Automated Vision-Based System for Real-Time Detection and Classification of Rice Diseases using YOLO-NAS

This proposed work presents an innovative approach to agricultural disease management through the integration of the YOLO-NAS (You Only Look Once Neural Architecture Search) algorithm for real-time rice leaf disease detection. Focusing on five major diseases—brown spot, bacterial leaf blight, hispa, dead heart, and bacterial panicle blight—the system leverages deep learning and computer vision to offer rapid and accurate disease identification. By providing early detection insights, the tool aids farmers in making informed decisions, enhancing precision agriculture, and fostering sustainable farming practices. The user-friendly interface ensures widespread adoption, empowering farmers to monitor disease progression and take timely action. This approach mitigates crop losses, improves yield, and demonstrates the transformative potential of AI in agriculture and the result F1_Score, Precision, Accuracy and Map/ap scores as 76%,90%,67% respectively. The study highlights the importance of technological innovation in addressing critical agricultural challenges and advancing global food security.