A Novel Approach to Detect Leaf Diseases Using GAN, YOLO and DCNN

The accurate detection of leaf diseases is a pivotal challenge in agriculture, directly impacting crop health and productivity. Existing approaches often struggle with limited annotated datasets, high inter-class variability, and computational inefficiencies. This research introduces a novel methodology leveraging Generative Adversarial Networks (GAN), You Only Look Once (YOLO), and Deep Convolutional Neural Networks (DCNN) to address these gaps. GANs are employed for dataset augmentation, enhancing diversity and robustness, while YOLO enables real-time detection. DCNN provides detailed classification to ensure precise disease identification. The proposed framework builds upon prior research on machine learning-based disease detection by integrating advanced data augmentation and feature extraction techniques. Experimental evaluation demonstrates that this approach outperforms conventional models in terms of F1 score and accuracy, showcasing its potential for scalable and reliable deployment. This study bridges the gap between theoretical advancements and practical agricultural applications, contributing to sustainable farming practices.