeley Data
Data identification number: 10.17632/tt2smzrzrs.4
Direct URL to data: https://data.mendeley.com/datasets/tt2smzrzrs/4
Related research article
None
1
Value of the Data
•
Tea is a major global agricultural crop with economic implications as well as cultural significance. This drink is famous for diverse tastes and health benefits. In many civilizations, tea remains their main beverage [ 1 ]. There are several countries that supply most oOpen asset ↗Mendeley Data · 10.17632/tt2smzrzrs.4lines:1-51Plant phenotyping relevance match · UnverifiedEurope PMC · checked 14 Sept 2026
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.
Nitrogen and phosphorus are essential nutrients for the growth and development of tea plants.However, the nitrogen content (NC) and phosphorus content (PC) in different parts of fresh tea has not been paid attention. In this study, the NC and PC responses different nitrogen stress were analyzed, and a quantitative regression model for predicting NC and PC was established by using Vis/NIR spectroscopy and a variety of intelligent algorithms. Among them, NC and PC of different parts had significant difference. The selection of preprocessing algorithms has a significant impact on the predictive performance of the model. The VMDSG-D1-VCPA-IRIV-SVR prediction model for NC and the VMDSG-CARS-Stacking prediction model for PC have better prediction effects, and the correlation coefficients of the test set are more than 0.85, and the RPD is greater than 1.8. In conclusion, this study is helpful to guide the precise fertilization and in-situ detection of fresh tea leaves.
Why it matches plant phenotyping methods茶葉の窒素・リン含量という植物器官形質をVis/NIR分光と回帰モデルで推定する手法を開発し、テストセットで性能検証しているため、方法が中心です。
abstracta quantitative regression model for predicting NC and PC was established by using Vis/NIR spectroscopy and a variety of intelligent algorithms.
Addressing the challenge of identifying tea plant diseases against the complex background of tea gardens, this study proposes the ECA-ResNet50 model. By optimizing the ResNet50 architecture, adopting a multi-layer small convolution kernel strategy to enhance feature extraction capabilities, and introducing the ECA attention mechanism to focus on key features, the model achieves a 93.06% accuracy rate in tea disease identification, representing a 3.18% improvement over the original model, demonstrating industry-leading performance advantages. This model not only accurately identifies tea diseases in gardens but also possesses excellent generalization capabilities, performing outstandingly on datasets of other plant categories. These results indicate that ECA-ResNet50 can effectively mitigate the interference of complex backgrounds and precisely recognize tea disease targets.
Why it matches plant phenotyping methods茶葉の病害を画像から識別する深層学習モデルを開発し、精度比較と汎化性能を評価しており、植物病害状態の取得・推定手法が中心である。
abstractthis study proposes the ECA-ResNet50 model.
Reproduction assets foundThe paper's tea disease image dataset (885 images, seven disease types plus healthy leaves) is a public Kaggle dataset explicitly cited by the authors with URL. No author analysis code or trained model checkpoints are stated as publicly available; the data availability statement only offers raw data on request.Dataset · publica wide variety of diseases, totaling approximately over 140 types, which are widely distributed across various parts of the tea plants, including leaves, stems, roots, and flowers ( Chen, 2022 ). Given the limitations of experimental conditions, this study collected a total of 885 images of tea diseases through search engines ( https://www.kaggle.com/datasets/shashwatwork/identifying-disease-in-tea-leafs ). After meticulous identification and classification by authoritative experts, these images were categorized into seven distinct types of leaf diseases, as well as healthy leaves. The seven disease types are algae leaf spot, anthracnose, bird’s eye spot, cloud blotch, gray spot, red leaf spOpen asset ↗Kaggle · shashwatwork/identifying-disease-in-tea-leafslines:33-59Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Abstract has not been obtained from indexed metadata or an accessible article page.
Why it matches plant phenotyping methodsUAVスペクトル画像と機械学習により茶樹の成長を非破壊モニタリングする手法が題名の中心であり、植物形質の取得・推定を主題としている。
titleNon-destructive monitoring of tea plant growth through UAV spectral imagery and meteorological data using machine learning and parameter optimization algorithms
Traditional methods for estimating tea yield mainly rely on manual sampling surveys and empirical estimation, which are labor-intensive and time-consuming. Accurately estimating fresh tea production in different seasons has become a challenging task. It is possible to estimate the seasonal yield of tea at the field scale by using the spatial resolution of 10 m, 5-day revisit period and rich spectral information of Sentinel-2 imagery. This study integrated Sentinel-2 images and uncrewed aerial vehicle (UAV) RGB imagery to develop six regression models at the field scale, which were employed for the estimation of seasonal and annual fresh tea yields of the Yunlong Tea Cooperatives in Yixiang Town, Pu'er City, China. Firstly, we gathered fresh tea production data from 133 farmers in the cooperative over the past five years and obtained UAV RGB and Sentinel-2 imagery. Secondly, 23 spectral features were extracted from Sentinel-2 images. Based on the UAV images, the parcel of each farmer was positioned and three topographic features of slope, aspect, and elevation were extracted. Subsequently, these 26 features were screened using the random forest algorithm and Pearson correlation analysis. Thirdly, we applied six different regression algorithms to establish fresh tea yield models for each season and evaluated their estimation accuracy. The results showed that random forest regression models were the optimal choice for estimating spring and summer yields, with the spring model achieving an R 2 value of 0.45, an RMSE of 40.38 kg/acre, and an rRMSE of 40.79%. Similarly, the summer model achieved an R 2 value of 0.5, an RMSE of 78.46 kg/acre, and an rRMSE of 39.81%. For autumn and annual yield estimation, voting regression models demonstrated superior performance, with the autumn model achieving an R 2 value of 0.42, an RMSE of 70.6 kg/acre, and an rRMSE of 39.77%, and the annual model attained an R 2 value of 0.47, an RMSE of 168.7 kg/acre, and an rRMSE of 34.62%. This study provides a promising new method for estimating fresh tea yield in different seasons at the field scale.
Why it matches plant phenotyping methodsUAV RGB・Sentinel-2画像と複数の回帰モデルを用いて、圃場・農家区画レベルの茶収量を推定する手法を開発・評価しており、植物の収量形質の取得・推定が中心である。
abstractThis study integrated Sentinel-2 images and uncrewed aerial vehicle (UAV) RGB imagery to develop six regression models at the field scale, which were employed for the estimation of seasonal and annual fresh tea yields
Introduction Accurate detection and recognition of tea bud images can drive advances in intelligent harvesting machinery for tea gardens and technology for tea bud pests and diseases. In order to realize the recognition and grading of tea buds in a complex multi-density tea garden environment. Methods This paper proposes an improved YOLOv7 object detection algorithm, called YOLOv7-DWS, which focuses on improving the accuracy of tea recognition. First, we make a series of improvements to the YOLOv7 algorithm, including decouple head to replace the head of YOLOv7, to enhance the feature extraction ability of the model and optimize the class decision logic. The problem of simultaneous detection and classification of one-bud-one-leaf and one-bud-two-leaves of tea was solved. Secondly, a new loss function WiseIoU is proposed for the loss function in YOLOv7, which improves the accuracy of the model. Finally, we evaluate different attention mechanisms to enhance the model's focus on key features. Results and discussion The experimental results show that the improved YOLOv7 algorithm has significantly improved over the original algorithm in all evaluation indexes, especially in the R Tea (+6.2%) and mAP@0.5 (+7.7%). From the results, the algorithm in this paper helps to provide a new perspective and possibility for the field of tea image recognition.
Why it matches plant phenotyping methods茶芽画像から芽の種類・葉数を認識および等級化する改良物体検出法を開発し、性能評価しており、植物器官の状態推定が中心である。
abstractThis paper proposes an improved YOLOv7 object detection algorithm, called YOLOv7-DWS, which focuses on improving the accuracy of tea recognition.
Camellia sinensis is a widely cultivated crop that is harvested for two leaves and a bud. However, these soft tissues are highly susceptible to the infection known as Exobasidium vexans. This fungal disease reduces the quality and quantity of tea produced. The objective of the study was to develop a remote sensing‐based model that could be used to predict the severity of blister blight infections. The study was conducted on five tea varieties susceptible to blister blight infections and the hyperspectral data were collected from leaves with a handheld instrument. Spectral preprocessing algorithms that included Puchwein's and Honig's were applied to select calibration sets and perform feature selection, respectively. Four machine learning algorithms that included artificial neural network (ANN), random forest, k‐nearest neighbors, and support vector machine were compared. The result indicated that the ANN outperformed other machine learning models, achieving a training accuracy of 83% (kappa coefficient = 0.78) and a testing accuracy of 92% (kappa coefficient = 0.90). The classification model was tested on another set of Kangra Asha tea leaves, resulting in a classification accuracy of 90% (kappa coefficient = 0.86). Thus, machine learning methods provided a novel technique to identify blister blight disease in the tea crop.
Why it matches plant phenotyping methods茶葉の病害重症度をハイパースペクトル計測と機械学習で推定する手法を開発・比較・検証しており、植物状態の取得が研究の中心です。
abstractThe objective of the study was to develop a remote sensing‐based model that could be used to predict the severity of blister blight infections.
In 2022, China experienced a historically rare compound drought–heatwave (CDH) event, which had more severe impacts on vegetation compared with individual extreme events. However, quantitatively mapping the damage severity of CDH on tea tree using satellite data remains a significant challenge. Here we proposed a novel framework for dynamic and quantitative mapping of tea trees damage severity caused by CDH in 2022 using Sentinel-2 and Unmanned Aerial Vehicle (UAV) data. The Extreme Gradient Boosting (XGBoost) was selected as the optimal machine learning algorithm to extract tea plantations using Sentinel-2 data from XGBoost, Random Forest (RF), Logistic regression (LR), and Naive Bayes. The User’s Accuracy and Producer’s Accuracy for the extraction of tea plantations are 92.20 % and 93.51 %, respectively. UAV images with 2.5 cm spatial resolution were utilized to detect the tea trees damaged caused by the CDH in 2022. A new index, named the CDH damage severity index (CDH_DSI), was proposed to quantitatively evaluate the damage severity of CDH on tea trees at pixel level, with a spatial resolution of 10 m x 10 m. Based on the results of tea plantations and damaged tea trees detection, UAV-derived CDH_DSI was calculated and used as ground truth data. Then, The XGBoost was selected as the optimal CDH_DSI prediction model from XGBoost, RF, and LR with the Sentnel-2 derived vegetation indices and spectral reflectance as predictors. The coefficient of determination was 0.81 and root mean squared error was 7.61 %. Finally, dynamic and quantitative CDH_DSI maps were generated with the optimal CDH_DSI prediction model. The results show that 50 percent of tea plantations in Wuyi were damaged by the prolonged CDH event in 2022. These results can be attributed to precipitation deficits and heatwaves. Given that more severe CDH events are projected for the future, quantifying their impacts can provide decision-making support for disaster mitigation and prevention.
Why it matches plant phenotyping methodsUAV・衛星画像から茶樹の被害状態を定量推定する手法とCDH被害重症度指標を開発・検証しており、植物フェノタイピングが中心である。
abstractA new index, named the CDH damage severity index (CDH_DSI), was proposed to quantitatively evaluate the damage severity of CDH on tea trees at pixel level
Tea (Camellia sinensis) has a long history in China, and the tea industry plays a crucial role in the national economy. Tea diseases can lead to the reduction of tea yield and reduce the quality of tea. Accurate and rapid identification of these diseases can help prevent and manage them effectively, significantly reducing production losses. However, manual recognition of tea diseases is costly, slow and subject to subjective factors. This paper proposes a deep learning‐based tea disease recognition method in natural environment: referred to as YOLOv8‐tea disease. The tea disease dataset in natural environment was made by ourselves. YOLOv8s is the baseline model. The VoVGSCSP module and efficient multi‐scale attention module were introduced into YOLOv8s to improve the training speed and recognition accuracy of the model. To reduce the number of model parameters, Cross Stage Partial GhostNet Layer was used in the backbone network instead of C2f. Wise‐IoU loss is used as a loss function to solve the problem of inaccurate detection caused by low image quality and improve the generalization ability of the model. Finally, in the dataset of tea diseases, the proposed method achieved an mAP@0.5 (where mAP is mean average precision) of 96.34%. The number of model parameters was reduced to 8.81 M, and the number of floating point operations was reduced to 20.3 G. Compared to the original YOLOv8s model, mAP@0.5 increased by 5.08%, the number of parameters decreased by 26.14%, and the detection speed was the fastest, with the frame per second reaching 153.3.
Why it matches plant phenotyping methods茶葉の病害状態を自然環境画像から検出するYOLOv8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が中心的な技術貢献である。
abstractThis paper proposes a deep learning‐based tea disease recognition method in natural environment: referred to as YOLOv8‐tea disease.
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
Introduction The detection efficiency of tea diseases and defects ensures the quality and yield of tea. However, in actual production, on the one hand, the tea plantation has high mountains and long roads, and the safety of inspection personnel cannot be guaranteed; on the other hand, the inspection personnel have factors such as lack of experience and fatigue, resulting in incomplete and slow testing results. Introducing visual inspection technology can avoid the above problems. Methods Firstly, a dynamic sparse attention mechanism (Bi Former) is introduced into the model backbone. It filters out irrelevant key value pairs at the coarse region level, utilizing sparsity to save computation and memory; jointly apply fine region token to token attention in the remaining candidate regions. Secondly, Haar wavelets are introduced to improve the down sampling module. By processing the input information flow horizontally, vertically, and diagonally, the original image is reconstructed. Finally, a new feature fusion network is designed using a multi-head attention mechanism to decompose the main network into several cascaded stages, each stage comprising a sub-backbone for parallel processing of different features. Simultaneously, skip connections are performed on features from the same layer, and unbounded fusion weight normalization is introduced to constrain the range of each weight value. Results After the above improvements, the confidence level of the current mainstream models increased by 7.1%, mAP0.5 increased by 8%, and reached 94.5%. After conducting ablation experiments and comparing with mainstream models, the feature fusion network proposed in this paper reduced computational complexity by 10.6 GFlops, increased confidence by 2.7%, and increased mAP0.5 by 3.2%. Discussion This paper developed a new network based on YOLOv8 to overcome the difficulties of tea diseases and defects such as small target, multiple occlusion and complex background.
Why it matches plant phenotyping methods茶葉の病害・欠損を画像から検出するYOLOv8改良モデルを開発し、アブレーション実験と既存モデル比較で性能検証しているため、植物表現型取得法が中心です。
abstractIntroducing visual inspection technology can avoid the above problems.
Tea bud detection plays a crucial role in early-stage tea production estimation and robotic harvesting, significantly advancing the integration of computer vision and agriculture. Currently, tea bud detection faces several challenges such as reduced accuracy due to high background similarity, and the large size and parameter count of the models, which hinder deployment on mobile devices. To address these issues, this study introduces the lightweight Tea Bud DG model, characterized by the following features: 1) The model employs a Dynamic Head (DyHead), which enhances tea bud feature extraction through three types of perceptual attention mechanisms-scale, spatial, and task awareness. Scale awareness enables the model to adapt to objects of varying sizes; spatial awareness focuses on discriminative regions to distinguish tea buds against complex backgrounds; task awareness optimizes feature channels for specific tasks, such as classification or localization of tea buds. 2) A lightweight C3ghost module is designed, initially generating basic feature maps with fewer filters, followed by simple linear operations (e.g., translation or rotation) to create additional "ghost" feature maps, thus reducing the parameter count and model size, facilitating deployment on lightweight mobile devices. 3) By introducing the α-CIoU loss function with the parameter α, the loss and gradient of objects with different IoU scores can be adaptively reweighted by adjusting the α parameter. This approach emphasizes objects with higher IoU, enhancing the ability to identify tea buds in environments with high background similarity. The use of α-CIoU focuses on accurately differentiating tea buds from surrounding leaves, improving detection performance. The experimental results show that compared with YOLOv5s, the Tea Bud DG model reduces the model size by 31.41 % and the number of parameters by 32.21 %. Compared with YOLOv7_tiny, the size and parameters are reduced by 18.94 % and 23.84 %, respectively. It achieved improvements in mAP@0.5 by 3 %, 3.9 %, and 5.1 %, and in mAP@0.5_0.95 by 2.6 %, 3.2 %, and 4 % compared with YOLOv5s, YOLOv8s, and YOLOv9s, respectively. The Tea Bud DG model estimates the tea yield with an error range of 10 % to 16 %, providing valuable data support for tea plantation management.
Why it matches plant phenotyping methods茶芽を画像から検出・計数し収量推定に用いる軽量な深層学習モデルを開発し、既存モデルとの性能・サイズ比較を行っており、植物器官の表現型取得法が中心である。
abstractThe experimental results show that compared with YOLOv5s, the Tea Bud DG model reduces the model size by 31.41 % and the number of parameters by 32.21 %.
Recognition of tea plant variety and grade is essential for tea germplasm resources protection. The rapid and accurate acquisition of phenotype of tea leaves is a crucial step in exploring the variety type, nutrition status, and yield prediction. Monitoring the phenotypic characteristics of tea leaves is necessary for intelligent tea germplasm management. This study analyzed phenotypic features of tea leaves based on multispectral imaging technology. Tea leaf images of 12242 sets from 25 different types, along with 61 groups of chemical characteristics of fresh tea leaves were obtained. A total of 92 indicators were extracted, and 38 indicators were screened using the successive projection algorithm and the shuffled frog leaping algorithm, which showed significant differences among different tea varieties. The phenotypic indexes of different tea varieties were analyzed, and a tea variety recognition model was established based on these indexes combined with gray wolf optimization-support vector machine algorithm. The average accuracy of the training, test, and validation sets were 99.74 %, 92.17 %, and 91.56 %, respectively. Additionally, quantitative evaluation for tea plant germplasm resources was explored. Stepwise Fisher discriminant analysis was used to identify the 61 tea plant germplasm resources, achieving an accuracy of 93.44 % with the discrimination accuracy of each grade is above 90 %.
Why it matches plant phenotyping methodsマルチスペクトル画像から茶葉の表現型指標を抽出・選択し、品種認識と遺伝資源評価に利用する解析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として含める。
abstractThe rapid and accurate acquisition of phenotype of tea leaves is a crucial step in exploring the variety type, nutrition status, and yield prediction.
Abstract As major pests in tea plantations, Matsumurasca onukii Matsuda (Hemiptera: Cicadellidae) and Dendrothrips minowai Priesner (Thysanoptera: Thripidae) reduce tea yields and cause large economic loss. Host plant resistance is one of the most effective and economical potential pest management strategies but is not well understood in tea. This study aimed to screen tea lines to determine chemical and structural traits that were associated with resistance to both herbivore species and then develop comprehensive resistance indicators and evaluation model of insect resistance. In addition, we modelled host plant identification and selection by the two pests and established resistance grading criteria for each. Traits positively associated with resistance to M. onukii were: concentrations of nonanal and dodecane, epidermal thickness of adaxial leaf surface, and ratio of this to leaf thickness. Negatively associated traits were: concentrations of malonic dialdehyde and linalool, ratio of adaxial leaf cuticle thickness to leaf thickness, and ratio of abaxial cuticle thickness to leaf thickness. For D. minowai , length of leaf, trichome density of buds, and caffeine content were positively associated with resistance; whilst dodecane and phenethyl alcohol concentrations as well as several color parameters of foliage were negatively associated. To comprehensively evaluate the insect resistance of tea cultivars, the affiliation function method was used and the results of the model showed significantly correlation for observed population densities of both pests. This study provides the first comprehensive framework for host plant resistance traits and will underpin risk assessment among existing cultivars and selection in future plant breeding programs.
Why it matches plant phenotyping methods茶品種の害虫抵抗性を示す化学・構造形質を統合し、抵抗性指標、評価モデル、等級基準を開発しているため、形質評価手法が研究の中心である。
abstractThis study aimed to screen tea lines to determine chemical and structural traits that were associated with resistance to both herbivore species and then develop comprehensive resistance indicators and evaluation model of insect resistance.
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.
