Early Accurate Identification of Grape leaf Disease Detection using CNN based VGG-19 model

As the world’s population continues to grow, it is becoming necessary to increase the overall crop production, in order to guarantee food for all. Prior to taking action, it’s critical to properly diagnose and extensively monitor crop illnesses. This research introduces an innovative application of the VGG-19 CNN model for grape leaf disease detection. By harnessing the power of deep convolutional layers, the study addresses the challenges of accurately identifying and classifying various diseases affecting grape leaves, ultimately paving the way for more effective disease management in vineyards. Using the VGG-19 architecture, the research presents a unique application of Convolutional Neural Networks for automated grape leaf disease detection and classification in viticulture. A large dataset with a range of grape leaf conditions is selected and used to train and optimize the VGG-19 model. The network is used to precisely identify and classify several grape leaf diseases by taking advantage of its capacity to recognize complex patterns in high-resolution leaf images. The accuracy attained by VGG 19 architecture is 98% and the strict assessment criteria confirm the effectiveness of the suggested approach, demonstrating better results than the current models.