An effective method for detecting tomato leaf disease using distributed neural networks

Abstract

Tomato, a prominent agricultural commodity, hold substantial economic significance and boast high productivity. The crop's yield and quality are profoundly influenced by an array of plant diseases, underscoring the imperative of early detection. Hence, this study addresses the critical issue of identifying and classifying various diseases that hinder tomato plants. Employing deep learning techniques, particularly through the integration of state-of-the-art machine learning models, especially CNN (Convolutional Neural Network), and effective data augmentation techniques, we aim to achieve an optimal means of classifying tomato leaf diseases. The proposed methodology leverages automatic feature extraction to classify input images, utilizing neural network models to assign them to the relevant disease categories. This research contributes to advancing the field of automated plant disease detection and establishes a foundation for efficient, resource-conscious identification of tomato leaf diseases.