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
In the context of climate change, extreme weather events, represented by frost injury, are increasingly having a negative impact on the growth of tea plants. This has brought huge losses to the tea industry. Traditionally, the freezing injury of tea plants in the field was assessed by vision. This is labor-intensive and subjective. In this research, multimodal remote sensing data from different periods of natural overwintering tea plantations were collected by using unmanned aerial vehicles (UAV) equipped with multispectral (MS), thermal infrared (TIR) and RGB sensors. And the physiological data of tea leaves on the same day were obtained to construct a tea cold injury score (TCIS). Then, a convolutional neural networks-gate recurrent unit (CNN-GRU) model was improved for estimating TCIS. To better compare the performance of CNN-GRU, a single GRU model and three classical machine learning models were also used for comparison. The study found that: (1) The multimodal data fusion was superior to the unimodal data. The best prediction results were achieved for the combined bimodal MS + RGB data (Rp² = 0.862, RMSEP = 0.138, RPD = 2.220); (2) The CNN-GRU hybrid model was superior to the other four baseline models. The best effect was achieved based on the multivariate input of MS + RGB (Rp² = 0.862) or MS + RGB + TIR (Rp² = 0.850); (3) The accuracy of the model after removing soil features was lower than that of the model without background removal. Therefore, the TCIS-CNN-GRU model combined with multi-source remote sensing data can objectively and accurately evaluate the cold injury phenotype of tea plants, making the CNN-GRU model more scientific and promising.
Why it matches plant phenotyping methodsUAVマルチセンサー画像から茶樹の凍害表現型を推定する取得・計算手法を開発し、複数モデルと比較検証しており、フェノタイピング手法が中心である。
abstractmultimodal remote sensing data from different periods of natural overwintering tea plantations were collected by using unmanned aerial vehicles (UAV) equipped with multispectral (MS), thermal infrared (TIR) and RGB sensors.
The estimation of tea leaf pose is an emerging research topic. Recognising the morphological features of tea leaves can help accurately categorise, grade, and determine their level of maturity. Therefore, this study proposes a deep neural network, TeaPoseNet, to estimate tea leaf poses. The algorithm was trained and validated using a dataset of one-bud-one-leaf images of Yinghong No.9 tea leaves and was compared with four other pose estimation networks. At the same time, the contribution of TKS_NMS to the algorithm was validated through ablation experiments. The results indicate that TKS_NMS improved the EPE accuracy of pose recognition by 16.33 %. More specifically, the algorithm achieved a good overall performance, with PCK, AUC, EPE, and NME reaching 0.9800, 0.8147, 9.0955, and 0.0644, respectively. The average running speed for detecting the pose of a single tea leaf image was 40.01 ms. To the best of our knowledge, this is the first application of pose estimation technology to the detection and analysis of Yinghong No.9 tea leaves. The results show that the proposed algorithm can effectively estimate the pose of tea leaves, thus providing a reference for subsequent tea research.
Why it matches plant phenotyping methods茶葉の葉姿勢という植物形態形質を画像から推定する深層学習手法を開発し、データセット、比較評価、アブレーション検証、性能指標を提示しており、植物フェノタイピング手法が研究の中心である。
abstractTherefore, this study proposes a deep neural network, TeaPoseNet, to estimate tea leaf poses.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Rapid and non-destructive estimation of tea plant growth and nitrogen (N) nutrition status using hyperspectral remote sensing is crucial for precise management of tea gardens. This study aimed to mine and fuse sensitive hyperspectral features to achieve an accurate estimation of tea plant growth parameters (biomass and N accumulation) throughout the whole year. An ASD Handheld 2 sensor was used to collect canopy hyperspectral reflectance of tea plants across four periods (Period 1–4) within a year, with tea plant biomass and N accumulation indicators acquired synchronously. The measured spectral reflectance and its first derivative, and wavelet feature were extracted and used to establish quantitative relationships with tea plant growth parameters. Random forest and LASSO algorithms were employed to combine sensitive hyperspectral features and construct the biomass and N accumulation monitoring models. The results showed that wavelet features (R² = 0.35–0.58) had a stronger correlation with tea plant biomass and N accumulation parameters compared with the measured reflectance or first derivative spectral features. Similarly, the hyperspectral indices (R² = 0.51–0.69) derived from sensitive wavelet features performed an accurate estimation of tea plant growth parameters. Furthermore, the combination of sensitive hyperspectral indices derived from measured reflectance, first derivative, and wavelet feature using random forest (R² = 0.67–0.76) and LASSO (R² = 0.61–0.72) algorithms achieved the greatest accuracy for monitoring tea plant biomass and N accumulation compared with individual hyperspectral feature. Additionally, the above estimation models obtained higher accuracy in period 4 compared to periods 1–3. This study provides valuable remote sensing technical support for predicting biomass and N accumulation status of tea plant throughout the whole year.
Why it matches plant phenotyping methods茶植物のバイオマスと窒素蓄積を対象に、ハイパースペクトル特徴量の抽出・融合と推定モデル構築を中心的に扱う植物フェノタイピング手法研究である。
abstractThis study aimed to mine and fuse sensitive hyperspectral features to achieve an accurate estimation of tea plant growth parameters (biomass and N accumulation) throughout the whole year.
Accurate detection of tea leaf diseases and insects is crucial for their scientific and effective prevention and control, essential for ensuring the quality and yield of tea. Traditional methods for identifying tea leaf diseases and insects primarily rely on professional technicians, which are difficult to apply in various scenarios. This study proposes a recognition method for tea leaf diseases and insects based on improved MobileNetV3. Initially, a dataset containing images of 17 different types of tea leaf diseases and insects was curated, with data augmentation techniques utilized to broaden recognition scenarios. Subsequently, the network structure of MobileNetV3 was enhanced by integrating the CA (coordinate attention) module to improve the perception of location information. Moreover, a fine-tuning transfer learning strategy was employed to optimize model training and accelerate convergence. Experimental results on the constructed dataset reveal that the initial recognition accuracy of MobileNetV3 is 94.45%, with an F1-score of 94.12%. Without transfer learning, the recognition accuracy of MobileNetV3-CA reaches 94.58%, while with transfer learning, it reaches 95.88%. Through comparative experiments, this study compares the improved algorithm with the original MobileNetV3 model and other classical image classification models (ResNet18, AlexNet, VGG16, SqueezeNet, and ShuffleNetV2). The findings show that MobileNetV3-CA based on transfer learning achieves higher accuracy in identifying tea leaf diseases and insects. Finally, a tea diseases and insects identification application was developed based on this model. The model showed strong robustness and could provide a reliable reference for intelligent diagnosis of tea diseases and insects.
Why it matches plant phenotyping methods茶葉画像から病害（植物の状態）を分類する画像・計算手法の開発、データセット構築、比較評価が研究の中心であり、植物病害表現型の取得に該当する。
abstractThis study proposes a recognition method for tea leaf diseases and insects based on improved MobileNetV3.
Early non-destructive detection of stress effect is crucial for efficient breeding strategies and germplasm characterization. Recently developed hyperspectral technologies allow to perform fast real-time phenotyping through reflectance-based vegetation indices. However, efficiency of these vegetation indices has to be validated for each crop in different environment. The aim of this study was to reveal efficient vegetation indices for phenotyping of abiotic stress (cold, freezing and nitrogen deficiency) response in tea plant. Among 31 studied VIs, few indices were efficient to distinguish tolerant and susceptible tea plants under abiotic stress: ZMI (Zarco-Tejada & Miller Index), VREI1,2,3 (Vogelmann Red Edge Indices), RENDVI (Red Edge Normalized Difference Vegetation Index), CTR1 and CTR2 (Carter Indices). Most of these indices are calculated based on reflectance in near-infrared area at 705-760 nm, indicating this range as promising for tea germplasm characterization under abiotic stresses. Tolerant tea plants showed the following values under freezing: ZMI ≥1.90, VREI1 ≥ 1.40, RENDVI ≥0.38, Ctr1 ≤ 1.74. The leaf N-content was positively correlated (Pearson's) with the following indices ZMI, VREI1, RENDVI, while negatively correlated with CTR, and VREI2,3. These results will be useful for tea germplasm management, genomics and breeding research aimed at abiotic stress tolerance of tea plant.
Why it matches plant phenotyping methods茶植物の非破壊ハイパースペクトル指標を用いたストレス表現型評価が研究の中心で、複数の植生指数の有効性を検証している。
abstractRecently developed hyperspectral technologies allow to perform fast real-time phenotyping through reflectance-based vegetation indices.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 7 Sept 2026
TeaMultispectral / hyperspectralGrowth / development / phenologyStress response / tolerance
Rapid detection of plant phenotypic traits is crucial for plant breeding and cultivation. Traditional measurement methods are carried out by rich-experienced agronomists, which are time-consuming and labor-intensive. However, with the increasing demand for rapid and high-throughput testing in tea plants traits, digital breeding and smart cultivation of tea plants rely heavily on precise plant phenotypic trait measurement techniques, among which hyperspectral imaging (HSI) technology stands out for its ability to provide real-time and rich-information. In this paper, we provide a comprehensive overview of the principles of hyperspectral imaging technology, the processing methods of cubic data, and relevant algorithms in tea plant phenomics, reviewing the progress of applying hyperspectral imaging technology to obtain information on tea plant phenotypes, growth conditions, and quality indicators under environmental stress. Lastly, we discuss the challenges faced by HSI technology in the detection of tea plant phenotypic traits from different perspectives, propose possible solutions, and envision the potential development prospects of HSI technology in the digital breeding and smart cultivation of tea plants. This review aims to provide theoretical and technical support for the application of HSI technology in detecting tea plant phenotypic information, further promoting the trend of developing high quality and high yield tea leaves.
Why it matches plant phenotyping methods茶植物のハイパースペクトル画像による表現型取得技術を体系的にレビューしており、植物フェノタイピング手法が中心である。
abstractIn this paper, we provide a comprehensive overview of the principles of hyperspectral imaging technology, the processing methods of cubic data, and relevant algorithms in tea plant phenomics, reviewing the progress of applying hyperspectral imaging technology to obtain information on tea plant phenotypes
Traditional leaf chlorophyll estimation using Soil Plant Analysis Development (SPAD) devices and spectrophotometers is a high-cost mechanism in agriculture. Recently, research on chlorophyll estimation using leaf camera images and machine learning has been seen. However, these techniques use self-defined image color combinations where the system performance varies, and the potential utility has not been well explored. This paper proposes a new method that combines an improved contact imaging technique, the images’ original color parameters, and a 1-D Convolutional Neural Network (CNN) specifically for tea leaves’ chlorophyll estimation. This method utilizes a smartphone and flashlight to capture tea leaf contact images at multiple locations on the front and backside of the leaves. It extracts 12 different original color features, such as the mean of RGB, the standard deviation of RGB and HSV, kurtosis, skewness, and variance from images for 1-D CNN input. We captured 15,000 contact images of tea leaves, collected from different tea gardens across Assam, India to create a dataset. SPAD chlorophyll measurements of the leaves are included as true values. Other models based on Linear Regression (LR), Artificial Neural Networks (ANN), Support Vector Regression (SVR), and K-Nearest Neighbor (KNN) were also trained, evaluated, and tested. The 1-D CNN outperformed them with a Mean Absolute Error (MAE) of 2.96, Mean Square Error (MSE) of 15.4, Root Mean Square Error (RMSE) of 3.92, and Coefficient of Regression (R2) of 0.82. These results show that the method is a digital replication of the traditional method, while also being non-destructive, affordable, less prone to performance variations, and simple to utilize for sustainable agriculture.
Why it matches plant phenotyping methodsスマートフォン画像と1-D CNNによる茶葉クロロフィル推定法を開発・評価しており、植物生理形質の取得が研究の中心である。
abstractThis paper proposes a new method that combines an improved contact imaging technique, the images’ original color parameters, and a 1-D Convolutional Neural Network (CNN) specifically for tea leaves’ chlorophyll estimation.
Background Breeding programs for nutrient-efficient tea plant varieties could be advanced by the combination of genotyping and phenotyping technologies. This study was aimed to search functional SNPs in key genes related to the nitrogen-assimilation in the collection of tea plant Camellia sinensis (L.) Kuntze. In addition, the objective of this study was to reveal efficient vegetation indices for phenotyping of nitrogen deficiency response in tea collection. Methods The study was conducted on the tea plant collection of Camellia sinensis (L.) Kuntze of Western Caucasus grown without nitrogen fertilizers. Phenotypic data was collected by measuring the spectral reflectance of leaves in the 350-1100 nm range calculated as vegetation indices by the portable hyperspectral spectrometer Ci710s. Single nucleotide polymorphisms were identified in 30 key genes related to nitrogen assimilation and tea quality. For this, pooled amplicon sequencing, SNPs annotation and effect prediction with SnpEFF tool were used. Further, a linear regression model was applied to reveal associations between the functional SNPs and the efficient vegetation indices. Results PCA and regression analysis revealed significant vegetation indices with high R2 values (more than 0.5) and the most reliable indices to select ND-tolerant genotypes were established: ZMI, CNDVI, RENDVI, VREI1, GM2, GM1, PRI, and Ctr2, VREI3, VREI2. The largest SNPs frequency was observed in several genes, namely F3'5'Hb , UFGTa , UFGTb , 4Cl , and AMT1.2 . SNPs in NRT2.4 , PIP , AlaDC , DFRa , and GS1.2 were inherent in ND-susceptible genotypes. Additionally, SNPs in AlaAT1 , MYB4 , and WRKY57 , were led to alterations in protein structure and were observed in ND-susceptible tea genotypes. Associations were revealed between flavanol reflectance index (FRI) and SNPs in ASNb and PIP , that change the amino acids. In addition, two SNPs in 4Cl were associated with water band index (WBI). Conclusions The results will be useful to identify tolerant and susceptible tea genotypes under nitrogen deficiency. Revealed missense SNPs and associations with vegetation indices improve our understanding of nitrogen effect on tea quality. The findings in our study would provide new insights into the genetic basis of tea quality variation under the N-deficiency and facilitate the identification of elite genes to enhance tea quality.
Why it matches plant phenotyping methods携帯型ハイパースペクトル分光計による葉の反射スペクトルから窒素欠乏応答を表す植生指数を算出し、耐性遺伝子型の選抜に有効な指数を評価・確立しており、表現型取得法の応用が中心的に含まれる。
abstractthe objective of this study was to reveal efficient vegetation indices for phenotyping of nitrogen deficiency response in tea collection.
Background The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan Big leaf kind of tea within its complex ecological niche. Results Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 98.58% and a verification accuracy rate of 98.2310%. Conclusions These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan.
Why it matches plant phenotyping methods茶葉画像から病害・害虫状態を認識するCNN手法の開発・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対象範囲に含める。
abstractthe present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests
Rapidly evaluating tea bud quality and diagnosing nitrogen status is crucial for optimizing nitrogen fertilization and enhancing tea quality. This study analyzed how key quality components (free amino acids (AA), tea polyphenols (TP), and the ratio of tea polyphenols to amino acids (RTA)) in tea buds from six varieties responded to nitrogen fertilizer. We also examined relationships between pigment levels (chlorophyll A (CA), chlorophyll B (CB) and carotenoids (TC)) and quality components across varieties. For quality estimation, our custom convolutional neural network (CNN) model, TeabudNet, offered superior prediction of TP, AA, and RTA (Rp values 0.924, 0.936, and 0.962 respectively) compared to traditional machine learning approaches. For nitrogen status diagnosis, we assessed RTA as an indicator of quality and nitrogen status, determining optimal nitrogen rates and thresholds delineating deficiency, sufficiency and excess for each variety. A ResNet-18 model reliably classified nitrogen status in tea buds and powder with 92–96% accuracy. This study provides robust technical support for optimizing nitrogen management and controlling quality during tea production.
Why it matches plant phenotyping methods茶芽を対象に、近赤外分光とCNNによる品質成分推定および窒素状態診断手法を開発・評価しており、植物状態の取得・推定が研究の中心である。
titleData-driven optimization of nitrogen fertilization and quality sensing across tea bud varieties using near-infrared spectroscopy and deep learning
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).
Traditional estimation of tea yield significantly depends on fields observation, which is facing operational and management challenges due to increasing farm sizes and rising labor costs. Development of artificial intelligence such as deep learning (DL) and unmanned aerial vehicles (UAVs) provide opportunities where intelligent system of tea fields will be constructed. This study carried out the application of tea yield estimation model to practical field scenarios. A large dataset of UAV tea buds’ images was built, which contained 5899 images and 29,958 labelled tea buds. Based on the large dataset, YOLOv5 model was used to train, and CSPDarknet53 performed best over Swin Transformer and ConvNeXt as backbone. The mean average precision (mAP), precision, recall and F1 score of CSPDarknet53 were respectively 85.63%, 84.91%,72.19% and 78.00%. Meanwhile, the large database weakened the differences among models of different sizes. Squeeze-and-excitation (SE) block was inserted, and the mAP of all models with CSPDarknet53 and SE was over 85.00%, indicating models could be applied to tea fields. To reduce the number of repeated tea bud detection boxes in the prediction process, a second non-maximum suppression (NMS) filter was used with threshold value of 0.20. The yield of fresh tea leaves before and after picking was estimated according to the number of tea buds detected in different seasons and different types of tea plants. The yield of fresh tea leaves in spring before picking was estimated to 1223.22 kg/ha. This study is a complete report from model training to tea field application, and will advance the industrialization development of agriculture.
Why it matches plant phenotyping methodsUAV画像から茶芽を検出し、検出数に基づいて茶葉収量を推定する深層学習手法を開発・評価し、圃場適用まで扱っており、植物形質取得が研究の中心である。
abstractA large dataset of UAV tea buds’ images was built, which contained 5899 images and 29,958 labelled tea buds.
To address the issues of low accuracy and slow response speed in tea disease classification and identification, an improved YOLOv7 lightweight model was proposed in this study. The lightweight MobileNeXt was used as the backbone network to reduce computational load and enhance efficiency. Additionally, a dual-layer routing attention mechanism was introduced to enhance the model's ability to capture crucial details and textures in disease images, thereby improving accuracy. The SIoU loss function was employed to mitigate missed and erroneous judgments, resulting in improved recognition amidst complex image backgrounds.The revised model achieved precision, recall, and average precision of 93.5%, 89.9%, and 92.1%, respectively, representing increases of 4.5%, 1.9%, and 2.6% over the original model. Furthermore, the model's volum was reduced by 24.69M, the total param was reduced by 12.88M, while detection speed was increased by 24.41 frames per second. This enhanced model efficiently and accurately identifies tea disease types, offering the benefits of lower parameter count and faster detection, thereby establishing a robust foundation for tea disease monitoring and prevention efforts.
Why it matches plant phenotyping methods茶葉の病害画像から病状を推定するYOLOv7改良モデルの開発・性能評価が中心であり、植物の病害状態を対象とする画像ベース表現型計測に該当する。
abstractan improved YOLOv7 lightweight model was proposed in this study
Reproduction assets foundThe paper's data availability statement says all data and code are available on GitHub and provides an authors' public URL for the improved YOLOv7 code, which matches an allowed URL. The tea disease image dataset itself is referenced but no explicit dataset URL is supplied, so only the code asset qualifies.Code · publicAll data generated or analysed during this study are available in the Github repository. Links to the code and datasets are provided in the below hyperlinked text. Code of Improved YOLOv7 project: https://github.com/anqi99/yolov7.gitOpen asset ↗https://github.com/anqi99/yolov7.gitlines:192-263Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
The primary challenges in tea production under multiple stress exposures have negatively affected its global market sustainability, so introducing an infield fast technique for monitoring tea leaves' stresses has tremendous urgent needs. Therefore, this study aimed to propose an efficient method for the detection of stress symptoms based on a portable smartphone with deep learning models. Firstly, a database containing over 10,000 images of tea garden canopies in complex natural scenes was developed, which included healthy (no stress) and three types of stress (tea anthracnose (TA), tea blister blight (TB) and sunburn (SB)). Then, YOLOv5m and YOLOv8m algorithms were adapted to discriminate the four types of stress symptoms; where the YOLOv8m algorithm achieved better performance in the identification of healthy leaves (98%), TA (92.0%), TB (68.4%) and SB (75.5%). Furthermore, the YOLOv8m algorithm was used to construct a model for differentiation of disease severity of TA, and a satisfactory result was obtained with the accuracy of mild, moderate, and severe TA infections were 94%, 96%, and 91%, respectively. Besides, we found that CNN kernels of YOLOv8m could efficiently extract the texture characteristics of the images at layer 2, and these characteristics can clearly distinguish different types of stress symptoms. This makes great contributions to the YOLOv8m model to achieve high-precision differentiation of four types of stress symptoms. In conclusion, our study provided an effective system to achieve low-cost, high-precision, fast, and infield diagnosis of tea stress symptoms in complex natural scenes based on smartphone and deep learning algorithms.
