Automated Detection and Classification of Tomato Leaf Diseases Using Convolutional Neural Networks

Abstract

Tomato (Solanum lycopersicum) is one of the most important vegetable crops globally, but its production is significantly affected by various foliar diseases such as Early Blight, Late Blight, and Septoria Leaf Spot. Timely and accurate detection of these diseases is critical for effective crop management and yield preservation. Traditional diagnostic methods rely heavily on manual inspection, which is time-consuming, error-prone, and impractical for large-scale monitoring. In this study, we present a deep learning-based approach utilizing Convolutional Neural Networks (CNNs) to automatically detect and classify multiple tomato leaf diseases from images. We employed the PlantVillage dataset, which contains over 10 classes of tomato leaf images, including healthy and diseased samples. Data preprocessing and augmentation techniques were applied to enhance model generalization and robustness under real-world conditions. The proposed CNN model achieved a classification accuracy of 97.30% on the test set, outperforming traditional machine learning models and demonstrating resilience across varied image conditions. Furthermore, we evaluated the model using precision, recall, F1-score, and confusion matrices, highlighting its ability to distinguish between visually similar diseases. Our approach provides a scalable, low-cost, and efficient solution for early disease detection, with potential for deployment in mobile applications and precision agriculture systems.