Classification and Detection for Oryza Folia (Palay Leaf) Disease an Analysis with YOLOv5

This study demonstrated the effectiveness of the YOLOv5 object detection model in automating the classification and detection of six common diseases affecting the Palay (rice) leaves using advanced machine learning techniques, the model was able to reliably diagnose diseases from leaf images, addressing an important problem in agricultural production. The image classification model training progresses through 30 epochs and shows significant improvement in its performance on the training model as it reaches 0.989 or 98% accuracy at the end of the training. The classification result for bacterial blight that is predominant in the subject oryza folia was successfully classified by the model. This can also be compared visually to accurately having 50% bacterial blight, also based on the model's performance as the accuracy yield starting at 36.1% to 98% in image classification. The system model allows for early intervention and mitigation strategies, reducing potential yield losses due to crop diseases.