Disease Detection In Grapes Using CNN

Abstract

In this research, Grape diseases significantly impact on production and fruit quality, leading to economical loss in agriculture sector. Traditional methods of disease detection is manually inspection which is time consuming and labor intensive with human errors to address this challenges. This study examine the application of Convolutional Neural Network (CNN) for automatic grape disease detection. CNN shows outstanding performance in image classification task, making them well suited for analyzing grape leaf images to identify diseases such as Black rot, Esca (Black Measles), and Leaf blight. This model trained on dataset comprising disease leaf and healthy grape leaf images, employing deep learning techniques for feature extraction and classification. Predicted result indicate that the CNN based approach achieves high accuracy in disease detection, offering a reliable, automated, and scalable solution for early detection. These research precision agriculture by facilitating immediate help and reduce chemical treatments, ultimately promote sustainable agriculture practices.