Why it matches plant phenotyping methodsスマートフォン画像と深層学習により、茶葉のストレス症状および病害重症度を直接推定する手法を開発・評価しており、植物表現型取得が中心である。
abstractthis study aimed to propose an efficient method for the detection of stress symptoms based on a portable smartphone with deep learning models.
Taking the AquaCrop crop model as the research object, considering the complexity and uncertainty of the crop growth process, the crop model can only achieve more accurate simulation on a single point scale. In order to improve the application scale of the crop model, this study inverted the canopy coverage of a tea garden based on UAV multispectral technology, adopted the particle swarm optimization algorithm to assimilate the canopy coverage and crop model, constructed the AquaCrop-PSO assimilation model, and compared the canopy coverage and yield simulation results with the localized model simulation results. It is found that there is a significant regression relationship between all vegetation indices and canopy coverage. Among the single vegetation index regression models, the logarithmic model constructed by OSAVI has the highest inversion accuracy, with an R 2 of 0.855 and RMSE of 5.75. The tea yield was simulated by the AquaCrop-PSO model and the measured values of R 2 and RMSE were 0.927 and 0.12, respectively. The canopy coverage R 2 of each simulated growth period basically exceeded 0.9, and the accuracy of the simulation results was improved by about 19.8% compared with that of the localized model. The results show that the accuracy of crop model simulation can be improved effectively by retrieving crop parameters and assimilating crop models through UAV remote sensing.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から茶園の樹冠被覆率を推定し、作物モデルへ同化する手法が研究の中心であり、植物形質の取得・検証を実施している。
abstractthis study inverted the canopy coverage of a tea garden based on UAV multispectral technology
In response to the challenge of low recognition rates for similar phenotypic symptoms of tea diseases in low-light environments and the difficulty in detecting small lesions, a novel adaptive method for tea disease severity detection is proposed. This method integrates an image enhancement algorithm based on an improved EnlightenGAN network and an enhanced version of YOLO v8. The approach involves first enhancing the EnlightenGAN network through non-paired training on low-light-intensity images of various tea diseases, guiding the generation of high-quality disease images. This step aims to expand the dataset and improve lesion characteristics and texture details in low-light conditions. Subsequently, the YOLO v8 network incorporates ResNet50 as its backbone, integrating channel and spatial attention modules to extract key features from disease feature maps effectively. The introduction of adaptive spatial feature fusion in the Neck part of the YOLOv8 module further enhances detection accuracy, particularly for small disease targets in complex backgrounds. Additionally, the model architecture is optimized by replacing traditional Conv blocks with ODConv blocks and introducing a new ODC2f block to reduce parameters, improve performance, and switch the loss function from CIOU to EIOU for a faster and more accurate recognition of small targets. Experimental results demonstrate that YOLOv8-ASFF achieves a tea disease detection accuracy of 87.47% and a mean average precision (mAP) of 95.26%. These results show a 2.47 percentage point improvement over YOLOv8, and a significant lead of 9.11, 9.55, and 7.08 percentage points over CornerNet, SSD, YOLOv5, and other models, respectively. The ability to swiftly and accurately detect tea diseases can offer robust theoretical support for assessing tea disease severity and managing tea growth. Moreover, its compatibility with edge computing devices and practical application in agriculture further enhance its value.
Why it matches plant phenotyping methods茶樹病害の病斑・重症度を低照度画像から推定する画像解析手法を開発・評価しており、植物状態の取得が研究の中心である。
abstracta novel adaptive method for tea disease severity detection is proposed.
Abstract Tea, a globally cultivated crop renowned for its unique flavor profile and health-promoting properties, ranks among the most favored functional beverages worldwide. However, pests and diseases severely jeopardize the production and quality of tea leaves, leading to significant economic losses.While early and accurate identification coupled with the removal of infected leaves can mitigate widespread infection, manual leaves removal remains time-consuming and expensive. To address this challenge, this paper introduces the YOLO-DBD network model for detecting of harmful tea leaves. The model excels in efficiently identifying harmful tea leaves with various poses in complex backgrounds, providing crucial guidance for the posture and obstacle avoidance of a robotic arm during the pruning process.The improvements proposed in this study encompass the C2f-DCN module, Bi-Level Routing Attention, Dynamic Head, and Focal-CIoU Loss function, enhancing the model's feature extraction, computation allocation, and perception capabilities. Comparative analysis with the YOLOv8s model demonstrates a 6% improvement in mAP and a reduction of 3.3G FLOPs in the YOLO-DBD model.
Why it matches plant phenotyping methods有害茶葉の画像検出モデルを開発し、病害・障害状態の直接的な推定を行う技術が研究の中心であるため、植物表現型計測手法として含める。
abstractthis paper introduces the YOLO-DBD network model for detecting of harmful tea leaves.
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.
Background: The occurrence, development, and outbreak of tea diseases and pests pose a significant challenge to the quality and yield of tea, necessitating prompt identification and control measures. Given the vast array of tea diseases and pests, coupled with the intricacies of the tea planting environment, accurate and rapid diagnosis remains elusive. In addressing this issue, the present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests. Our objective is to facilitate the accurate and expeditious detection of diseases and pests affecting the Yunnan big-leaf sun-dried green tea within its complex ecological niche. Results Initially, we gathered 1878 image data encompassing 10 prevalent types of tea diseases and pests from complex environments within tea plantations, compiling a comprehensive dataset. Additionally, we employed data augmentation techniques to enrich the sample diversity. Leveraging the ImageNet pre-trained model, we conducted a comprehensive evaluation and identified the Xception architecture as the most effective model. Notably, the integration of an attention mechanism within the Xeption model did not yield improvements in recognition performance. Subsequently, through transfer learning and the freezing core strategy, we achieved a test accuracy rate of 99.17% and a verification accuracy rate of 96.3889%. Conclusions These outcomes signify a significant stride towards accurate and timely detection, holding promise for enhancing the sustainability and productivity of Yunnan tea. Our findings provide a theoretical foundation and technical guidance for the development of online detection technologies for tea diseases and pests in Yunnan.
Why it matches plant phenotyping methods茶葉の病害を画像から認識・検出するCNN手法の開発と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対象範囲に含める。害虫認識も含むが、病害フェノタイピング手法として技術的評価が明確である。
abstractthe present study investigates the utilization of transfer learning convolution neural networks for the identification of tea diseases and pests
This study employs a deep-learning method, Y-Net, to estimate 10 tea flavor-related chemical compounds (TFCC), including gallic acid, caffeine and eight catechin isomers, using fresh tea shoot reflectance and transmittance. The unique aspect of Y-Net lies in its utilization of dual inputs, reflectance and transmittance, which are seamlessly integrated within the Y-Net architecture. This architecture harnesses the power of a convolutional neural network-based residual network to fuse tea shoot spectra effectively. This strategic combination enhances the capacity of the model to discern intricate patterns in the optical characteristics of fresh tea shoots, providing a comprehensive framework for TFCC estimation. In this study, we destructively sampled tea shoots from tea farms in Alishan (Ali-Mountain) in Central Taiwan within the elevation range of 879–1552 m a.s.l. Tea shoot reflectance and transmittance data (n = 2032) within the optical region (400–2500 nm) were measured using a portable spectroradiometer and pre-processed using an algorithm; corresponding TFCC were qualified using the high-performance liquid chromatography analysis. To enhance the robustness and performance of Y-Net, we employed data augmentation techniques for model training. We compared the performances of Y-Net and seven other commonly utilized statistical, machine-/deep-learning models (partial least squared regression, Gaussian process, cubist, random forests and three feedforward neural networks) using root-mean-square error (RMSE). Furthermore, we assessed the prediction accuracies of Y-Net and Y-Net using spectra within the visible and near-infrared (VNIR) regions (for higher energy throughput and low-cost instruments) and reflectance only (for airborne and spaceborne remote sensing applications). The results showed that overall Y-Net (mean RMSE ± standard deviation [SD] = 2.51 ± 2.20 mg g −1 ) outperformed the other statistical, machine- and deep-learning models (≥ 2.59 ± 2.64 mg g −1 ), demonstrating its superiority in predicting TFCC. In addition, this original Y-Net also yielded slightly lower mean RMSE (± SD) compared with VNIR (2.76 ± 2.41 mg g −1 ) and reflectance-only (2.68 ± 2.74 mg g −1 ) Y-Nets using validation data. This study highlights the feasibility of using spectroscopy and Y-Net to assess minor biochemical components in fresh tea shoots and sheds light on the potential of the proposed approach for effective regional monitoring of tea shoot quality.
Why it matches plant phenotyping methods茶の新芽を対象に、反射・透過スペクトルと深層学習モデルで化学的品質形質を推定する手法を開発・比較検証しており、形質取得・推定法が研究の中心である。
abstractThis study employs a deep-learning method, Y-Net, to estimate 10 tea flavor-related chemical compounds (TFCC)
In the natural tea plantation environment, the accurate detection of multi-size and multi-target tea bud leaves within a wide field of view is essential for successful tea picking. However, the detection task is challenging due to factors such as the targets have a high resemblance to the background color, and the size of tea varies across different varieties and growth conditions. Additionally, there are numerous targets in the field of view, all of which contribute to the increased difficulty in detecting tea bud leaves. To address these challenges, this paper presents a novel method for the detection of tea bud leaves. The method incorporates a selective kernel attention mechanism in the Backbone network to enhance the ability to extract morphological features. Then a new multi-feature fusion module is introduced to combine different local features and integrate them with global features, capturing both local and global dependencies, and enabling comprehensive and distinct feature representation. Furthermore, an effective loss function is employed to calculate the loss values for class probability and objective score, penalizing false detections and missed detections during the training process. The experimental results demonstrate that the proposed model improved YOLOv7 achieves superior detection performance and robustness, with a recall rate of 84.95%, precision of 90.99%, and average precision of 94.43%. These values are approximately 10% higher compared to the original YOLOv7 model. The detection network can accurate detection of tea bud leaves in tea plantation environments.
Why it matches plant phenotyping methods茶芽葉を対象とした画像検出ネットワークの開発が中心で、植物器官の形態特徴を抽出し、野外での検出性能を評価しているため、植物フェノタイピング手法として含める。
abstractTo address these challenges, this paper presents a novel method for the detection of tea bud leaves.
In light of the prevalent issues concerning the mechanical grading of fresh tea leaves, characterized by high damage rates and poor accuracy, as well as the limited grading precision through the integration of machine vision and machine learning (ML) algorithms, this study presents an innovative approach for classifying the quality grade of fresh tea leaves. This approach leverages an integration of image recognition and deep learning (DL) algorithm to accurately classify tea leaves' grades by identifying distinct bud and leaf combinations. The method begins by acquiring separate images of orderly scattered and randomly stacked fresh tea leaves. These images undergo data augmentation techniques, such as rotation, flipping, and contrast adjustment, to form the scattered and stacked tea leaves datasets. Subsequently, the YOLOv8x model was enhanced by Space pyramid pooling improvements (SPPCSPC) and the concentration-based attention module (CBAM). The established YOLOv8x-SPPCSPC-CBAM model is evaluated by comparing it with popular DL models, including Faster R-CNN, YOLOv5x, and YOLOv8x. The experimental findings reveal that the YOLOv8x-SPPCSPC-CBAM model delivers the most impressive results. For the scattered tea leaves, the mean average precision, precision, recall, and number of images processed per second rates of 98.2%, 95.8%, 96.7%, and 2.77, respectively, while for stacked tea leaves, they are 99.1%, 99.1%, 97.7% and 2.35, respectively. This study provides a robust framework for accurately classifying the quality grade of fresh tea leaves.
Why it matches plant phenotyping methods生鮮茶葉の芽・葉の組合せを画像から認識し品質等級を分類する深層学習手法を開発・比較評価しており、植物器官の状態・品質の取得が中心的な方法論的貢献である。
abstractthis study presents an innovative approach for classifying the quality grade of fresh tea leaves
The degree of production efficiency and the quality of the commodities produced may both be directly impacted by the presence of illnesses in tea leaves. These days, this procedure may be automated with the use of artificial intelligence tools, and a number of approaches have been put out to satisfy these needs. Nonetheless, current research efforts have focused on improving diagnosis accuracy and expanding the variety of illnesses that might affect tea leaves. In this article, a new method is proposed for accurately diagnosing tea leaf diseases using artificial intelligence techniques. In the proposed method, the input images are preprocessed to remove redundant information. Then, a hybrid pooling-based Convolutional Neural Network (CNN) is employed to extract image features. In this method, the pooling layers of the CNN model are randomly adjusted based on either max pooling or average pooling functions. This strategy can enhance the efficiency of the CNN-based feature extraction model. In this method, the pooling layers of the CNN model are randomly adjusted based on either max pooling or average pooling functions. This strategy can enhance the efficiency of the CNN-based feature extraction model. After feature extraction, a weighted Random Forest (WRF) model is used for the detection of tea leaf diseases. The outputs of the decision tree models and their corresponding weights are used to identify tea leaf illnesses in this classification model, where each tree in the random forest is given a weight depending on how well it performs. The Cuckoo Search Optimization (CSO) method is used in the proposed classification model to give a weight to each tree. Tea Sickness Dataset (TSD) has been used as the basis for evaluating the suggested method's effectiveness. The findings show that the suggested approach has an average accuracy of 92.47% in identifying seven different forms of tea leaf illnesses. Additionally, the recall and accuracy metrics indicate results of 92.35 and 92.26, respectively, indicating improvements over earlier techniques.
Why it matches plant phenotyping methods茶葉の画像から病害状態を自動分類する画像解析手法を提案・評価しており、植物病害フェノタイプの取得が中心的な技術貢献である。
abstractIn this article, a new method is proposed for accurately diagnosing tea leaf diseases using artificial intelligence techniques.
Globally, tea production and its quality fundamentally depend on tea leaves which are susceptible to invasion from pathogenic organisms. Precise and early-stage identification of plant foliage diseases is a key element to prevent and control 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 3,330 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 with 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茶葉の病害状態を画像からCNNで自動推定する手法の開発・検証が研究の中心であり、植物表現型（病害状態）の測定に該当する。
abstractThis study focuses on a pragmatic approach for automatically detecting selected tea foliage diseases based on convolutional neural network (CNN).
Leaf spectra (reflectance and transmittance) are key parameters for land surface physical and biogeochemical modeling and are commonly measured using a portable spectroradiometer and an integrating sphere or contact probe with an artificial light source. However, spectral data may be obscured mainly because of water vapor and low signal-to-noise ratios, especially in the shortwave infrared-2 region (SWIR-2, 2001-2500 nm). This erroneous pattern is particularly pronounced in humid conditions, such as in many tropical and subtropical regions, making data unusable in SWIR-2. In this study, we proposed a statistical/mathematical spectral reconstruction approach to retrieve noise-free SWIR-2 fresh green leaf spectra by referring to the available previously published quality-controlled fresh green leaf reflectance and transmittance reference databases. We processed 896 pairs of fresh tea (Camellia sinensis var. sinensis) leaf reflectance and transmittance data from Alishan in central Taiwan. The spectral data were acquired by a field spectroradiometer with an integrating sphere. We selected a subset (500-1900 nm) of the spectra in the visible, near-infrared, and SWIR-1 regions (VNS-1) that was relatively insensitive to atmospheric conditions. Then, we applied a Gaussian fitting function to smooth the spectral profile. We matched those spectra with publicly available, quality-controlled, and Gaussian fitting function smoothed reference green leaf spectral databases obtained from Italy (LOPEX), Panama (SLZ), and Puerto Rico (G-LiHT) (1694 reflectance and 997 transmittance samples) and selected the one that was most similar (yielding the highest correlation coefficient) to each smoothed Alishan VNS-1 spectrum. We then used multivariable linear regression, linear parameter multiplication, and spectral reversion to reconstruct SWIR-2 spectra based on VNS-1 spectra. To assess the validity of the proposed SWIR-2 reconstruction method, we acquired an independent set of green leaf spectral databases from France (Angers) with SWIR-2 of 2001- 2450 nm. We found that the performance of the SWIR-2 reconstruction approach was satisfactory, with mean ({+/-} standard deviation) root-mean-square errors (RMSEs) of 0.0041 {+/-} 0.0019 (reflectance, 3.0% of the mean SWIR-2 of the test data) and 0.0054 {+/-} 0.0027 (transmittance, 2.5%) for each spectrum and RMSEs of 0.0058 {+/-} 0.0027 (reflectance, 4.2%) and 0.0055 {+/-} 0.0043 (transmittance, 2.5%) for each SWIR-2 band. The proposed approach successfully modeled SWIR-2 of the test spectra, which could be further improved with the availability of a more comprehensive set of green leaf reference spectral databases.
Why it matches plant phenotyping methods葉のスペクトルを再構成する統計・数学的方法を開発し、独立データで妥当性を検証しており、植物表現型取得・推定が研究の中心です。
abstractwe proposed a statistical/mathematical spectral reconstruction approach to retrieve noise-free SWIR-2 fresh green leaf spectra
As the raw material for tea making, the quality of tea leaves directly affects the quality of finished tea. The quality of fresh tea leaves is mainly assessed by manual judgment or physical and chemical testing of the content of internal components. Physical and chemical methods are more mature, and the test results are more accurate and objective, but traditional chemical methods for measuring the biochemical indexes of tea leaves are time-consuming, labor-costly, complicated, and destructive. With the rapid development of imaging and spectroscopic technology, spectroscopic technology as an emerging technology has been widely used in rapid non-destructive testing of the quality and safety of agricultural products. Due to the existence of spectral information with a low signal-to-noise ratio, high information redundancy, and strong autocorrelation, scholars have conducted a series of studies on spectral data preprocessing. The correlation between spectral data and target data is improved by smoothing noise reduction, correction, extraction of feature bands, and so on, to construct a stable, highly accurate estimation or discrimination model with strong generalization ability. There have been more research papers published on spectroscopic techniques to detect the quality of tea fresh leaves. This study summarizes the principles, analytical methods, and applications of Hyperspectral imaging (HSI) in the nondestructive testing of the quality and safety of fresh tea leaves for the purpose of tracking the latest research advances at home and abroad. At the same time, the principles and applications of other spectroscopic techniques including Near-infrared spectroscopy (NIRS), Mid-infrared spectroscopy (MIRS), Raman spectroscopy (RS), and other spectroscopic techniques for non-destructive testing of quality and safety of fresh tea leaves are also briefly introduced. Finally, in terms of technical obstacles and practical applications, the challenges and development trends of spectral analysis technology in the nondestructive assessment of tea leaf quality are examined.
Why it matches plant phenotyping methods茶葉の品質・安全性という植物器官の状態を、ハイパースペクトル等の分光技術で非破壊推定する方法を体系的にレビューしており、植物フェノタイピング手法が中心です。
abstractThis study summarizes the principles, analytical methods, and applications of Hyperspectral imaging (HSI) in the nondestructive testing of the quality and safety of fresh tea leaves
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
To overcome the constraints associated with conventional approaches used in the classification and detection of tea diseases, which are characterized by their limited accuracy and sluggish responsiveness, this study introduces an enhanced YOLOv7 lightweight model algorithm integrated with MobileNeXt. This refinement not only bolsters the model's capacity for extracting and processing features but also effectively lightens the computational load, expedites recognition, and integrates a dual-layer routing attention mechanism visual converter to enhance the capture of crucial details and textures within disease images. Consequently, these enhancements lead to improved model performance and computational efficiency, ensuring precise and rapid identification of tea diseases. Furthermore, this model incorporates the more appropriate SIoU as the loss function, mitigating losses, minimizing omissions, and reducing misclassifications, thus resulting in superior recognition, even in complex image backgrounds. Based on the training outcomes, the enhanced model attains Precision, Recall and mean Average Precision scores of 93.5%, 89.9%, and 92.1%, respectively, marking substantial enhancements of 5.06%, 2.16%, and 2.91% compared to the original YOLOv7 model. Additionally, the model's size is reduced by 19.12%, and its detection speed accelerates by 11.13%. This improved model excels in accurately and expediting.
