ResNet Fusion with GAN Augmentation: A Dual-Powered Model for Grape Leaf Diagnostics

This research focuses on an AI-based solution for automated detection of grape plant leaf diseases, aiming to address diseases like black rot, esca measles, and leaf blight. Using Generative Adversarial Networks (GANs) for data augmentation and Convolutional Neural Networks (CNNs) for accurate classification, the system ensures robust performance under diverse conditions. The methodology includes pre-processing, feature extraction with ResNet models, and real-time optimization, which makes it suitable for resource-constrained environments. Results show significant accuracy improvements, promoting sustainable farming practices and reducing crop losses. This study contributes to advancing precision agriculture through innovative machine learning solutions.