Comparative Analysis of Deep Learning Techniques for Enhanced Detection and Classification of Tomato Leaf Diseases: A Study

Tomato leaf diseases provide a significant challenge to crops productivity and quality, requiring accurate and timely evaluation for effective control. This paper offers a comparative review of sophisticated deep learning (DL) algorithms for the automated recognition and categorization of tomato foliar illnesses utilising picture data. Various advanced convolutional neural network (CNN) models, like ResNet, VGG19, and DenseNet variants, were trained, then validated on an extensive, annotated dataset of tomato leaf images displaying a range of disease symptoms. Performance was assessed using various criteria, with results compared to conventional image processing techniques. The research identifies the most effective and efficient model for disease detection and classification, illustrating that DL methods significantly surpass traditional methodologies. These findings highlight the practical capabilities of AI-driven systems for real-time crop surveillance, prompt intervention, and enhanced agricultural productivity.