Automated Detection and Classification of Vegetable Leaf Disease using Machine Learning Techniques

Abstract

Plant leaf diseases are a major concern in agriculture because they reduce crop quality, lower productivity, and cause economic losses to farmers. Early detection of these diseases is important for protecting plants and improving overall crop management. However, manual identification through visual inspection is often slow and may produce inaccurate results, especially in the early stages of infection. To overcome this problem, this work proposes an automated leaf disease detection system using image processing and deep learning techniques. OpenCV is used for preprocessing the leaf images through resizing, noise removal, color normalization, and enhancement, while a Convolutional Neural Network (CNN) is trained to extract important features and classify the images into different disease categories. The dataset consists of healthy and diseased leaf images collected from publicly available sources and is divided into training, validation, and testing sets for effective model development. For practical implementation, the trained model is integrated into a Flask-based web application that allows users to upload leaf images and obtain predictions easily. The performance of the system is evaluated using accuracy, precision, recall, and F1-score, and the model achieved an accuracy of 95%. The results show that the proposed system can detect leaf diseases effectively and efficiently, making it a useful and cost-effective solution for supporting farmers and agricultural experts in early disease diagnosis.