Why it matches plant phenotyping methods茶の病害画像から病気を分類・検出するYOLOv7改良モデルの開発と性能評価が中心であり、植物の病害状態を画像ベースで推定するフェノタイピング手法に該当する。
abstractthis study introduces an enhanced YOLOv7 lightweight model algorithm integrated with MobileNeXt
Reproduction assets foundThe paper's Data Availability statement links a public GitHub repository containing the authors' code and tea disease image dataset used to train and evaluate the improved YOLOv7 model.Code · public359 Data Availability
360 Our relevant data are allowed by Yunnan Agricultural University and related bases. All data
361 generated or analysed during this study are available in the Github repository. Links to the code
362 and datasets are provided in the below hyperlinked text. Code and dataset of Improved YOLOv7
363 project: https://github.com/anqi99/yolov7.git.
364
365
366
367 References
368 1. Xue, Z., Xu, R., Bai, D. & Lin, H. Yolo-Tea: A Tea Disease Detection Model Improved by Yolov5.
369 Forests. 14, 415 (2023). https://doi.org/10.3390/f14020415
370 2. Lee, L. K. & Foo, K. Y. Recent Advances On the Beneficial Use and Health Implications of Pu-Erh
12Open asset ↗https://github.com/anqi99/yolov7.gitpdf-layout-page:14 lines:1-46Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Accurate detection of tea diseases is essential for optimizing tea yield and quality, improving production, and minimizing economic losses. In this paper, we introduce TeaDiseaseNet, a novel disease detection method designed to address the challenges in tea disease detection, such as variability in disease scales and dense, obscuring disease patterns. TeaDiseaseNet utilizes a multi-scale self-attention mechanism to enhance disease detection performance. Specifically, it incorporates a CNN-based module for extracting features at multiple scales, effectively capturing localized information such as texture and edges. This approach enables a comprehensive representation of tea images. Additionally, a self-attention module captures global dependencies among pixels, facilitating effective interaction between global information and local features. Furthermore, we integrate a channel attention mechanism, which selectively weighs and combines the multi-scale features, eliminating redundant information and enabling precise localization and recognition of tea disease information across diverse scales and complex backgrounds. Extensive comparative experiments and ablation studies validate the effectiveness of the proposed method, demonstrating superior detection results in scenarios characterized by complex backgrounds and varying disease scales. The presented method provides valuable insights for intelligent tea disease diagnosis, with significant potential for improving tea disease management and production.
Why it matches plant phenotyping methods茶葉画像から病害状態を推定する新規画像解析手法を開発し、比較実験とアブレーションで検証しており、植物病害フェノタイピングが中心です。
abstractwe introduce TeaDiseaseNet, a novel disease detection method designed to address the challenges in tea disease detection
Reproduction assets foundThe article's data availability statement provides a public link to the raw tea disease dataset (776 annotated images used for TeaDiseaseNet training/evaluation). The other allowed URL is a cited prior-work reference, not a paper-specific asset.Dataset · publicons can improve the practicality and effectiveness of tea disease detection systems.
Data availability statement
The original contributions presented in the study are included in the article/supplementary material. Further inquiries can be directed to the corresponding author. The raw data can be accessed at the following link: https://www.jianguoyun.com/p/DRwyMxYQqJnmCxiGl5IFIAA .
Author contributionsOpen asset ↗lines:321-358Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
The rapid detection of quality indicators of fresh tea leaves is helpful to guide tea garden management. Therefore, it is very important to develop a fast and reliable detection method for fresh tea leaf quality indicators. In this study, the feasibility of visible-near-infrared hyperspectral image (VNHI) combined with stoichiometry for the determination of tea polyphenols (TP) and crude fiber (CF) in 14 cultivars of tea plants was investigated. Based on the VNHI, different tea cultivars were distinguished with an accuracy of 99.56% by using one-dimensional ResNet18 (1D-ResNet18). For the quantitative determination of CF and TP contents, the prediction determination coefficient (r²) reached 0.80 and 0.77, respectively, by integrating VNHI with PLS. In addition, we proposed a generalization index (GI) that can evaluate the cross-cultivar generalization ability of models. The GI can judge if the model built on a few tea cultivars can predict the quality indicators of other cultivars. Then, the predicted distribution maps of CF and TP contents were analyzed. The results showed that the quantitative models based on spectra (474–1734 nm) had higher cross-cultivar generalization ability with higher mean GI_0.7 in predicting the cross-cultivar content of CF (mean GI_0.7 = 2.563) and TP (mean GI_0.7 = 1.376). The models based on spectra (474–1030 nm) had stronger visualization ability with lower mean predictive variance. This study proved the feasibility of the VNHI technique in predicting the content of TP and CF of multiple cultivars of tea plants and provided methods with higher generalization, perceptual intuition, and speediness for the detection of quality indicators of tea in the field.
Why it matches plant phenotyping methods茶葉の品質指標を対象に、可視近赤外ハイパースペクトル画像とPLS/ResNetを用いた植物器官の成分推定法を開発・評価し、品種間汎化性能も検証しているため、フェノタイピング手法が中心である。
abstractit is very important to develop a fast and reliable detection method for fresh tea leaf quality indicators.
Background The common tea tree disease known as "tea coal disease" (Neocapnodium theae Hara) can have a negative impact on tea yield and quality. The majority of conventional approaches for identifying tea coal disease rely on observation with the human naked eye, which is labor- and time-intensive and frequently influenced by subjective factors. The present study developed a deep learning model based on RGB and hyperspectral images for tea coal disease rapid classification. Results Both RGB and hyperspectral could be used for classifying tea coal disease. The accuracy of the classification models established by RGB imaging using ResNet18, VGG16, AlexNet, WT-ResNet18, WT-VGG16, and WT-AlexNet was 60%, 58%, 52%, 70%, 64%, and 57%, respectively, and the optimal classification model for RGB was the WT-ResNet18. The accuracy of the classification models established by hyperspectral imaging using UVE-LSTM, CARS-LSTM, NONE-LSTM, UVE-SVM, CARS-SVM, and NONE-SVM was 80%, 95%, 90%, 61%, 77%, and 65%, respectively, and the optimal classification model for hyperspectral was the CARS-LSTM, which was superior to the model based on RGB imaging. Conclusions This study revealed the classification potential of tea coal disease based on RGB and hyperspectral imaging, which can provide an accurate, non-destructive, and efficient classification method for monitoring tea coal disease.
Why it matches plant phenotyping methodsRGB・ハイパースペクトル画像と深層学習により茶樹病害を分類する手法を開発・評価しており、感染植物の病害状態を観測する方法が研究の中心である。
abstractThe present study developed a deep learning model based on RGB and hyperspectral images for tea coal disease rapid classification.
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.
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.
Tea diseases are one of the main causes of tea yield reduction, and the use of computer vision for classification and diagnosis is an effective means of tea disease management. However, the random location of lesions, high symptom similarity, and complex background make the recognition and classification of tea images difficult. Therefore, this paper proposes a tea disease IterationVIT diagnosis model that integrates a convolution and iterative transformer. The convolution consists of a superimposed bottleneck layer for extracting the local features of tea leaves. The iterative algorithm incorporates the attention mechanism and bilinear interpolation operation to obtain disease location information by continuously updating the region of interest in location information. The transformer module uses a multi-head attention mechanism for global feature extraction. A total of 3544 images of red leaf spot, algal leaf spot, bird's eye disease, gray wilt, white spot, anthracnose, brown wilt, and healthy tea leaves collected under natural light were used as samples and input into the IterationVIT model for training. The results show that when the patch size is 16, the model performed better with an IterationVIT classification accuracy of 98% and F1 measure of 96.5%, which is superior to mainstream methods such as VIT, Efficient, Shuffle, Mobile, Vgg, etc. In order to verify the robustness of the model, the original images of the test set were blurred, noise- was added and highlighted, and then the images were input into the IterationVIT model. The classification accuracy still reached over 80%. When 60% of the training set was randomly selected, the classification accuracy of the IterationVIT model test set was 8% higher than that of mainstream models, with the ability to analyze fewer samples. Model generalizability was performed using three sets of plant leaf public datasets, and the experimental results were all able to achieve comparable levels of generalizability to the data in this paper. Finally, this paper visualized and interpreted the model using the CAM method to obtain the pixel-level thermal map of tea diseases, and the results show that the established IterationVIT model can accurately capture the location of diseases, which further verifies the effectiveness of the model.
Why it matches plant phenotyping methods茶葉画像から病斑の位置と病害状態を推定する深層学習モデルを開発し、複数条件・データセットで性能と汎化性を検証しており、植物病害フェノタイピング手法が中心である。
abstractTherefore, this paper proposes a tea disease IterationVIT diagnosis model that integrates a convolution and iterative transformer.
The precise detection and positioning of tea buds are among the major issues in tea picking automation. In this study, a novel algorithm for detecting tea buds and estimating their poses in a field environment was proposed by using a depth camera. This algorithm introduces some improvements to the YOLOv5l architecture. A Coordinate Attention Mechanism (CAM) was inserted into the neck part to accurately position the elements of interest, a BiFPN was used to enhance the small object detection ability, and a GhostConv module replaced the original Conv module in the backbone to reduce the model size and speed up model inference. After testing, the proposed detection model achieved an mAP of 85.2%, a speed of 87.71 FPS, a parameter number of 29.25 M, and a FLOPs value of 59.8 G, which are all better than those achieved with the original model. Next, an optimal pose-vertices search method (OPVSM) was developed to estimate the pose of tea by constructing a graph model to fit the pointcloud. This method could accurately estimate the poses of tea buds, with an overall accuracy of 90%, and it was more flexible and adaptive to the variations in tea buds in terms of size, color, and shape features. Additionally, the experiments demonstrated that the OPVSM could correctly establish the pose of tea buds through pointcloud downsampling by using voxel filtering with a 2 mm × 2 mm × 1 mm grid, and this process could effectively reduce the size of the pointcloud to smaller than 800 to ensure that the algorithm could be run within 0.2 s. The results demonstrate the effectiveness of the proposed algorithm for tea bud detection and pose estimation in a field setting. Furthermore, the proposed algorithm has the potential to be used in tea picking robots and also can be extended to other crops and objects, making it a valuable tool for precision agriculture and robotic applications.
Why it matches plant phenotyping methods茶芽の検出と3D姿勢推定という植物器官の形態・状態を取得する画像／深度センシング手法を開発し、精度・速度を評価しており、フェノタイピング手法が中心である。
abstracta novel algorithm for detecting tea buds and estimating their poses in a field environment was proposed by using a depth camera.
Tea polyphenol and epigallocatechin gallate (EGCG) were considered as key components of tea. The rapid prediction of these two components can be beneficial for tea quality control and product development for tea producers, breeders and consumers. This study aimed to develop reliable models for tea polyphenols and EGCG content prediction during the breeding process using Fourier Transform-near infrared (FT-NIR) spectroscopy combined with machine learning algorithms. Various spectral preprocessing methods including Savitzky-Golay smoothing (SG), standard normal variate (SNV), vector normalization (VN), multiplicative scatter correction (MSC) and first derivative (FD) were applied to improve the quality of the collected spectra. Partial least squares regression (PLSR) and least squares support vector regression (LS-SVR) were introduced to establish models for tea polyphenol and EGCG content prediction based on different preprocessed spectral data. Variable selection algorithms, including competitive adaptive reweighted sampling (CARS) and random forest (RF), were further utilized to identify key spectral bands to improve the efficiency of the models. The results demonstrate that the optimal model for tea polyphenols calibration was the LS-SVR with R p = 0.975 and RPD = 4.540 based on SG-smoothed full spectra. For EGCG detection, the best model was the LS-SVR with R p = 0.936 and RPD = 2.841 using full original spectra as model inputs. The application of variable selection algorithms further improved the predictive performance of the models. The LS-SVR model for tea polyphenols prediction with R p = 0.978 and RPD = 4.833 used 30 CARS-selected variables, while the LS-SVR model build on 27 RF-selected variables achieved the best predictive ability with R p = 0.944 and RPD = 3.049, respectively, for EGCG prediction. The results demonstrate a potential of FT-NIR spectroscopy combined with machine learning for the rapid screening of genotypes with high tea polyphenol and EGCG content in tea leaves.
Why it matches plant phenotyping methods茶葉中のポリフェノールとEGCG含量という植物器官の化学的形質を、FT-NIR分光と機械学習で予測するモデルを開発・評価しており、表現型取得法が中心である。
abstractThis study aimed to develop reliable models for tea polyphenols and EGCG content prediction during the breeding process using Fourier Transform-near infrared (FT-NIR) spectroscopy combined with machine learning algorithms.
Accurate detection of tea shoots and precise location of picking points are prerequisites for automated, intelligent and accurate tea picking. A method was developed for the detection of tea shoots and key points and the localisation of picking points in complex environments. Images of four types of tea shoots were collected from multiple fields of view in a tea plantation over two months and labelling criteria were established. The YOLO-Tea model was developed based on the YOLOv5 network model, which uses a content-based upsampling operator (CARAFE) with a larger field of perception to implement the tea shoot feature upsampling operation, adds a convolutional attention mechanism module (CBAM) to focus the model on both channel and spatial dimensions to detect and localise important areas of tea shoots in a large field of view. The Bottleneck Transformers module was used to inject global self-focus for residuals to create long-distance dependencies on the tea shot feature images, and a six-point landmark regression head was added. The experimental results demonstrated that the YOLO-Tea model improved the mean Average Precision (mAP) value of tea shoots and their key points by 5.26% compared to YOLOv5. Finally, we use image processing methods to locate picking point positions based on key point information during the model inference phase. This study has theoretical and practical implications for the detection of tea shoots and their key points, tea shoot alignment, phenotype identification, pose estimation and picking locations of premium teas in complex environments.
Why it matches plant phenotyping methods茶芽の検出・キーポイント推定・摘採点位置推定を目的とする画像ベース手法を開発し、YOLOv5との性能比較で検証している。ロボット摘採向けだが、単なる対象位置特定に留まらず、茶芽の形態・姿勢に関わる表現型推定を含むため中心的なフェノタイピング手法研究である。
abstractA method was developed for the detection of tea shoots and key points and the localisation of picking points in complex environments.
A reliable and accurate diagnosis and identification system is required to prevent and manage tea leaf diseases. Tea leaf diseases are detected manually, increasing time and affecting yield quality and productivity. This study aims to present an artificial intelligence-based solution to the problem of tea leaf disease detection by training the fastest single-stage object detection model, YOLOv7, on the diseased tea leaf dataset collected from four prominent tea gardens in Bangladesh. 4000 digital images of five types of leaf diseases are collected from these tea gardens, generating a manually annotated, data-augmented leaf disease image dataset. This study incorporates data augmentation approaches to solve the issue of insufficient sample sizes. The detection and identification results for the YOLOv7 approach are validated by prominent statistical metrics like detection accuracy, precision, recall, mAP value, and F1-score, which resulted in 97.3%, 96.7%, 96.4%, 98.2%, and 0.965, respectively. Experimental results demonstrate that YOLOv7 for tea leaf diseases in natural scene images is superior to existing target detection and identification networks, including CNN, Deep CNN, DNN, AX-Retina Net, improved DCNN, YOLOv5, and Multi-objective image segmentation. Hence, this study is expected to minimize the workload of entomologists and aid in the rapid identification and detection of tea leaf diseases, thus minimizing economic losses.
Why it matches plant phenotyping methods茶葉の病害状態を画像から検出・識別するYOLOv7手法の開発と性能検証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。
abstractThis study aims to present an artificial intelligence-based solution to the problem of tea leaf disease detection by training the fastest single-stage object detection model, YOLOv7, on the diseased tea leaf dataset collected from four prominent tea gardens in Bangladesh.
Freezing damage has been a common natural disaster for tea plantations. Quantitative detection of low temperature stress is significant for evaluating the degree of freezing injury to tea plants. Traditionally, the determination of physicochemical parameters of tea leaves and the investigation of freezing damage phenotype are the main approaches to detect the low temperature stress. However, these methods are time-consuming and laborious. In this study, different low temperature treatments were carried out on tea plants. The low temperature response index (LTRI) was established by measuring seven low temperature-induced components of tea leaves. The hyperspectral data of tea leaves was obtained by hyperspectral imaging and the feature bands were screened by successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) and uninformative variable elimination (UVE). The LTRI and seven indexes of tea plant were modeled by partial least squares (PLS), support vector machine (SVM), random forests (RF), back propagation (BP) machine learning methods and convolutional neural networks (CNN), long short-term memory (LSTM) deep learning methods. The results indicated that: (1) the best prediction model for the seven indicators was LTRI-UVE-CNN (R 2 = 0.890, RMSEP=0.325, RPD=2.904); (2) the feature bands screened by UVE algorithm were more abundant, and the later modeling effect was better than CARS and SPA algorithm; (3) comparing the effects of the six modeling algorithms, the overall modeling effect of the CNN model was better than other models. It can be concluded that out of all the combined models in this paper, the LTRI-UVE-CNN was a promising model for predicting the degree of low temperature stress in tea plants.
Why it matches plant phenotyping methods茶樹の凍害ストレス状態を、ハイパースペクトル画像から低温応答指数として推定する手法を構築・比較しており、植物表現型取得と予測モデルが研究の中心である。
abstractThe low temperature response index (LTRI) was established by measuring seven low temperature-induced components of tea leaves.
Tea leaves are the most important part for consumption. Leaves that are healthy have a distinct color, while leaves that are not healthy have a color that is very different from the original. Chlorophyll in leaves effects the reflection of infrared light, allowing healthy plants to reflect more infrared light than unhealthy plants. Leaf color and chlorophyll have an important role in showing the growth and health of tea plants. Remote sensing consists of collecting information about objects and features without contacting the equipment. The Normalized Difference Vegetation Index (NDVI), one of the first remote sensing analysis products used to simplify the complexity of multispectral imaging, is now the most commonly used index for botanical assessment. inconsistencies in NDVI depending on sensor-specific spatial and spectral resolutions. Different parts of the leaf have discolored spots due to health conditions or nutritional stress, so there are different spectral values on different parts of the leaf. Unhealthy tea leaves have low NIR values due to disease, insects, and sunburn, which damage the chloroplast structure of the leaves, weaken the absorption of the appropriate band, and increase reflectance. There is a difference between the measurement results of the NDVI spectrometer and the sentinel image. This is due to the fact that the Sentinel-2 image can only retrieve image pixels with a resolution and not diseased leaf parts, as with the use of a spectrometer, which directly extracts the value of the infected area from the normal part of the plant
Why it matches plant phenotyping methods分光計とSentinel-2画像による茶葉の健康状態・感染部位のスペクトル測定を比較しており、植物状態の取得方法が中心的に扱われている。
abstractThere is a difference between the measurement results of the NDVI spectrometer and the sentinel image.
Indonesia's tea production and export volume have fluctuated with a downward trend in the last five years, partly due to the increasingly competitive world tea quality. Crop yield estimation is part of the management of tea plucking, affecting tea quality and quantity. The constraint in estimating crop yields requires technology that can make the process more effective and efficient. Remote sensing technology and machine learning have been widely used in precision agriculture. Recently, big data processing, especially remote sensing data, machine learning, and deep learning have been carried out using a cloud computing platform. Therefore, we propose using GeoAI, a combination of Sentinel-2A imagery, machine learning, and Google Collaboratory, to predict ready for plucking tea leaves at optimal plucking time at Gunung Mas Plantation Bogor. We used selected bands of Sentinel-2A and extracted more features (i.e., NDVI) as a training set. Then we utilized the tea blocks boundary and tea plucking data to generate labels using Random Forest (RF) and Support Vector Machine (SVM). The classification results were further used to estimate the production of crop tea yield. The RF classifier is able to achieve overall accuracy at 51% and SVM at 54%. Meanwhile, accuracy at optimally aged tea blocks is able to achieve at 75.62% for RF and 52.88% for SVM. Thus, the SVM classifier is better in terms of overall accuracy. Meanwhile, the RF classifier is superior in predicting ready for plucking tea at optimally aged tea blocks.
