Tomato Leaf Disease Detection Using CNN and Web Deployment Via Flask and Ngrok

Abstract

Tomato plants are heavily susceptible to a range of diseases that bring about major damage to crops in agriculture. Early detection and classification of these diseases are crucial for crop maintenance and conservation of production. This paper proposes a Convolutional Neural Network (CNN)-based multi-class classification for tomato leaf diseases. The model is trained on an open-source dataset and is deployed via a Flask web application, accessed using Ngok. The system provides real-time disease prediction based on user-uploaded images and provides specific remedies for each identified disease. The results of the experiments establish the effectiveness and usability of the proposed system.