Potato Leaf Disease Detection Method Based on the YOLO Model

Global potato production is at risk because of potato leaf diseases, which cause huge economic losses. To ensure crop productivity and disease management, their efficient and accurate localization is of utmost importance. The YOLOv7 deep learning model is presented in this paper as a means of disease detection and classification in potato leaves. The suggested approach uses YOLOv7's superior detection accuracy to successfully identify and categorize potato leaf diseases. To train the model, we used a wide variety of images showing both healthy and diseased potato leaves. Verified by the test results, the suggested methodology successfully identified and classified diseases affecting potato foliage with a 98.1% accuracy rate. Through early disease detection and prompt control measure implementation, this method holds great promise for enhancing the yield and quality of potato crops in precision agriculture systems. The proposed framework shows great promise for practical implementation, as the experimental results confirm that it offers enhanced accuracy in detecting and predicting potato crop diseases.