Why it matches plant phenotyping methodsSentinel-2画像と機械学習を用いて、茶葉の摘採適期という植物状態と茶収量を推定するGeoAI手法を提案・評価しており、表現型取得・推定が研究の中心である。
abstractTherefore, we propose using GeoAI, a combination of Sentinel-2A imagery, machine learning, and Google Collaboratory, to predict ready for plucking tea leaves at optimal plucking time at Gunung Mas Plantation Bogor.
We proposed a novel deep convolutional neural network (DCNN) using inverted residuals and linear bottleneck layers for diagnosing grey blight disease on tea leaves. The proposed DCNN consists of three bottleneck blocks, two pairs of convolutional (Conv) layers, and three dense layers. The bottleneck blocks contain depthwise, standard, and linear convolution layers. A single-lens reflex digital image camera was used to collect 1320 images of tea leaves from the North Bengal region of India for preparing the tea grey blight disease dataset. The nongrey blight diseased tea leaf images in the dataset were categorized into two subclasses, such as healthy and other diseased leaves. Image transformation techniques such as principal component analysis (PCA) color, random rotations, random shifts, random flips, resizing, and rescaling were used to generate augmented images of tea leaves. The augmentation techniques enhanced the dataset size from 1320 images to 5280 images. The proposed DCNN model was trained and validated on 5016 images of healthy, grey blight infected, and other diseased tea leaves. The classification performance of the proposed and existing state-of-the-art techniques were tested using 264 tea leaf images. Classification accuracy, precision, recall, F measure, and misclassification rates of the proposed DCNN are 98.99%, 98.51%, 98.48%, 98.49%, and 1.01%, respectively, on test data. The test results show that the proposed DCNN model performed superior to the existing techniques for tea grey blight disease detection.
Why it matches plant phenotyping methods茶葉画像から病害状態を推定する深層学習モデルを開発・検証しており、植物病害表現型の取得・分類が中心である。
abstractWe proposed a novel deep convolutional neural network (DCNN) using inverted residuals and linear bottleneck layers for diagnosing grey blight disease on tea leaves.
Tea polyphenols, amino acids, soluble sugars, and other ingredients in fresh tea leaves are the key parameters of tea quality. In this research, a tea leaf ingredient estimation sensor was developed based on a multi-channel spectral sensor. The experiment showed that the device could effectively acquire 700-1000 nm spectral data of tea tree leaves and could display the ingredients of leaf samples in real time through the visual interactive interface. The spectral data of Fuding white tea tree leaves acquired by the detection device were used to build an ingredient content prediction model based on the ridge regression model and random forest algorithm. As a result, the prediction model based on the random forest algorithm with better prediction performance was loaded into the ingredient detection device. Verification experiment showed that the root mean square error (RMSE) and determination coefficient (R 2 ) in the prediction were, respectively, as follows: moisture content (1.61 and 0.35), free amino acid content (0.16 and 0.79), tea polyphenol content (1.35 and 0.28), sugar content (0.14 and 0.33), nitrogen content (1.15 and 0.91), and chlorophyll content (0.02 and 0.97). As a result, the device can predict some parameters with high accuracy (nitrogen, chlorophyll, free amino acid) but some of them with lower accuracy (moisture, polyphenol, sugar) based on the R 2 values. The tea leaf ingredient estimation sensor could realize rapid non-destructive detection of key ingredients affecting tea quality, which is conducive to real-time monitoring of the current quality of tea leaves, evaluating the status during tea tree growth, and improving the quality of tea production. The application of this research will be helpful for the automatic management of tea plantations.
Why it matches plant phenotyping methods茶葉の生葉からスペクトルデータを取得し、成分・クロロフィル等を推定する低コストセンサーと予測モデルを開発・検証しており、植物形質取得が研究の中心である。
abstracta tea leaf ingredient estimation sensor was developed based on a multi-channel spectral sensor
Drought tolerance and quality stability are important indicators to evaluate the stress tolerance of tea germplasm resources. The traditional screening method of drought resistant germplasm is mainly to evaluate by detecting physiological and biochemical indicators of tea plants under drought stresses. However, the methods are not only time consuming but also destructive. In this study, hyperspectral images of tea drought phenotypes were obtained and modeled with related physiological indicators. The results showed that: (1) the information contents of malondialdehyde, soluble sugar and total polyphenol were 0.21, 0.209 and 0.227 respectively, and the drought tolerance coefficient (DTC) index of each tea variety was between 0.069 and 0.81; (2) the comprehensive drought tolerance of different varieties were (from strong to weak): QN36, SCZ, ZC108, JX, JGY, XY10, QN1, MS9, QN38 , and QN21 ; (3) by using SVM, RF and PLSR to model DTC (drought tolerance coefficient) data, the best prediction model was selected as MSC-2D-UVE-SVM (R 2 = 0.77, RMSE = 0.073, MAPE = 0.16) for drought tolerance of tea germplasm resources, named Tea-DTC model. Therefore, the Tea-DTC model based on hyperspectral machine-learning technology can be used as a new screening method for evaluating tea germplasm resources with drought tolerance.
Why it matches plant phenotyping methods茶樹の乾燥耐性という植物状態をハイパースペクトル画像と機械学習で推定するモデルを開発し、従来の生理・生化学指標に代わるスクリーニング手法として性能評価しているため、フェノタイピング手法が中心である。
abstractIn this study, hyperspectral images of tea drought phenotypes were obtained and modeled with related physiological indicators.
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。Supplement · publicThe content data of physiological and biochemical components of tea leaves measured with the kit are shown in supplementary Table 1Open asset ↗lines:322-334Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Dec 2022Journal of the science of food and agriculture.
Why it matches plant phenotyping methods茶葉の形態・色・輪郭特徴をカメラ画像から抽出し、遺伝的アルゴリズムと分類器で葉のタイプを高速識別するシステムを開発・評価しており、植物器官の表現型取得・分類が中心である。
abstractThe present study proposes a method based on an improved genetic algorithm for identifying fresh tea leaves in high‐speed parabolic motion using the phenotypic characteristics of the leaves.
Discrimination of tea plant (Camellia sinensis L.) varieties is of significant value for the efficient management of cultivation and resources optimization of tea industry. Phenotypic and spectral characteristics of tea plants are important indicators for determining the quality of tea cultivars to a certain extent. However, few studies have used spectral image information to identify tea plant varieties. The aim of this research was the discrimination of 16 types of high-yield tea plant varieties using a multispectral camera. This methodology involved image registration, calibration, segmentation, information extraction, and data fusion. The hue (H), saturation (S), and value (V), texture information, and several spectral vegetation indices were acquired from the multispectral image of the tea plant canopy. The successive projection algorithm (SPA) was used to analyze the original parameters. Three classification methods were applied to tea plant variety discrimination: Bayes discriminant analysis (BDA), support vector machine (SVM), and extreme learning machine (ELM). The results indicated that SPA based on fusing data combined with the SVM classification model, achieved a feasible method to identify tea plant varieties. Additionally, the method achieved accuracy in the training, test, and validation sets, reaching 97.00%, 90.52%, and 88.67%, respectively. This study proposed a new perspective on multispectral image information as an identifier of tea plant varieties. The explored model will be helpful for the development of portable instruments for commercial applications in variety identification and phenotype recognition of tea plants.
Why it matches plant phenotyping methods茶樹キャノピーのマルチスペクトル画像から色・テクスチャ・植生指数を抽出し、品種識別する画像計測・解析ワークフローが研究の中心であり、植物の表現型認識に直接結びつくため。
abstractThis methodology involved image registration, calibration, segmentation, information extraction, and data fusion.
Brown blight, target spot, and tea coal diseases are three major leaf diseases of tea plants, and Apolygus lucorum is a major pest in tea plantations. The traditional symptom recognition of tea leaf diseases and insect pests is mainly through manual identification, which has some problems, such as low accuracy, low efficiency, strong subjectivity, and so on. Therefore, it is very necessary to find a method that could effectively identify tea plants diseases and pests. In this study, we proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet. First, Mask R-CNN model was used to segment disease spots and insect spots from tea leaves. Second, the two-dimensional discrete wavelet transform was used to enhance the features of the disease spots and insect spots images, so as to obtain the images with four frequencies. Finally, the images of four frequencies were simultaneously input into the four-channeled residual network (F-RNet) to identify symptoms of tea leaf diseases and insect pests. The results showed that Mask R-CNN model could detect 98.7% of DSIS, which ensure that almost disease spots and insect spots can be extracted from leaves. The accuracy of F-RNet model is 88%, which is higher than that of the other models (like SVM, AlexNet, VGG16 and ResNet18). Therefore, this experimental framework can accurately segment and identify diseases and insect spots of tea leaves, which not only of great significance for the accurate identification of tea plant diseases and insect pests, but also of great value for further using artificial intelligence to carry out the comprehensive control of tea plant diseases and insect pests.
Why it matches plant phenotyping methods茶葉の病斑・虫害斑という植物の病害状態を、Mask R-CNNによる分割とF-RNetによる認識で抽出・評価する画像解析手法が研究の中心であるため。
abstractwe proposed a recognition framework of tea leaf disease and insect pest symptoms based on Mask R-CNN, wavelet transform and F-RNet.
Reproduction assets foundThe paper's data availability statement points to two GitHub repositories. The F-RNet repository (github.com/Du553/F-RNet) is the authors' own public code implementing the paper's four-channeled residual network analysis and qualifies as a paper-specific asset. The matterport/Mask_RCNN link is a generic third-partyMaskCode · publicThe dataset and source code has been uploaded to GitHub: https://github.com/matterport/Mask_RCNN , https://github.com/Du553/F-RNet .Open asset ↗Du553/F-RNetlines:469-489Plant phenotyping relevance match · UnverifiedEurope PMC · checked 8 Sept 2026
Tea height, leaf area index, canopy water content, leaf chlorophyll, and nitrogen concentrations are important phenotypic parameters to reflect the status of tea growth and guide the management of tea plantation. UAV multi-source remote sensing is an emerging technology, which can obtain more abundant multi-source information and enhance dynamic monitoring ability of crops. To monitor the phenotypic parameters of tea canopy more efficiently, we first deploy UAVs equipped with multispectral, thermal infrared, RGB, LiDAR, and tilt photography sensors to acquire phenotypic remote sensing data of tea canopy, and then, we utilize four machine learning algorithms to model the single-source and multi-source data, respectively. The results show that, on the one hand, using multi-source data sets to evaluate H, LAI, W, and LCC can greatly improve the accuracy and robustness of the model. LiDAR + TC data sets are suggested for assessing H, and the SVM model delivers the best estimation (Rp 2 = 0.82 and RMSEP = 0.078). LiDAR + TC + MS data sets are suggested for LAI assessment, and the SVM model delivers the best estimation (Rp 2 = 0.90 and RMSEP = 0.40). RGB + TM data sets are recommended for evaluating W, and the SVM model delivers the best estimation (Rp 2 = 0.62 and RMSEP = 1.80). The MS +RGB data set is suggested for studying LCC, and the RF model offers the best estimation (Rp 2 = 0.87 and RMSEP = 1.80). On the other hand, using single-source data sets to evaluate LNC can greatly improve the accuracy and robustness of the model. MS data set is suggested for assessing LNC, and the RF model delivers the best estimation (Rp 2 = 0.65 and RMSEP = 0.85). The work revealed an effective technique for obtaining high-throughput tea crown phenotypic information and the best model for the joint analysis of diverse phenotypes, and it has significant importance as a guiding principle for the future use of artificial intelligence in the management of tea plantations.
Why it matches plant phenotyping methodsUAV多センサー画像と機械学習により、茶樹冠の複数形質を推定する取得・解析手法が研究の中心であり、技術性能も比較評価している。
abstractTo monitor the phenotypic parameters of tea canopy more efficiently, we first deploy UAVs equipped with multispectral, thermal infrared, RGB, LiDAR, and tilt photography sensors to acquire phenotypic remote sensing data of tea canopy, and then, we utilize four machine learning algorithms to model the single-source and multi-source data, respectively.
As compared with the traditional visual discrimination methods, deep learning and image processing methods have the ability to detect plants efficiently and non-invasively. This is of great significance in the diagnosis and breeding of plant disease resistance phenotypes. Currently, the studies on plant diseases and pest stresses mainly focus on a leaf scale. There are only a few works regarding the stress detection at a complex canopy scale. In this work, three tea plant stresses with similar symptoms that cause a severe threat to the yield and quality of tea gardens, including the tea green leafhopper [ Empoasca (Matsumurasca) onukii Matsuda], anthracnose ( Gloeosporium theae-sinensis Miyake), and sunburn (disease-like stress), are evaluated. In this work, a stress detection and segmentation method by fusing deep learning and image processing techniques at a canopy scale is proposed. First, a specified Faster RCNN algorithm is proposed for stress detection of tea plants at a canopy scale. After obtaining the stress detection boxes, a new feature, i.e., RGReLU, is proposed for the segmentation of tea plant stress scabs. Finally, the detection model at the canopy scale is transferred to a field scale by using unmanned aerial vehicle (UAV) images. The results show that the proposed method effectively achieves canopy-scale stress adaptive segmentation and outputs the scab type and corresponding damage ratio. The mean average precision (mAP) of the object detection reaches 76.07%, and the overall accuracy of the scab segmentation reaches 88.85%. In addition, the results also show that the proposed method has a strong generalization ability, and the model can be migrated and deployed to UAV scenarios. By fusing deep learning and image processing technology, the fine and quantitative results of canopy-scale stress monitoring can provide support for a wide range of scouting of tea garden.
Why it matches plant phenotyping methods茶樹キャノピーの病害・ストレスを画像から検出・分割し、病斑タイプと被害率を定量化する手法を開発・検証しており、植物表現型取得が研究の中心である。
abstracta stress detection and segmentation method by fusing deep learning and image processing techniques at a canopy scale is proposed
Nitrogen (N) plays a pivotal role in management of tea plantation, with significant impacts on the growth, productivity, and nutrition status of tea plants. The existing methods for N content monitoring of tea leaves are complicated and can not realize in suite and in real time way. This study proposed a method for estimating the N content of tea plants in field conditions based on a combination of a multispectral imaging system and hyperspectral data. A total of 32 parameters were extracted from five tea gardens using calibrated multispectral images of the tea plant canopy, and 27 indices were selected by Pearson correlation analysis. A total of 28 wavelengths selected by competitive adaptive reweighted sampling from hyperspectral data were combined with 27 multispectral indices as the original data. Subsequently, five variables of fused data (H, VOG, BGI, 1664 nm and 1665 nm) were selected by variable combination population analysis based on the 55 combination parameters. Partial least squares regression, random forest regression, and support vector machine regression (SVR) models all showed excellent performance for both the calibration and prediction sets. The overall results indicated that the infused data of multispectral and hyperspectral data combined with SVR are effective in monitoring the N level under field conditions, and the R² (coefficient of determination) and root mean square error values of the prediction were 0.9186 and 0.0560, respectively. The findings of this study are important in retaining the nutritional and quality attributes of agricultural commodities.
Why it matches plant phenotyping methods茶樹の窒素状態という植物生理形質を、マルチスペクトル・ハイパースペクトルデータから推定する手法を開発・評価しており、形質取得と予測性能の検証が研究の中心である。
abstractThis study proposed a method for estimating the N content of tea plants in field conditions based on a combination of a multispectral imaging system and hyperspectral data.
Why it matches plant phenotyping methods茶葉の形態・色・形状特徴を画像から抽出し、分類性能と特徴量構成を検証する認識システムが研究の中心であり、植物器官の観測可能な形質を扱うため対象に含める。
abstractThe present study proposes a method based on an improved genetic algorithm for identifying fresh tea leaves in high-speed parabolic motion using the phenotypic characteristics of the leaves.
Catechin polyphenols and caffeine play an important role in tea quality. This study analyzed the visible and near-infrared (Vis-NIR) spectral variation and concentration differences of catechin and caffeine of fresh tea leaves (Camellia sinensis L.) in three varieties and six leaf positions, and a universal spectral model for quickly and accurately measurement of the catechin and caffeine content in the various varieties and leaf positions was established. It was found that all the catechins and caffeine were significantly influenced by variety and leaf position. While, the Vis/NIR spectrum as an indication of internal biochemical substances was successfully used to distinguish different varieties and leaf positions with the discrimination accuracy rates of 98.15% and 100%, respectively. The quantitative relationship between the chemical components and the data obtained by Vis-NIR spectroscopy was established based on multivariate regression analysis such as partial least squares (PLS) and multiple linear regression (MLR). Furthermore, competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to select the characteristic wavelengths for the development of simple models. Results showed that the quantitative determination models obtained good performance with the determination coefficients (R²) of 0.949, 0.893, 0.968, 0.931 and 0.917 for epigallocatechin gallate (EGCG), epicatechin gallate (ECG), epigallocatechin (EGC), epicatechin (EC) and caffeine (CAF), respectively. Such high detection accuracy shows that the spectral detection model has a strong applicability for both varieties and leaf positions. The overall results of the study revealed the potential use of Vis-NIR spectroscopy as a rapid, simple and non-destructive method for the determination of four main catechins and caffeine in fresh tea leaves, and it will play a great role in the real-time detection of tea physiological information in tea garden.
Why it matches plant phenotyping methods新鮮茶葉のカテキン・カフェイン含量をVis-NIR分光で非破壊推定するモデルを開発・評価しており、植物の生理的形質取得が研究の中心である。
abstracta universal spectral model for quickly and accurately measurement of the catechin and caffeine content in the various varieties and leaf positions was established.
High-cost data collection and processing are challenges for UAV LiDAR (light detection and ranging) mounted on unmanned aerial vehicles in crop monitoring. Reducing the point density can lower data collection costs and increase efficiency but may lead to a loss in mapping accuracy. It is necessary to determine the appropriate point cloud density for tea plucking area identification to maximize the cost–benefits. This study evaluated the performance of different LiDAR and photogrammetric point density data when mapping the tea plucking area in the Huashan Tea Garden, Wuhan City, China. The object-based metrics derived from UAV point clouds were used to classify tea plantations with the extreme learning machine (ELM) and random forest (RF) algorithms. The results indicated that the performance of different LiDAR point density data, from 0.25 (1%) to 25.44 pts/m2 (100%), changed obviously (overall classification accuracies: 90.65–94.39% for RF and 89.78–93.44% for ELM). For photogrammetric data, the point density was found to have little effect on the classification accuracy, with 10% of the initial point density (2.46 pts/m2), a similar accuracy level was obtained (difference of approximately 1%). LiDAR point cloud density had a significant influence on the DTM accuracy, with the RMSE for DTMs ranging from 0.060 to 2.253 m, while the photogrammetric point cloud density had a limited effect on the DTM accuracy, with the RMSE ranging from 0.256 to 0.477 m due to the high proportion of ground points in the photogrammetric point clouds. Moreover, important features for identifying the tea plucking area were summarized for the first time using a recursive feature elimination method and a novel hierarchical clustering-correlation method. The resultant architecture diagram can indicate the specific role of each feature/group in identifying the tea plucking area and could be used in other studies to prepare candidate features. This study demonstrates that low UAV point density data, such as 2.55 pts/m2 (10%), as used in this study, might be suitable for conducting finer-scale tea plucking area mapping without compromising the accuracy.
