The early and accurate detection of diseases in tomato plants is crucial for ensuring high crop yields and quality. Traditional methods of disease identification are often labor-intensive, time-consuming, and subject to human error. This research presents an enhanced classification system for detecting tomato leaf diseases using Convolutional Neural Networks (CNNs). Leveraging the power of deep learning, our approach significantly improves the accuracy and efficiency of disease identification compared to conventional techniques. We developed a CNN-based model that was trained and validated using a comprehensive dataset of tomato leaf images, encompassing various disease classes and healthy samples. The model architecture was meticulously designed to optimize feature extraction and classification performance. Extensive data augmentation techniques were employed to enhance the robustness and generalization capability of the model. Our enhanced classification system achieved remarkable accuracy, outperforming existing models in the literature. The results demonstrate the model's ability to effectively differentiate between multiple disease types and healthy leaves, even under challenging conditions such as varying lighting and background noise. This advancement holds great potential for integration into automated agricultural systems, providing farmers with a reliable tool for early disease detection and management.The implementation of this CNN-based improved classification system can lead to significant advancements in precision agriculture, minimizing crop losses and promoting sustainable farming practices. Future work will focus on extending this approach to other crops and refining the system for real-time field applications.
Sharma et al. (Wed,) studied this question.