Development of a Localized Tomato Leaf Disease Detection using YoloV9 Model via RoboFlow 3.0

This study aims to localize seven diseased tomato leaf situations with the help of annotated image data in the YOLOv9 model to improve enhanced object detection accuracy and enhanced timely detections. This cuts short the whole process through Roboflow 3—an end-to-end platform of computer vision that encompasses state-of-the-art tools related to data preparation training, and model development, hence drastically reducing dependency on work-intensive code and accelerating growth. The model demonstrated its efficiency in attaining average precision at 96%, mAP at 96.4%, average precision rate at 96.7%, and recall rate at 94.8%. The system will benefit the agricultural sectors, particularly farmers and agronomists, to facilitate early and accurate detection of tomato leaf diseases, thus improving crop management and yield.