Method for Detecting Potato Leaf Disease Using the YOLOv8 Model

Potato leaf diseases pose a significant risk to the global potato sector, with significant financial implications. It is vital to precisely and efficiently target agricultural productivity and disease management. This work presents the YOLOv8 deep learning model as a method for recognizing and categorizing diseases in potato leaves. The proposed methodology effectively uses YOLOv8’s high detection precision to detect and classify illnesses affecting potato leaves. Many images were used to help the model’s training process, including healthy and sick potato leaves. The test results revealed that the proposed methodology correctly discovered and classified leaf disease in potato plants with a 98.6 % accuracy. This technique has the potential to significantly improve the quality and productivity of potato crops in precision agriculture systems by detecting diseases early on and adopting control measures. The experimental results support the proposed framework’s operational capability, which has great promise for reliably detecting and predicting potato crop illnesses.