DEVELOPMENT OF A WEB BASED APPLICATION FOR DETECTION AND CLASSIFICATION OF TOMATO LEAF DISEASE USING CONVOLUTIONAL NEURAL NETWORK

Tomato leaf diseases pose significant threats to agricultural productivity and food security, requiring efficient and accurate detection methods to minimize crop losses. This study presents the development of a Convolutional Neural Network (CNN)-based system for detecting and classifying tomato leaf diseases, leveraging deep learning techniques to address the limitations of traditional manual diagnosis. Using a curated dataset of tomato leaf images, the system was trained to classify diseases such as Early Blight, Late Blight, and Bacterial Spot with high accuracy. The model achieved a validation accuracy of 97.1% after 50 training epochs, demonstrating its effectiveness in recognizing disease patterns. Key steps included data preprocessing, class distribution analysis, and visualization, which enhanced model performance and understanding. The trained model was integrated into a user-friendly application, allowing real-time disease detection through image uploads. This practical deployment highlights the potential of AI in agriculture to improve crop health monitoring and support timely intervention. Recommendations for future work include expanding the dataset, integrating Internet of Things (IoT) technologies, and optimizing the model for real-time deployment in diverse agricultural environments. This study underscores the transformative role of deep learning in advancing smart farming practices