Why it matches plant phenotyping methodsUAV-LiDAR／写真測量の点密度が茶園の摘採可能領域マッピング精度に与える影響を比較・検証し、特徴量選択と再利用可能な解析手順も提示しているため、植物キャノピー状態の計測手法が中心である。
abstractThis study evaluated the performance of different LiDAR and photogrammetric point density data when mapping the tea plucking area
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 15 Sept 2026
Compared with the traditional visual detection method, hyperspectral imaging enables efficient and non-destructive plant monitoring. Besides, it has great potential in plant phenotyping in response to disease and insect infections. However, most previous studies on hyperspectral imaging have focused on detecting a single disease, which can rarely discriminate between multiple co-occurring diseases and insects. In this study, three tea plant stresses with similar symptoms, including the tea green leafhopper (Empoasca (Matsumurasca) onukii Matsuda), anthracnose (Gloeosporium theae-sinesis Miyake), and sunburn (disease-like stress), were evaluated. A multi-step approach was proposed based on hyperspectral imaging and continuous wavelet analysis (CWA) to discriminate the plant stresses. The process entailed: (1) Feature extraction for detection and discrimination of tea plant stresses based on CWA; (2) Detecting abnormal areas on tea leaves via the k-means clustering and support vector machine algorithms; (3) Construction of a model for identification and discrimination of the three tea plant stresses via the random forest algorithm. The results showed that CWA could effectively identify spectral features for distinguishing the three stresses. The overall accuracy (OA) of the proposed approach reached 90.26%-90.69%, with anthracnose having the highest OA (94.12%-94.28%), followed by tea green leafhopper (93.99%-94.20%), while sunburn damage was the least (82.50%-83.91%). Therefore, hyperspectral imaging is effective for plant phenotyping after diseases and insect infections.
Why it matches plant phenotyping methodsハイパースペクトル画像と波レット解析を中核に、茶葉の病害・虫害・日焼けによる植物状態を検出・識別する手法を開発し、精度を評価しているため。
abstractA multi-step approach was proposed based on hyperspectral imaging and continuous wavelet analysis (CWA) to discriminate the plant stresses.
Tea plants that have a large leaf area mainly suffer from heavy metal accumulation in the above-ground parts through foliar uptake. With the world rapid industrialization, this pollution in tea is considered a crucial challenge due to its potential health risks. The present study proposes an innovative approach based on visible and near-infrared (Vis-NIR) spectroscopy coupled with chemometrics for the characterization of tea chemical indicators under airborne lead stress, which can be performed fast and in situ. The effects of lead stress on chemical indicators and accumulation in leaves of the two tea varieties at different time intervals and levels of treatment were investigated. In addition, changes in cell structure and leaf stomata were monitored during foliar uptake of aerosol particles by transmission electron microscopy (TEM) and scanning electron microscopy (SEM). The spectral variation was able to classify the tea samples into the Pb treatment groups through the linear discriminant analysis (LDA) model. Two machine learning techniques, namely, partial least squares (PLS) and radial basis function neural network (RBFNN), were evaluated and compared for building the quantitative determination models. The RBFNN models combined with correlation-based feature selection (CFS) and PLS data compression methods were used to optimize the prediction performance. The results demonstrated that the PLS-RBFNN as a non-linear model outperformed the PLS model and provided the R-value of 0.944, 0.952, 0.881, 0.937, and 0.930 for prediction of MDA, starch, sucrose, fructose, glucose, respectively. It can be concluded that the proposed approach has strong application potential in monitoring the quality and safety of plants under airborne heavy metal stress.
Why it matches plant phenotyping methodsVis-NIR分光とケモメトリクスを用いて、Pbストレス下の茶葉の化学的状態を非破壊・迅速推定する手法を開発し、複数モデルの性能比較と予測評価を行っているため、植物状態の取得・推定が中心である。
abstractThe present study proposes an innovative approach based on visible and near-infrared (Vis-NIR) spectroscopy coupled with chemometrics for the characterization of tea chemical indicators under airborne lead stress, which can be performed fast and in situ.
Mapping plucking areas of tea plantations is essential for tea plantation management and production estimation. However, on-ground survey methods are time-consuming and labor-intensive, and satellite-based remotely sensed data are not fine enough for plucking area mapping that is 0.5–1.5 m in width. Unmanned aerial vehicles (UAV) remote sensing can provide an alternative. This paper explores the potential of using UAV-derived remotely sensed data for identifying plucking areas of tea plantations. In particular, four classification models were built based on different UAV data (optical imagery, digital aerial photogrammetry, and lidar data). The results indicated that the integration of optical imagery and lidar data produced the highest overall accuracy using the random forest algorithm (94.39%), while the digital aerial photogrammetry data could be an alternative to lidar point clouds with only a ~3% accuracy loss. The plucking area of tea plantations in the Huashan Tea Garden was accurately measured for the first time with a total area of 6.41 ha, which accounts for 57.47% of the tea garden land. The most important features required for tea plantation mapping were the canopy height, variances of heights, blue band, and red band. Furthermore, a cost–benefit analysis was conducted. The novelty of this study is that it is the first specific exploration of UAV remote sensing in mapping plucking areas of tea plantations, demonstrating it to be an accurate and cost-effective method, and hence represents an advance in remote sensing of tea plantations.
Why it matches plant phenotyping methodsUAV画像・写真測量・LiDARを組み合わせ、茶園の摘採面積を分類・定量化する手法を比較検証しており、植物キャノピーの状態測定が中心である。
abstractThis paper explores the potential of using UAV-derived remotely sensed data for identifying plucking areas of tea plantations.
The problem of excessive lead content in tea has become more and more serious with the development of society and industry. This paper investigated the ability of visible and near-infrared (Vis-NIR) spectroscopy to evaluate foliar lead uptake by tea plants through simulating real air pollution. Lead content of tea leaves in different treatment groups during stress time was measured by inductively coupled plasma mass spectrometry (ICP-MS). It was determined that stomata can be a channel for lead particles in the air and most of the lead entering through the stomata accumulates in the leaves. The spectral variation of treated samples was measured, and it was found that a combination of partial least squares-discriminant analysis (PLS-DA) and spectral responses can perfectly classify the tea samples under different lead concentrations stress with an overall accuracy of 0.979. Then the Vis-NIR spectra were used for fast monitoring physiological and biochemical indicators in tea leaves under atmospheric deposition. Relevant spectra pretreatment methods and characteristic wavelength selection approaches were evaluated for quantitative analysis and then optimal prediction models to instantly detect quality indicators in tea samples were built. Among predictive models, PLS had the best results (RMSE = 0.139 mg/g, 0.663 mmol/g, and 1.494 μmol/g) for the prediction of chlorophyll a (Chl-a), ascorbic acid (ASA), and glutathione (GSH), respectively. Also, principal component regression (PCR) gave the best results (RMSE = 0.053 mg/g, 0.024 mg/g, and 0.011%) for prediction of chlorophyll b (Chl-b), carotenoid (Car) and moisture content (MC), respectively. Results of this study can be applied for developing an effective and reliable approach for monitoring atmospheric deposition in plants.
Why it matches plant phenotyping methods茶葉の葉面鉛蓄積、ストレス状態、クロロフィル等の植物形質をVis-NIR分光で分類・定量する手法を評価し、前処理・波長選択・予測モデルも比較しており、フェノタイピング手法が中心である。
abstractThis paper investigated the ability of visible and near-infrared (Vis-NIR) spectroscopy to evaluate foliar lead uptake by tea plants
Effective evaluation of physiological and biochemical indexes and drought degree of tea plant is an important technology to determine the drought resistance ability of tea plants. At present, the traditional detection method of tea drought stress is mainly based on physiological and biochemical detection, which is not only destructive to tea plants, but also time-consuming and laborious. In this study, through simulating drought treatment of tea plant, hyperspectral camera was used to obtain spectral data of tea leaves, and three machine learning models, namely, support vector machine (SVM), random forest (RF), and partial least-squares (PLS) regression, were used to model malondialdehyde (MDA), electrolyte leakage (EL), maximum efficiency of photosystem II ( Fv/Fm ), soluble saccharide (SS), and drought damage degree (DDD) of tea leaves. The results showed that the competitive adaptive reweighted sampling (CARS)-PLS model of MDA had the best effect among the four physiological and biochemical indexes (Rcal = 0.96, Rp = 0.92, RPD = 3.51). Uninformative variable elimination (UVE)-SVM model was the best in DDD (Rcal = 0.97, Rp = 0.95, RPD = 4.28). Therefore, through the establishment of machine learning model using hyperspectral imaging technology, we can monitor the drought degree of tea seedlings under drought stress. This method is not only non-destructive, but also fast and accurate, which is expected to be widely used in tea garden water regime monitoring.
Why it matches plant phenotyping methods茶葉の生理指標と干ばつ被害度をハイパースペクトル画像と機械学習で非破壊推定する手法が研究の中心であり、モデル性能も検証している。
abstracthyperspectral camera was used to obtain spectral data of tea leaves, and three machine learning models
Tea leaf blight (TLB) is a common tea disease seriously affecting the quality and yield of tea. An accurate estimation of TLB severity can be used to guide tea farmers to reasonably spray pesticides. This study proposes an estimation method for TLB severity in natural scene images and consists of four main steps: segmentation of the diseased leaves, area fitting of the diseased leaves, segmentation of the disease spots, and estimation of disease severity. Target leaves with TLB in the tea images are segmented by combining the U-Net network and fully connected conditional random field to reduce the influence of complex background. An ellipse restoration method is proposed to generate an elliptic mask to fit the full size of the occluded or damaged TLB leaves. The disease spot regions are segmented from the TLB leaves by a support vector machine classifier to calculate the Initial Disease Severity (IDS) index. The IDS index, color features, and texture features of the TLB leaves are inputted into the metric learning model to finally estimated disease severity. Experimental results show that the proposed method has higher estimation accuracy and stronger robustness against occluded and damaged TLB leaves compared with conventional convolution neural network methods and classical machine learning techniques.
Why it matches plant phenotyping methods茶葉の病害葉画像から病斑面積と病害重症度を推定する画像解析手法が研究の中心であり、植物の病害状態を直接定量化している。
abstractThis study proposes an estimation method for TLB severity in natural scene images
Tea shoot detection and localization are highly challenging tasks because of varying illumination, inevitable occlusion, tiny targets, and dense growth. To achieve the automatic plucking of tea shoots in a tea garden, a reliable algorithm based on red, green, blue-depth (RGB-D) camera images was developed to detect and locate tea shoots in fields for tea harvesting robots. In this study, labeling criteria were first established for the images collected for multiple periods and varieties in the tea garden. Then, a “you only look once” (YOLO) network was used to detect tea shoot (one bud with one leaf) regions on RGB images collected by an RGB-D camera. Additionally, the detection precision for tea shoots was 93.1% and the recall rate was 89.3%. To achieve the three-dimensional (3D) localization of the plucking position, 3D point clouds of the detected target regions were acquired by fusing the depth image and RGB image captured by an RGB-D camera. Then, noise was removed using point cloud pre-processing and the point cloud of the tea shoots was obtained using Euclidean clustering processing and a target point cloud extraction algorithm. Finally, the 3D plucking position of the tea shoots was determined by combining the tea growth characteristics, point cloud features, and sleeve plucking scheme, which solved the problem that the plucking point may be invisible in fields. To verify the effectiveness of the proposed algorithm, tea shoot localization and plucking experiments were conducted in the tea garden. The plucking success rate for tea shoots was 83.18% and the average localization time for each target was about 24 ms. All the results demonstrate that the proposed method could be used for robotic tea plucking.
Why it matches plant phenotyping methodsRGB-D画像、物体検出、点群処理により茶芽の検出・3D位置推定法を開発・検証しており、植物器官の形態・位置という表現型取得が中心的です。
abstracta reliable algorithm based on red, green, blue-depth (RGB-D) camera images was developed to detect and locate tea shoots in fields for tea harvesting robots
In the automatic intelligent picking of famous tea sprouts, the images obtained by the robot vision system have the following problems: the highlighted surface of a tea sprout leads to identification omissions, and the color distinction rate between the sprout and old leaves is low, resulting in an incomplete tea sprout segmentation and high segmentation error rate for old tea leaves. A tea sprout recognition segmentation method based on an improved watershed algorithm is proposed in this study. First, images of naturally grown tea leaves in a tea garden are collected. After an experimental analysis and comparison, the collected tea samples are smoothed by Gaussian filtering to remove noise, split the channels, obtain R, G, and B components, and analyze their characteristics. Second, the optimal adaptation threshold T′ is determined using the minimum error method. For all pixels of the B component, the pixel values are set to be greater than the threshold of zero. Third, image operations are performed on the G and B′ components to obtain G-B′ components, and the minimum error method is used to obtain the best adaptation thresholds T₁ and T₂ and enhance them via piecewise linear transformation to improve the distinction between the young leaves and the background in the image. Lastly, binarization is performed, and the Canny operator is utilized for edge detection. The foreground and background areas are determined, the unknown area is calculated and marked, and the watershed function is used to complete the segmentation. A comparative experiment is conducted by comparing the 100 samples collected using the threshold segmentation algorithm, watershed segmentation algorithm, and the proposed segmentation algorithm. One group is randomly selected among tea samples numbered 1–10, and another nine groups of tea samples are selected with a number interval of 10 for a total of 10 groups. Their experimental data are analyzed. Results show that the improved algorithm has an average segmentation accuracy rate of 95.79%, and it improves the accuracy and integrity of the segmentation of tea leaves.
Why it matches plant phenotyping methods茶芽を対象とする画像セグメンテーション手法を開発し、複数手法との比較で精度検証しており、植物器官の認識・抽出が中心的な技術貢献である。
abstractA tea sprout recognition segmentation method based on an improved watershed algorithm is proposed in this study.
In this research, multispectral and depth images were utilized for tea moisture content detection, the problems on leaf surface orientation and detection height were studied specifically. For the leaf surface orientation issue, multispectral images (25 bands) of the front surface and back surface of tea leaves were collected. Based on the spectra with same surface orientation, regression models of tea moisture content were established. The R²P values of LSSVR models reach 0.77 and 0.68 for the front surface and back surface, respectively. To distinguish the surface orientation of tea leaves, an LDA classifier was built based on spectral band ratio information. The overall classification accuracy reaches 87.8%. The distribution map of tea moisture content was successfully generated by importing the spectra into the classifier and the regression model. For the detection height issue, the multispectral image and depth image of tea leaves were collected simultaneously. First, an experiment was designed to figure out the attenuation coefficient of each band and the calibration model of detection height. Then, the detection height information was introduced into each pixel of the multispectral image by image registration. According to the detection height and calibration model, the spectrum of each pixel was calibrated. Finally, through importing the modified spectra into the classifier and regression model, the visual detection of tea moisture content was realized with detection height calibration. This research promoted the practicability of tea moisture content detection, and improved the visualization detection technology based on the fusion of multispectral image and depth image.
Why it matches plant phenotyping methods茶葉の水分含量という植物器官の状態を、マルチスペクトル・深度画像、分類、回帰、画像登録、検出高さ補正により推定・可視化する方法が研究の中心である。
abstractmultispectral and depth images were utilized for tea moisture content detection
Spectroscopic sensing provides physical and chemical information in a non-destructive and rapid manner. To develop non-destructive estimation methods of tea quality-related metabolites in fresh leaves, we estimated the contents of free amino acids, catechins, and caffeine in fresh tea leaves using visible to short-wave infrared hyperspectral reflectance data and machine learning algorithms. We acquired these data from approximately 200 new leaves with various status and then constructed the regression model in the combination of six spectral patterns with pre-processing and five algorithms. In most phenotypes, the combination of de-trending pre-processing and Cubist algorithms was robustly selected as the best combination in each round over 100 repetitions that were evaluated based on the ratio of performance to deviation (RPD) values. The mean RPD values were ranged from 1.1 to 2.7 and most of them were above the acceptable or accurate threshold (RPD = 1.4 or 2.0, respectively). Data-based sensitivity analysis identified the important hyperspectral regions around 1500 and 2000 nm. Present spectroscopic approaches indicate that most tea quality-related metabolites can be estimated non-destructively, and pre-processing techniques help to improve its accuracy.
Why it matches plant phenotyping methods新鮮茶葉の代謝物を非破壊推定する分光センシングと機械学習モデルの開発・評価が研究の中心であり、植物形質の取得手法に該当する。
abstractTo develop non-destructive estimation methods of tea quality-related metabolites in fresh leaves, we estimated the contents of free amino acids, catechins, and caffeine in fresh tea leaves using visible to short-wave infrared hyperspectral reflectance data and machine learning algorithms.
TeaLiDAR / point cloudLeaf2D/3D reconstructionArchitecture / morphology / geometry
Plant leaf 3D architecture changes during growth and shows sensitive response to environmental stresses. In recent years, acquisition and segmentation methods of leaf point cloud developed rapidly, but 3D modelling leaf point clouds has not gained much attention. In this study, a parametric surface modelling method was proposed for accurately fitting tea leaf point cloud. Firstly, principal component analysis was utilized to adjust posture and position of the point cloud. Then, the point cloud was sliced into multiple sections, and some sections were selected to generate a point set to be fitted (PSF). Finally, the PSF was fitted into non-uniform rational B-spline (NURBS) surface. Two methods were developed to generate the ordered PSF and the unordered PSF, respectively. The PSF was firstly fitted as B-spline surface and then was transformed to NURBS form by minimizing fitting error, which was solved by particle swarm optimization (PSO). The fitting error was specified as weighted sum of the root-mean-square error (RMSE) and the maximum value (MV) of Euclidean distances between fitted surface and a subset of the point cloud. The results showed that the proposed modelling method could be used even if the point cloud is largely simplified (RMSE < 1 mm, MV < 2 mm, without performing PSO). Future studies will model wider range of leaves as well as incomplete point cloud.
Why it matches plant phenotyping methods茶葉点群から葉の3D構造を推定するNURBS表面モデリング手法の開発が主題であり、植物形態のフェノタイピング手法に該当する。
abstracta parametric surface modelling method was proposed for accurately fitting tea leaf point cloud.
Background Photosynthetic pigments participating in the absorption, transformation and transfer of light energy play a very important role in plant growth. While, the spatial distribution of foliar pigments is an important indicator of environmental stress, such as pests, diseases and heavy metal stress. Results In this paper, in situ quantitative visualization of chlorophyll and carotenoid was realized by combining the Raman spectroscopy with calibration model transfer, and a laboratory Raman spectral model was successfully extended to a portable field spectral measurement. Firstly, a nondestructive and fast model for determination of chlorophyll and carotenoid in tea leaf was established based on confocal micro-Raman spectrometer in the laboratory. Then the spectral model was extended to a real-time foliar map scanning spectra of a field portable Raman spectrometer through calibration model transfer, and the spectral variation between the confocal micro-Raman spectrometer in the laboratory and the portable Raman spectrometer were effectively corrected by the direct standardization (DS) algorithm. The portable map scanning Raman spectra of the tea leaves after the model transfer were got into the established quantitative determination model to predict the concentration of photosynthetic pigments at each pixel of the tea leaves. The predicted photosynthetic pigments concentration of each pixel was imaged to illustrate the distribution map of foliar pigments. Statistical analysis showed that the predicted pigment contents were highly correlated with the real contents. Conclusions It can be concluded that the Raman spectroscopy was applicable for in situ, non-destructive and rapid quantitative detecting and imaging of photosynthetic pigment concentration in tea leaves, and the spectral detection model established based on the laboratory Raman spectrometer can be applied to a portable field spectrometer for quantitatively imaging of the foliar pigments.
Why it matches plant phenotyping methodsラマン分光と校正モデル移転を用いて茶葉のクロロフィル・カロテノイド濃度を画素単位で定量・画像化する手法を開発し、携帯型装置への移転と実測値との相関も検証しているため、植物フェノタイピング手法が中心である。
abstractin situ quantitative visualization of chlorophyll and carotenoid was realized by combining the Raman spectroscopy with calibration model transfer
Lesions of tea (Camellia sinensis) leaves are detrimental to the growth of tea crops. Their adverse effects include further disease of tea leaves and a direct reduction in yield and profit. Therefore, early detection and on‐site monitoring of tea leaf lesions are necessary for effective management to control infections and prevent further yield loss. In this study, 1,822 images of tea leaves with lesions caused by three diseases (brown blight, Colletotrichum camelliae; blister blight, Exobasidium vexans; and algal leaf spot, Cephaleuros virescens) and four pests (leaf miner, Tropicomyia theae; tea thrip, Scirtothrips dorsalis; tea leaf roller, Homona magnanima; and tea mosquito bug, Helopeltis fasciaticollis) were collected from northern and central Taiwan. A faster region‐based convolutional neural network (Faster R‐CNN) was then trained to detect the locations of the lesions on the leaves and to identify the causes of the lesions. The trained Faster R‐CNN detector achieved a precision of 77.5%, recall of 70.6%, an F1 score of 73.91%, and a mean average precision of 66.02%. An overall accuracy of 89.4% was obtained for identification of the seven classes of tea diseases and pests. The developed detector could assist tea farmers in identifying the causes of lesions in real time.
