Automated detection and classification of rice leaf diseases using YOLOv8: a deep learning approach for enhanced crop monitoring

Rice is a staple food crop, and its cultivation is crucial for ensuring global food security. However, rice plant diseases pose a significant threat to crop yields, emphasizing the need for effective disease detection and management strategies. With the rapid advancements in machine learning and computer vision techniques, there has been a growing interest in leveraging these technologies for automated disease detection in agriculture. Common diseases affecting rice plants, such as blast, brown spot, and bacterial blight, can cause substantial yield losses if left undetected and untreated. Early and accurate detection of these diseases is essential for implementing timely and targeted control measures, ultimately minimizing crop damage and maximizing yields. In this research, we propose the use of deep learning techniques, specifically the YOLOv8 (You Only Look Once) object detection algorithm, for the automated detection and classification of rice leaf diseases. The methodology involves training the YOLOv8 model on a carefully curated dataset comprising 2,304 annotated images of rice leaves, capturing diverse disease manifestations as well as healthy samples. The dataset was labeled, ensuring accurate ground truth for model training and evaluation. Experimental results demonstrate that the proposed deep learning model achieved an impressive accuracy of 68.2% in correctly classifying healthy rice leaf samples. This promising outcome highlights the potential of the YOLOv8 algorithm for practical applications in rice leaf disease detection and monitoring.