LEAF DISEASE DETECTION USING MATLAB AND DEEP LEARNING

Electronics and Communication Engineering

Agriculture is one of the most vital sectors for economic development, and plant diseases pose a significant threat to crop productivity. Early and accurate detection of these diseases is crucial for preventing yield loss and ensuring food security. Traditional methods of disease detection rely on manual inspection by experts, which is time-consuming, inconsistent, and often impractical for large-scale farming. In this study, we propose an automated leaf disease detection system using image processing and deep learning techniques in MATLAB. The system processes leaf images through preprocessing steps such as resizing, noise reduction, and contrast enhancement to improve feature extraction. A Convolutional Neural Network (CNN) based on the pre-trained VGG16 model is employed to classify leaves as either healthy or diseased. The diseased leaves are further categorized into specific diseases such as Powdery Mildew, Rust Disease, Bacterial Blight, and Leaf Spot Disease. The proposed approach eliminates the need for manual feature extraction, allowing the model to learn disease-specific patterns directly from images. The model is trained and tested on a diverse dataset, achieving an accuracy of over 91%. The results demonstrate that this deep learning-based system provides a fast, accurate, and reliable solution for farmers and agricultural researchers, enabling early disease detection and timely intervention. Future improvements may include real-time monitoring, integration with IoT-based systems, and the development of a mobile application for broader accessibility.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.