Why it matches plant phenotyping methods茶葉の病斑という植物の病害状態を画像から検出・分類するCNN手法を開発し、性能評価しており、植物フェノタイピング手法が研究の中心である。
abstractA faster region‐based convolutional neural network (Faster R‐CNN) was then trained to detect the locations of the lesions on the leaves and to identify the causes of the lesions.
Abstract Background: Photosynthetic pigments participating in the absorption, transformation and transfer of light energy play a very important role in plant growth. While, the spatial distribution of foliar pigments is an important indicator of environmental stress, such as pests, diseases and heavy metal stress. Results: In this paper, in situ quantitative visualization of chlorophyll and carotenoid was realized by combining the Raman spectroscopy with calibration model transfer, and a laboratory Raman spectral model was successfully extended to a portable field spectral measurement. Firstly, a nondestructive and fast model for determination of chlorophyll and carotenoid in tea leaf was established based on confocal micro-Raman spectrometer in the laboratory. Then the spectral model was extended to a real-time foliar map scanning spectra of a field portable Raman spectrometer through calibration model transfer, and the spectral variation between the confocal micro-Raman spectrometer in the laboratory and the portable Raman spectrometer were effectively corrected by the direct standardization (DS) algorithm. The portable map scanning Raman spectra of the tea leaves after the model transfer were got into the established quantitative determination model to predict the concentration of photosynthetic pigments at each pixel of the tea leaves. The predicted photosynthetic pigments concentration of each pixel was imaged to illustrate the distribution map of foliar pigments. Statistical analysis showed that the predicted pigment contents were highly correlated with the real contents. Conclusions: It can be concluded that the Raman spectroscopy was applicable for in situ, non-destructive and rapid quantitative detecting and imaging of photosynthetic pigment concentration in tea leaves, and the spectral detection model established based on the laboratory Raman spectrometer can be applied to a portable field spectrometer for quantitatively imaging of the foliar pigments.
Why it matches plant phenotyping methods茶葉の葉内クロロフィル・カロテノイド濃度を、ラマン分光とモデル移 transferにより非破壊・定量・画像化する手法を開発し、携帯型装置への移 transferと実含量との相関検証を行っており、植物表現型取得法が中心である。
abstractin situ quantitative visualization of chlorophyll and carotenoid was realized by combining the Raman spectroscopy with calibration model transfer
Nondestructive techniques for estimating nitrogen (N) status are essential tools for optimizing N fertilization input and reducing the environmental impact of agricultural N management, especially in green tea cultivation, which is notably problematic. Previously, hyperspectral indices for chlorophyll (Chl) estimation, namely a green peak and red edge in the visible region, have been identified and used for N estimation because leaf N content closely related to Chl content in green leaves. Herein, datasets of N and Chl contents, and visible and near-infrared hyperspectral reflectance, derived from green leaves under various N nutrient conditions and albino yellow leaves were obtained. A regression model was then constructed using several machine learning algorithms and preprocessing techniques. Machine learning algorithms achieved high-performance models for N and Chl content, ensuring an accuracy threshold of 1.4 or 2.0 based on the ratio of performance to deviation values. Data-based sensitivity analysis through integration of the green and yellow leaves datasets identified clear differences in reflectance to estimate N and Chl contents, especially at 1325-1575 nm, suggesting an N content-specific region. These findings will enable the nondestructive estimation of leaf N content in tea plants and contribute advanced indices for nondestructive tracking of N status in crops.
Why it matches plant phenotyping methods茶葉のハイパースペクトル反射と機械学習により葉の窒素・クロロフィル含量を非破壊推定する手法が研究の中心であり、植物形質の取得・推定に直接関与する。
abstractA regression model was then constructed using several machine learning algorithms and preprocessing techniques.
Functional traits can help elucidate and predict the impact of invasive plant species on ecosystem functioning. Yet, this approach requires comprehensive and labour‐intensive trait collection campaigns, covering intraspecific trait variation of both the invader and native species in the invaded community. One potential way to overcome these logistic constraints is using hyperspectral remote sensing technology to efficiently quantify functional trait values. Although such spectrally derived or ‘optical’ traits are known to closely link to directly measured functional traits, little research has explored how well these optical traits perform in assessing invader‐induced ecosystem impact. Here, we explored the trait‐mediated impact of the invasive Rosa rugosa on litter decomposition and evaluated whether optical traits perform equally well as directly measured traits in predicting litter decomposition variation. We collected data on species‐specific functional traits, leaf hyperspectral reflectance and standardized ‘tea bag index’ litter decomposition across 25 invaded and 25 uninvaded coastal grassland plots. The selected traits were all potentially related to litter decomposition and covered the leaf economics spectrum, additional leaf structural components and competitive ability. Optical traits were quantified through a combination of a physical radiative transfer model inversion and vegetation indices calculations. Invasion significantly increased the stabilization factor, i.e. the amount of resulting recalcitrant litter. Invader impact on litter decomposition could be entirely explained by changes it induced in the functional traits of the native community, rather than by the invader's traits itself. More specifically, the invader pushed the invaded community towards traits associated with high litter quality. Optical traits performed equally well as directly measured traits in explaining the invasion impact on the stabilization factor (R² = 41.9% vs. 38.5%). Furthermore, the interpretation of the results based on optical traits resulted in a similar functional understanding of the invader impact. Synthesis. Our results indicate the potential of hyperspectral data to explain changes in ecosystem functioning. The combination of radiative transfer models and vegetation indices allowed to extract all relevant trait information from the hyperspectral data. This framework thus presents a practical shortcut to assess relevant leaf traits, requiring only a limited amount of field trait measurements.
Why it matches plant phenotyping methodsハイパースペクトルデータから葉の機能形質を推定する手法を、直接測定形質と比較検証しており、植物形質の取得・抽出が研究の中心である。
Abstract At the moment, there are increasing trends of using deep learning for plant diseases detection. However, their implementations may be difficult in developing countries due to several reasons. First, existing deep learning models are usually trained with images with adequate resolutions. In developing countries however, with limited internet connection, models that would perform well even when data with low resolution are used are needed. Secondly, the generated models are large. Hence, most deep learning based applications are available on-line. Unfortunately, the trend for new deep learning architectures are either have larger models or require a heavy memory usage. So, models with smaller size would be preferred. In this paper, we evaluate various existing deep learning models for plant diseases detection when low resolution data are used. They are: VGGNet, AlexNet, Resnet, Xception, and MobileNet. Our focus is deep convolutional neural network (DCNN) which is commonly applied for image data. We also propose a new DCNN architecture with two branches of concatenated residual networks. It is well known that the deeper the networks the better performance of DCNN. However, DCNN with very deep networks and large number of training parameters is prone to vanishing gradient problems. One solutions for that is to apply residual networks as branches to DCNN. While it is found that increasing the branch of the networks benefit the performance, larger memory are required to train the networks. So, we apply two concatenated residual networks only. We called it Compact Networks (ComNet). We compare our method other with six popular CNN architectures. We evaluate the performance on the PlantVillage dataset and our own dataset. We collected images of tea leaves which consist of 6 classes: 5 classes of diseases that are commonly found in Indonesia and a healthy class. Our experiments show that our method is generally better than referenced DCNN networks.
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を提案し、複数モデルおよびデータセットで性能比較・評価しており、植物状態の取得手法が中心である。
abstractWe also propose a new DCNN architecture with two branches of concatenated residual networks.
Reproduction assets foundThe paper evaluates its ComNet and reference DCNN architectures on a subset of the public PlantVillage dataset (Apple, Corn, Potato; 9,176 images), which the authors explicitly link to a public GitHub repository. The authors' own tea disease dataset is not public and requires contacting the corresponding author. No作者-пDataset · publicoding; FF and VPR validated the dataset. All authors are contributed to the data
collections. All authors read and approved the final manuscript.
Funding
This work is partially funded by INSINAS grant from the Indonesian Ministry of Research, Technology, and Higher
Education.
Availability of data and materials
The Plantvillage: https://github.com/spMohanty/PlantVillage-Dataset. The tea dataset that are used during the current
study are not publicly available due to it is in the process of agreement between Research Center for Informatics and
Research Institute for Tea and Cinchona but are available from the corresponding author on reasonable request.
Competing interests
The authors declare tOpen asset ↗spMohanty/PlantVillage-Datasetpdf-raw-page:19 lines:1-50Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
A multi-channel photon sensor (MPS) capable of measuring Red Photon Flux Density (RPFD), Blue Photon Flux Density (BPFD) and Photosynthetic Photon Flux Density (PPFD) based on silicon photodiodes and filters is designed. At the same time, the FPGA-based environmental control system realizes the closed-loop control of RPFD, BPFD and PPFD by reading the data collected by the MPS that slides up and down according to the height of the canopy of the plant and using the PWM signal to control the LED light board’s red and blue channel. Based on the above method, the article completed an Artificial Climate Chamber (ACC) that realizes the automatic regulation of PPFD and RPFD/BPFD (R/B) of plant canopy that are the key parameters for determining the light formulations of plant lighting and environmental parameters including temperature, relative humidity, CO₂ concentration, photoperiod etc. At a significantly lower cost, the MPS’s photon response curve is close to the ideal value, and the linear response R² of the calibration exceeds 0.999. After setting the parameters for 30 s, the RPFD, BPFD and PPFD control error of the ACC are 1.43%, 1.39% and 0.71%, respectively. The paper also used tea seedlings as materials to explore the physiological and biochemical indexes of leaves under different R/B and PPFD. By comparing the biomass accumulation, free amino acid, tea polyphenols, polyphenols / amino acid ratio and other key parameters, PPFD = 100μmol∙m-2∙s-1 and R/B = 1/3 is the optimal light formulations for artificial light cultivation of tea seedlings.
Why it matches plant phenotyping methods植物キャノピーの光量子束密度を測定・制御するセンサーと人工気候室を開発し、校正精度と制御誤差を検証しているため、植物表現型取得・環境制御基盤が中心です。茶苗の生理指標測定もこの基盤の実証として行われています。
abstractA multi-channel photon sensor (MPS) capable of measuring Red Photon Flux Density (RPFD), Blue Photon Flux Density (BPFD) and Photosynthetic Photon Flux Density (PPFD) based on silicon photodiodes and filters is designed.
Why it matches plant phenotyping methods生きた茶植物内のフッ素輸送・分布を、18Fトレーサーと陽電子放出トレーサー画像化システムでリアルタイム取得しており、植物の生理状態を可視化する画像計測法の実質的な適用が中心です。
abstractF arrived at an aerial plant part about 1.5 h after absorption by roots, suggesting that tea roots had a retention effect on F, and then was transported upward mainly via the xylem and little via the phloem along the tea stem
Smartphones are equipped with various types of sensors which make them a promising tool to assist diverse digital farming tasks because of their mobility, cost, accessibility, and computing power allow us to perform real-time practical applications. This paper presents the utilization of various non-destructive methods of nutrient and disease classification techniques using smartphone collected images, processed through various image segmentation algorithms. Both in vivo and in vitro estimations shows comparable results with both chlorophyll and nitrogen contents of a crop shoot. Moreover, the correlation between SPAD measured values and nitrogen of crop shoot showed a significant linear association (R 2 =0.7309), revealing the potency of in vivo observation for prediction of actual chlorophyll content in tea crop. SPAD values and yield have a strong linear relationship (R 2 =0.7103), in which SPAD-meter performed better detection at very low values. The study concluded that the proposed techniques could be used for automatic detection as well as classification of foliar diseases and nutrients in tea.
Why it matches plant phenotyping methodsスマートフォン画像と画像セグメンテーションにより、茶葉の栄養・病害およびクロロフィル／窒素などの機能形質を非破壊推定する手法を開発・評価しており、形質取得法が研究の中心である。
titleDevelopment of non-destructive methods to estimate functional traits and field evaluation in tea plantations using a smartphone
Tea trees are kept in shaded locations to increase their chlorophyll content, which influences green tea quality. Therefore, monitoring change in chlorophyll content under low light conditions is important for managing tea trees and producing high-quality green tea. Hyperspectral remote sensing is one of the most frequently used methods for estimating chlorophyll content. Numerous studies based on data collected under relatively low-stress conditions and many hyperspectral indices and radiative transfer models show that shade-grown tea performs poorly. The performance of four machine learning algorithms-random forest, support vector machine, deep belief nets, and kernel-based extreme learning machine (KELM)-in evaluating data collected from tea leaves cultivated under different shade treatments was tested. KELM performed best with a root-mean-square error of 8.94 ± 3.05 μg cm -2 and performance to deviation values from 1.70 to 8.04 for the test data. These results suggest that a combination of hyperspectral reflectance and KELM has the potential to trace changes in the chlorophyll content of shaded tea leaves.
Why it matches plant phenotyping methods茶葉のクロロフィル含量という植物形質を、ハイパースペクトル反射と機械学習で非破壊推定する手法が研究の中心であり、複数アルゴリズムの性能比較・評価も行っている。
titleNon-Destructive Detection of Tea Leaf Chlorophyll Content Using Hyperspectral Reflectance and Machine Learning Algorithms.
We developed a novel substrate for the collection of volatile organic compounds (VOCs) emitted from either living or dried plant material to be analyzed by surface-enhanced Raman spectroscopy (SERS). We demonstrated that this substrate can be utilized to differentiate emissions from blends of three teas, and to differentiate emissions from healthy cotton plants versus caterpillar-infested cotton plants. The substrate we developed can adsorb VOCs in static headspace sampling environments, and VOCs naturally evaporated from three standards were successfully identified by our SERS substrate, showing its ability to differentiate three VOCs and to detect quantitative differences according to collection times. In addition, volatile profiles from plant materials that were either qualitatively different among three teas or quantitatively different in abundance between healthy and infested cotton plants were confirmed by collections on Super-Q resin for dynamic headspace and solid-phase microextraction for static headspace sampling, respectively, followed by gas chromatography to mass spectrometry. Our results indicate that both qualitative and quantitative differences can also be detected by our SERS substrate although we find that the detection of quantitative differences could be improved.
Why it matches plant phenotyping methods生植物からのVOC収集・SERS分析基質を開発し、健全な綿花と食害綿花の差異を検出・評価しているため、植物状態の取得法が研究の中心である。
abstractWe developed a novel substrate for the collection of volatile organic compounds (VOCs) emitted from either living or dried plant material to be analyzed by surface-enhanced Raman spectroscopy (SERS).
Why it matches plant phenotyping methods茶葉の窒素状態と葉窒素含量という植物状態・形質を、ハイパースペクトル画像と化学計量モデルで診断・推定する手法が研究の中心であるため。
abstractThis study aimed to evaluate the potential of hyperspectral imaging coupled with chemometrics for the qualitative and quantitative diagnosis of N status in tea plants under field conditions.
Anthracnose (Gloeosporium theae-sinesis Miyake) is an important and common foliar disease in tea plants and is a severe threat to tea quality and production. Hyperspectral imaging technology enables non-invasive, objective detection of the damages ca by foliar disease and offers significant potential for plant disease prevention and phenotyping. This study proposes a novel method for detecting anthracnose in tea plants based on hyperspectral imaging. By analyzing the spectral sensitivity, we identified disease-sensitive bands at 542, 686, and 754 nm and used these bands to create two new disease indices: the Tea Anthracnose Ratio Index (TARI) and the Tea Anthracnose Normalized Index (TANI). Based on an optimized set of spectral features, a strategy combining unsupervised classification and adaptive two-dimensional thresholding was developed to detect disease scabs. Compared with traditional pixel-based classification methods, the proposed method was not affected by leaf background differences and thereby provides an effective means for disease identification and damage analysis. The validation results gave an overall accuracy of 98% for identifying the disease at the leaf level and 94% at the pixel level. These results suggest that automated and accurate detection of anthracnose-infected tea leaves is possible by using hyperspectral imaging for practical tea-plant protection.
Why it matches plant phenotyping methods茶葉の病斑をハイパースペクトル画像から抽出・判定する手法を開発し、葉および画素レベルで精度検証しており、植物病害状態の表現型取得が中心である。
abstractThis study proposes a novel method for detecting anthracnose in tea plants based on hyperspectral imaging.
The tenderness of the fresh tea leaves can affect the quality of tea products. It is important to develop a mechanized, accurate way to evaluate the quality of fresh leaves that avoids the uncertainty of a subjective evaluation. Herein, an in-situ, ultra-rapid Raman microscopy strategy to quantify carotenoids in tea leaves was established. The Raman microscopy of carotenoids distribution in leaves from new branches of 22 representative tea varieties showed that the average carotenoid signals increased from a low level in the bud to a high level in the fourth leaf, which represent different developmental stages. The concentration of carotenoids in the bud to fourth leaf, which were from 69.1 ng mg -1 to 199.5 ng mg -1 , respectively. These results demonstrate that Raman imaging can serve as an in-situ, non-destructive and ultra-rapid technology for determining the tenderness of fresh tea leaves and be used in quality control for tea processing.
Why it matches plant phenotyping methods茶葉の柔らかさ（発育段階・品質）を評価するためのラマン画像計測法を開発しており、植物形質の取得手法が研究の中心である。
abstractHerein, an in-situ, ultra-rapid Raman microscopy strategy to quantify carotenoids in tea leaves was established.
Why it matches plant phenotyping methods茶植物の窒素状態・葉内窒素含量を、圃場でのハイパースペクトル画像とケモメトリクスにより推定し、分類・回帰性能を評価しているため、植物表現型取得法が中心である。
abstractThis study aimed to evaluate the potential of hyperspectral imaging coupled with chemometrics for the qualitative and quantitative diagnosis of N status in tea plants under field conditions.
In India, an estimated 15-25% of potential crop production is lost due pest and diseases (Roy and Bezbaruah, 2002). The country needs not only to raise production but also ensure food security for its growing consumption needs while curbing excessive pesticide usage. Detection of pests and diseases at an early stage plays a significant role in addressing the above-mentioned concerns and image classification offers a cost-effective and scalable solution to the disease detection problem (A. Ramcharan et al. 2017). Here, the principles of transfer learning are implemented with pretrained model – Resnet34 (K. He et al. 2015), and test its effectiveness in image classification using a dataset of tea leaves. The novelty of this work is that the images used are not curated, individual leaves with controlled backgrounds but of plants in-situ. The effect of the level of zoom and background is examined and class activation maps are used to validate that the basis of classification is indeed the disease and not an artificial bias from factors such as background, lighting etc.
Why it matches plant phenotyping methods茶葉の病害を植物画像から分類する方法を開発・検証しており、背景やズームの影響、クラス活性化マップによる妥当性確認も扱うため、病害状態のフェノタイピング手法が中心です。
abstractimage classification offers a cost-effective and scalable solution to the disease detection problem
In order to improve the reconstruction effect of plant hyperspectral images, a region-based block compressive sensing (RBCS) algorithm is proposed. Local means and local standard deviations (LMLSD) criterion is used to select the optimal band in the hyperspectral images. The k-means clustering algorithm is introduced to extract the tea regions from the optimal band. And spatial adaptive blocking strategy is involved to realize the optimized spatial blocking only for tea regions in the hyperspectral images. Then discrete cosine transform (DCT) sparse basis and random gaussian measurement matrix are combined to compress the data. Finally, stagewise orthogonal matching pursuit (StOMP) algorithm is used to reconstruct plant hyperspectral images. Peak signal to noise ratio (PSNR), spectrum curve and spectral angle mapper (SAM) and the error of spectral indices are used to evaluate the reconstructed performance in the spatial and spectral domains. Experimental results show that the reconstructed performance of RBCS is significantly better than that of single spectral compressive sensing (SSCS) and block compressive sensing (BCS) at different sampling ratios.
