Вебдіагностика захворювань сільськогосподарських культур засобами комп’ютерного зору

Abstract

This paper presents an intelligent computer vision system for detecting leaf diseases in tomatoes, potatoes and corn using deep learning. Convolutional neural networks with transfer learning classify leaf conditions from publicly available datasets of healthy and diseased leaves. The system combines an image analysis module with a rule-based recommendation subsystem that explains the diagnosis and suggests basic plant care actions. A web-based interface allows users to upload or capture leaf images and receive classification results with confidence scores and practical recommendations, with further extensions planned for climate-aware analysis and growth stage identification.