<![CDATA[One of the most significant staple crops in the world is rice, and one of the main causes of the drop in agricultural yields is illnesses that affect rice leaves. To avoid large agricultural losses, early diagnosis of these illnesses is essential. The goal of this project is to use YOLOv12, the most recent deep learning-based object detection architecture, to create a rice leaf disease detection system. The model was trained using a dataset of 4,744 photos of rice leaves that included three disease classes: Leaf Blast, Brown Spot, and Bacterial Leaf Blight. Methods to boost variability and enhance detection performance, image preprocessing with data augmentation was used. Standard object detection criteria, such as mean Average Precision (mAP), precision, and recall, were used to assess the model. The YOLOv12 model was highly effective in detecting rice leaf illnesses. According to the experimental data, it achieved a mAP of 97%, a precision of 96%, and a recall of 96.5%. The use of YOLOv12's greater efficiency and quality in detecting small objects—which is essential for identifying illness symptoms on leaves—is what makes this study successful. These results lay the groundwork for upcoming precision agricultural real-time monitoring applications.]]>
Copyrights © 2026