Why it matches plant phenotyping methods植物ハイパースペクトル画像の再構成を目的とする圧縮センシング手法を開発し、茶領域抽出、空間・スペクトル性能を定量評価しており、植物画像取得・解析手法が中心である。
abstractIn order to improve the reconstruction effect of plant hyperspectral images, a region-based block compressive sensing (RBCS) algorithm is proposed.
TeaLaboratory / benchtopMultispectral / hyperspectralLeafPhysiological trait estimationWater status / transpiration
Hitherto, the rapid and nondestructive determination of the moisture content of tea leaves is still an unresolved issue because the upward facing surfaces of tea leaves lying on a conveyor belt are randomly chosen by the collapse of the leaves onto their front side or back side. To study the above issue, hyperspectral images of both the front side and back side of tea leaves on a conveyor belt were captured in the lab to simulate a practical production environment, and LS-SVR models with Rᵥ² values of 0.951 and 0.918 for the front side and back side, respectively, were established based on their characteristic spectral bands. To ensure that the spectrum of each pixel can be correctly imported into its corresponding model, a logistic regression classifier with a correct classification rate of 100% was designed to identify the front side and back side of the leaves. Finally, a distribution map of the moisture content of the tea leaves was generated successfully according to the following steps: (1) Extracting the average spectrum of each leaf; (2) Identifying which side of the leaf the spectrum belongs to; (3) Importing the adjusted spectrum of each pixel into its corresponding regression model; and (4) Generating a distribution map of the moisture content. This research creatively provides a scheme for detecting the moisture content of tea leaves.
Why it matches plant phenotyping methods茶葉の水分含量という植物器官形質を、ハイパースペクトル画像と回帰・分類モデルで非破壊推定する方法の開発が中心である。
abstractthe rapid and nondestructive determination of the moisture content of tea leaves is still an unresolved issue
Why it matches plant phenotyping methods茶葉の病害面積・状態を赤外熱画像から抽出する画像処理アルゴリズムを開発し、人手観察との相関で検証しており、植物病害表現型の取得が中心である。
abstractThe overall goal of this study is to develop an effective, simple, apt computer vision algorithm to detect tea disease area using infrared thermal image processing techniques and to estimate tea disease.
Why it matches plant phenotyping methods茶葉の色素含量という植物生理形質を、HSIと波長選択・PLSRで非破壊推定する手法が研究の中心であり、予測性能も評価している。
abstractThe present study aimed to predict chlorophyll a (Chl a), chlorophyll b (Chl b), total chlorophyll (total Chl), and carotenoid (Car) content in tea leaves under different levels of nitrogen treatment using hyperspectral imaging (HSI) in combination with variable selection algorithms.
TeaMultispectral / hyperspectralLeafPhysiological trait estimationVisualization / data managementWater status / transpiration
Effective visualization of moisture content in tea leaves isveryimportant in the tea cultivation industry and in favor of irrigation management in tea garden. In order to obtain the moisture content distribution map of tea leaves, successive projections algorithm(SPA) coupled with stepwise regression(SPA-SR) and competitive adaptive reweighted sampling(CARS) coupled with stepwise regression(CARS-SR) were proposed to select characteristic wavelengths in this study. The whole region of the tea leaves were selected as region of interest (ROI) to extract the NIR hyperspectral reflectance. Moreover, Savitzky-Golay smoothing(SG), orthogonal signal correction(OSC), multiplicative scatter correction(MSC) and detrending were used to handle with raw spectra. In addition, four feature selection algorithms(SPA, CARS, SPA-SR and CARS-SR) were used to extract the most effective wavelengths. Furthermore, multiple linear regression (MLR) was adopted to establish the prediction models based on spectrum after 20 different combination algorithm treatments. The results showed that SPA-SR and CARS-SR can effectively improve the correlation coefficient of prediction set in established MLR models compared with SPA and CARS, respectively. Besides, the combination algorithm for obtaining the best prediction MLR model was SG-MSC coupled with CARS-SR(Rp2=0.8631 and RMSEP=0.0163), and it was applied to retrieve the distribution of moisture content in tea leaves. Visualizing distribution map of tea leaves offered a more intuitive and comprehensive assessment of moisture contents at each pixel, and it provides a novel approach to evaluate plant irrigation.
Why it matches plant phenotyping methods茶葉の葉面水分含量という植物状態を、NIRハイパースペクトル画像と波長選択・回帰モデルで画素単位に推定・可視化する手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。
abstractIn order to obtain the moisture content distribution map of tea leaves, successive projections algorithm(SPA) coupled with stepwise regression(SPA-SR) and competitive adaptive reweighted sampling(CARS) coupled with stepwise regression(CARS-SR) were proposed to select characteristic wavelengths in this study.
Why it matches plant phenotyping methods赤外線熱画像から茶樹の病害領域を抽出・推定する画像処理アルゴリズムを開発し、人手計数と比較検証しており、植物病害状態の取得手法が中心である。
abstractThe overall goal of this study is to develop an effective, simple, apt computer vision algorithm to detect tea disease area using infrared thermal image processing techniques and to estimate tea disease.
For the purpose of improving the extraction of tea plant leaf disease saliency map under complex backgrounds, a new algorithm combining SLIC (Simple Linear Iterative Cluster) with SVM (Support Vector Machine) is proposed in this paper. Firstly, super-pixel block is obtained by SLIC algorithm, significant point is detected by Harris algorithm, and fuzzy salient region contour is extracted by employing convex hull method. Secondly, the four-dimensional texture features of super-pixel blocks in salient regions and background areas are extracted, and then the classification map is obtained by classifying the super-pixel blocks with the help of SVM classifier. Lastly, the morphological and algebraic operations are implemented for repairing classified super-pixel blocks. As a result, one accurate saliency map of tea plant leaf disease image is obtained. Through testing based on 261 diseased images, the quality evaluation index, the accuracy, precision, recall and F-value are 98.5%, 96.8%, 98.6% and 97.7%, respectively. It demonstrates that the proposed method performs better than the other three SLIC-based algorithms in visual effects and quality assessment index. Such conclusion can be drawn that the proposed method can effectively extract tea plant leaf disease saliency map from complex background. Consequently, this research is expected to lay a good basis for the study of tea plant leaf disease identification. Last but not the least, the proposed method has good potential that extracts saliency map of crops or plants disease.
Why it matches plant phenotyping methods茶葉の病害葉画像から病斑の顕著領域を抽出する画像解析手法を開発し、261枚の画像で性能比較・評価しているため、植物病害状態の表現型取得が中心である。
abstracta new algorithm combining SLIC (Simple Linear Iterative Cluster) with SVM (Support Vector Machine) is proposed in this paper
TeaField / plotRGB / grayscaleLeafClassificationSegmentationGrowth / development / phenologyLeaf traits
The harvesting time of fresh tea leaves has a significant impact on product yield and quality. The aim of this study was to propose a method for real-time monitoring of the optimum harvesting time for picking fresh tea leaves based on machine vision. Firstly, the shapes of fresh tea leaves were distinguished from RGB images of the tea-tree canopy after graying with the improved B-G algorithm, filtering with a median filter algorithm, binary processing with the Otsu algorithm, and noise reduction and edge smoothing using open and close operations. Then the leaf characteristics, such as leaf area index, average length, and leaf identification index, were calculated. Based on these, the Bayesian discriminant principle and method were used to construct a discriminant model for fresh tea-leaf collection status. When this method was applied to a RGB tea-tree canopy image acquired at 45° shooting angle, the fresh tea-leaf recognition rate was 90.3%, and the accuracy for fresh tea-leaf harvesting status was 98% by cross validation. Hence, this method provides the basic conditions for future tea-plantation operation and management using information technology, automation, and intelligent systems. Keywords: agricultural machinery, fresh tea leaves, machine vision, intelligent recognition, real-time monitoring DOI: 10.25165/j.ijabe.20191201.3418 Citation: Zhang L, Zhang H D, Chen Y D, Dai S H, Li X M, Imou K, Liu Z H, et al. Real-time monitoring of optimum timing for harvesting fresh tea leaves based on machine vision. Int J Agric & Biol Eng, 2019; 12(1): 6–9.
Why it matches plant phenotyping methods茶樹キャノピー画像から葉形状・葉面積指数・平均長などの植物形質を抽出し、収穫適期を判定する機械視覚手法を開発・検証しており、フェノタイピング手法が中心である。
abstractThe aim of this study was to propose a method for real-time monitoring of the optimum harvesting time for picking fresh tea leaves based on machine vision.
It is highly possible that tea ( Camellia sinensis ) plant is attacked by more than one pest species at the same time, and the determination of their proportion is of great significance to the management of tea plants. However, there are no literatures focusing on it previously. In this work, two pest species ( Ectropis obliqua and Ectropis grisescens ) in six different ratios (10:0, 8:2, 6:4, 4:6, 2:8 and 0:10) were applied to attack tea plants and electronic nose (E‐nose) was employed to detect them, labelled as group 10:0, 8:2, 6:4, 4:6, 2:8 and 0:10, respectively. Two prediction methods were applied to predict the ratio of E. obliqua and E. grisescens attacking tea plant and their performances were compared. The first method employed regression algorithm for prediction analysis based on the whole E‐nose data directly. The second method classified tea plants into three main classes (the first class contained group 10:0, the second class contained groups 8:2, 6:4, 4:6 and 2:8, and the third class contained group 0:10) first, then regression algorithm was applied to deal with the second class for prediction analysis. The results showed that the second method had a better performance. Its discrimination results showed 100% of the correct classification rate for training set and 93.75% for testing set. Meanwhile, its prediction results showed 0.0005 of root mean square error (RMSE) for calibration set, 0.0064 for validation set and 99.07% of fitting correlation coefficients ( R 2 ) for calibration set, 91.22% for validation set, which were acceptable for prediction analysis and proved that E‐nose was a feasible technique for pests' ratio prediction.
Why it matches plant phenotyping methods電子鼻を用いて茶樹への複数害虫加害比率を植物から推定し、分類・回帰性能を比較検証しており、植物の状態推定手法が研究の中心である。
abstractelectronic nose (E‐nose) was employed to detect them
TeaField / plotRGB / grayscaleLeafClassificationSegmentationGrowth / development / phenologyLeaf traits
The harvesting time of fresh tea leaves has a significant impact on product yield and quality. The aim of this study was to propose a method for real-time monitoring of the optimum harvesting time for picking fresh tea leaves based on machine vision. Firstly, the shapes of fresh tea leaves were distinguished from RGB images of the tea-tree canopy after graying with the improved B-G algorithm, filtering with a median filter algorithm, binary processing with the Otsu algorithm, and noise reduction and edge smoothing using open and close operations. Then the leaf characteristics, such as leaf area index, average length, and leaf identification index, were calculated. Based on these, the Bayesian discriminant principle and method were used to construct a discriminant model for fresh tea-leaf collection status. When this method was applied to a RGB tea-tree canopy image acquired at 45° shooting angle, the fresh tea-leaf recognition rate was 90.3%, and the accuracy for fresh tea-leaf harvesting status was 98% by cross validation. Hence, this method provides the basic conditions for future tea-plantation operation and management using information technology, automation, and intelligent systems. Keywords: agricultural machinery, fresh tea leaves, machine vision, intelligent recognition, real-time monitoring DOI: 10.25165/j.ijabe.20191201.3418 Citation: Zhang L, Zhang H D, Chen Y D, Dai S H, Li X M, Imou K, Liu Z H, et al. Real-time monitoring of optimum timing for harvesting fresh tea leaves based on machine vision. Int J Agric & Biol Eng, 2019; 12(1): 6–9.
Why it matches plant phenotyping methods茶樹キャノピーのRGB画像から葉形状・葉面積指数・平均長などの植物形質を抽出し、収穫適期を判定する機械視覚手法を中心に開発・検証しているため。
abstractThe aim of this study was to propose a method for real-time monitoring of the optimum harvesting time for picking fresh tea leaves based on machine vision.
Why it matches plant phenotyping methods茶葉の色素含量という植物形質を、ハイパースペクトル画像と波長選択・回帰モデルで非破壊推定する手法が研究の中心であり、予測性能も評価しているため。
abstractThe present study aimed to predict chlorophyll a (Chl a), chlorophyll b (Chl b), total chlorophyll (total Chl), and carotenoid (Car) content in tea leaves under different levels of nitrogen treatment using hyperspectral imaging (HSI) in combination with variable selection algorithms.
It is generally feasible to classify different species of vegetation based on remotely sensed images, but identification of different sub-species or even cultivars is uncommon. Tea trees ( Camellia sinensis L.) have been proven to show great differences in taste and quality between cultivars. We hypothesize that hyperspectral remote sensing would make it possibly to classify cultivars of plants and even to estimate their taste-related biochemical components. In this study, hyperspectral data of the canopies of tea trees were collected by hyperspectral camera mounted on an unmanned aerial vehicle (UAV). Tea cultivars were classified according to the spectral characteristics of the tea canopies. Furthermore, two major components influencing the taste of tea, tea polyphenols (TP) and amino acids (AA), were predicted. The results showed that the overall accuracy of tea cultivar classification achieved by support vector machine is higher than 95% with proper spectral pre-processing method. The best results to predict the TP and AA were achieved by partial least squares regression with standard normal variant normalized spectra, and the ratio of TP to AA-which is one proven index for tea taste-achieved the highest accuracy ( R CV = 0.66, RMSE CV = 13.27) followed by AA ( R CV = 0.62, RMSE CV = 1.16) and TP ( R CV = 0.58, RMSE CV = 10.01). The results indicated that classification of tea cultivars using the hyperspectral remote sensing from UAV was successful, and there is a potential to map the taste-related chemical components in tea plantations from UAV platform; however, further exploration is needed to increase the accuracy.
Why it matches plant phenotyping methodsUAV搭載ハイパースペクトル画像を用いて茶樹キャノピーから品種および生化学的形質を推定する手法が研究の中心であり、単なる生物学的実験の routine measurement ではない。
abstracthyperspectral data of the canopies of tea trees were collected by hyperspectral camera mounted on an unmanned aerial vehicle (UAV).
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 · publicHyperspectral Images obtained by UAV, measured TP and AA content were used as raw data and uploaded to Figshare:
https://figshare.com/articles/spectra_data_of_tea_plantation/5844801 .
Fei, Teng (2018): Spectra data of tea plantation. figshare. Figure. https://doi.org/10.6084/m9.figshare.5844801.v1 .Open asset ↗figshare · 10.6084/m9.figshare.5844801.v1lines:386-480Plant phenotyping relevance match · UnverifiedEurope PMC · checked 10 Sept 2026
RiceTeaRootPhysiological trait estimationVisualization / data managementStress response / tolerance
Lipid peroxidation is a physiological indicator of both biotic and abiotic stress responses, hence is often used as a biomarker to assess stress-induced cell damage or death. Here we demonstrate an easy, quick and cheap staining method to assess lipid peroxidation in plant tissues. In this methodology, Schiff's reagent, is used to assay for membrane degradation. Histochemical detection of lipid peroxidation is performed in this protocol. In brief, Schiff's reagent detects aldehydes that originate from lipid peroxides in stressful condition. Schiff's reagent is prepared and applied to plants tissue. After the reaction, plant tissue samples are rinsed with a sulfite solution to retain the staining color. From this analysis, qualitative visualization of lipid peroxidation in plant tissue is observed in the form of magenta coloration. This reagent is useful for visualization of stress induced lipid peroxidation in plants. In this protocol, Indica rice root, Assam tea root and Indian mustard seedlings are used for demonstration.
Why it matches plant phenotyping methods植物組織の脂質過酸化という生理状態を可視化する組織化学的測定法そのものが中心であり、単なる生物学的実験の routine measurement ではない。
abstractHere we demonstrate an easy, quick and cheap staining method to assess lipid peroxidation in plant tissues.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Summary Simplifying sample processing, shortening the sample preparation time, and adjusting procedures to suitable for new health and safety regulations, these issues are the current challenges which electron microscopic examinations need to face. In order to resolve these problems, new plant tissue sample processing protocols for transmission electron microscopy should be developed. In the present study, we chose the LR‐White resin‐assisted processing protocol for the ultrastructural observation of different types of plant tissues. Moreover, we explored Oolong tea extract (OTE) as a substitute for UA in staining ultrathin sections of plant samples. The results revealed that there was no significant difference between the OTE double staining method and the traditional double staining method. Furthermore, in some organelles, such as mitochondria in root cells of tomatoes and chloroplast in leaf cells of watermelons, the OTE double staining method achieved little better results than the traditional double staining method. Therefore, OTE demonstrated good potentials in replacing UA as a counterstain on ultrathin sections. In addition, sample preparation time was significantly shortened and simplified using LR‐White resin. This novel protocol reduced the time for preparing plant samples, and hazardous reagents in traditional method (acetone and UA) were also replaced by less toxic ones (ethanol and OTE).
Why it matches plant phenotyping methods植物組織のTEM観察における試料調製・染色プロトコル自体を開発・比較しており、植物の超微細構造を取得する画像計測法の技術的貢献が中心である。
abstractnew plant tissue sample processing protocols for transmission electron microscopy should be developed
The research achievements and trends of spectral technology in fast detection of Camellia sinensis growth process information and tea quality information were being reviewed. Spectral technology is a kind of fast, nondestructive, efficient detection technology, which mainly contains infrared spectroscopy, fluorescence spectroscopy, Raman spectroscopy and mass spectroscopy. The rapid detection of Camellia sinensis growth process information and tea quality is helpful to realize the informatization and automation of tea production and ensure the tea quality and safety. This paper provides a review on its applications containing the detection of tea (Camellia sinensis) growing status(nitrogen, chlorophyll, diseases and insect pest), the discrimination of tea varieties, the grade discrimination of tea, the detection of tea internal quality (catechins, total polyphenols, caffeine, amino acid, pesticide residual and so on), the quality evaluation of tea beverage and tea by-product, the machinery of tea quality determination and discrimination. This paper briefly introduces the trends of the technology of the determination of tea growth process information, sensor and industrial application. In conclusion, spectral technology showed high potential to detect Camellia sinensis growth process information, to predict tea internal quality and to classify tea varieties and grades. Suitable chemometrics and preprocessing methods is helpful to improve the performance of the model and get rid of redundancy, which provides the possibility to develop the portable machinery. Future work is to develop the portable machinery and on-line detection system is recommended to improve the further application. The application and research achievement of spectral technology concerning about tea were outlined in this paper for the first time, which contained Camellia sinensis growth, tea production, the quality and safety of tea and by-produce and so on, as well as some problems to be solved and its future applicability in modern tea industrial.
Why it matches plant phenotyping methods茶樹の生育状態（窒素、クロロフィル、病害虫など）をスペクトル技術で検出する方法を中心にレビューしており、植物表現型取得手法のレビューとして適格です。茶品質や加工品も含みますが、植物生育情報のセンシングが明示されています。
abstractThe research achievements and trends of spectral technology in fast detection of Camellia sinensis growth process information and tea quality information were being reviewed.
Blister blight caused by the biotrophic fungus, Exobasidium vexans Massee, is the most problematic foliar disease of tea in Sri Lanka. A reliable and accurate method is needed for field assessment of severity of the disease for epidemiological studies, formulating disease control strategies and crop improvement programmes. A field assessment key with 0–6 scores was developed for blister blight, considering the lowest (0) and highest (>30%) limits of disease severity observed in the field and different stages of symptom development. The key was validated by six raters, 3 experienced and 3 inexperienced. The field assessment trials made using the key were accurate and precise (R2 > 0.80). The area under the disease progress curve (AUDPC), calculated using the disease severity levels obtained using the assessment key, was used to combine multiple observations of disease progress into a 0–9 susceptible scale. Ascending numbers in the scale represent increasing susceptibility. The new scale was proposed to discriminate blister blight resistance in tea accessions/cultivars in field screening. Screening trials for validation of the susceptible scale, conducted using tea cultivars of known resistance or susceptibility levels and newly developed accessions of tea, at three locations, revealed that the 0–9 scale is simple to apply, offers a fine discrimination of blister blight resistance levels, and allows objective evaluation.
Why it matches plant phenotyping methods茶の葉の病害重症度を定量評価するフィールド評価キーと抵抗性スケールを開発・検証しており、植物表現型の取得手法が研究の中心です。
abstractA field assessment key with 0–6 scores was developed for blister blight