PotatoGuardNet: a refined deep learning framework for potato leaf disease detection.

Abstract

Introduction The potato is one of the most consumed vegetable crops worldwide. However, the environmental changes and various crop diseases have a significant impact on potato production, indicating severe damage to yield quality and quantity. Farmers mostly employ manual disease classification methods in agriculture, which have limitations in detecting subtle disease symptoms, are time-intensive, and often necessitate specialized expertise, which may not be accessible in all farming communities. Therefore, automated systems are designed for accurate and rapid disease classification, mitigating the risks of misdiagnoses and delayed treatments. However, differences in the size, mass, and structure of the diseased areas of potato leaf diseases, combined with complex environmental conditions, complicate the effective identification of these diseases. Methods Therefore, to address the existing issues, we propose an improved deep learning approach, namely the PotatoGuardNet, which is an Inception-ResNet-V2-based Faster-RCNN model, for locating and classifying various potato leaf diseases. Precisely, the InceptionResNet-V2 approach is employed as the base network to capture the visual attributes of the samples, which are later recognized and classified by the 2-stage detector of the Faster-RCNN model. Results The model is tested on huge and complex data samples of potato plants from the PlantVillage dataset and reported a classification accuracy of 99.41%, along with an mAP of 0.9556. Further, the core working of the proposed method is evaluated by generating the heatmaps to show its explanatory power. Discussion Extensive experiments and comparative analyses against several recent state-of-the-art approaches confirm the effectiveness and reliability of PotatoGuardNet for potato leaf disease detection. The results demonstrate that the proposed framework successfully captures disease-specific visual patterns and provides accurate localization and classification, indicating its potential for practical deployment in automated agricultural disease monitoring systems.

Plant phenotyping relevance

ジャガイモ葉の病徴を画像から局在化・分類する深層学習手法を提案し、精度とmAPによる評価および比較実験を行っており、植物病害状態の表現型取得が中心である。

Code and data availability

The paper uses the public PlantVillage potato leaf image subset for its disease detection experiments, but the supplied blocks contain no authors' public URL, code deposit, trained model release, or dataset link for PlantVillage itself. The only external URL present (Oxford VGG CNN practicals) is a cited reference, not

No evidence-backed public reproduction asset is currently recorded.