Identification of Plant Leaf Diseases

Plant diseases remain a significant threat to global agriculture, necessitating rapid andaccurate detection to minimize crop loss. This paper presents a lightweight, end-to-end system for plantleaf disease detection and severity estimation, optimized for real-time field deployment. We propose acustom Convolutional Neural Network (CNN), built using PyTorch, trained on the PlantVillage datasetto classify leaves as healthy or diseased with a test accuracy of 92.06%. To enhance its practical relevance,we incorporate a classical image processing pipeline using OpenCV and NumPy to estimate the severityof infection by computing the ratio of diseased to total leaf area. These capabilities are integrated into across-platform mobile application developed using React Native, with inference served via a Flask-basedbackend API. The mobile app enables users to capture or upload images and instantly receive diagnosticresults, and severity percentages. Our system bridges the gap between deep learning research and real-worldagricultural application by combining accurate classification, interpretable severity estimation, and mobileaccessibility. This approach offers farmers a powerful, on-device digital assistant to monitor crop health andmake informed intervention decisions. Experimental results demonstrate strong generalization performance,visual alignment of model attention with infected regions, and real-time usability in field conditions.