Advanced Leaf Disease Detection: Integrating YOLOv9 with Transfer Learning for Precision Agriculture

Leaf diseases pose a significant challenge to agriculture, threatening crop health and yield. Effective detection and management of these diseases are critical for sustainable farming. This study introduces a novel method for detecting leaf diseases in agricultural images by leveraging the YOLOv9 model and transfer learning. By integrating YOLOv9 with various deep-learning libraries, our approach achieves a classification accuracy of 98%. Building on this success, we developed a mobile application that provides real-time disease detection using the trained model. A key strength of this method lies in the curated dataset, annotated with disease labels and bounding boxes. This dataset encompasses diverse crops and environmental conditions, ensuring the robustness and versatility of the model. Extensive experiments demonstrate that our approach outperforms conventional methods in both accuracy and efficiency. The resulting mobile application offers farmers and agricultural stakeholders a user-friendly tool for proactive disease management. It enables real-time identification of leaf diseases via a live camera feed, facilitating timely interventions and crop protection. By combining high accuracy with real- time detection, this method can significantly enhance crop productivity and contribute to sustainable agricultural practices.