DEEP LEARNING BASED AUTOMATED DETECTION AND CLASSIFICATION OF TOMATO LEAF DISEASES

Abstract

Tomato is one of the most widely cultivated and economically important crops worldwide, but its productivity is significantly affected by various leaf diseases. Early and accurate detection of these diseases is crucial to minimize crop loss and improve agricultural yield. This project presents a deep learning-based approach for the automated detection and classification of tomato leaf diseases using image processing techniques. The proposed system utilizes convolutional neural networks (CNNs) to analyze leaf images and identify different disease categories such as bacterial spot, early blight, late blight, leaf mold, and healthy leaves. A labeled dataset of tomato leaf images is used to train the model, enabling it to learn complex patterns and features associated with each disease. The system includes preprocessing steps such as image resizing, normalization, and augmentation to enhance model performance and generalization. The trained model is capable of accurately classifying tomato leaf conditions with high precision and minimal human intervention. Experimental results demonstrate that the proposed deep learning model achieves significant accuracy and outperforms traditional machine learning approaches. This automated system can assist farmers and agricultural experts in early diagnosis, reducing dependency on manual inspection and enabling timely disease management. Overall, the proposed solution contributes to smart agriculture by integrating artificial intelligence for efficient crop health monitoring and sustainable farming practices.