A Deep Learning Approach For Plant Disease Detection Using YOLOV5

Abstract

Plant diseases pose a significant threat to agricultural productivity and food security worldwide. This paper presents a novel approach utilizing the YOLOv5 object detection algorithm for plant disease detection, leveraging an annotated dataset obtained from Kaggle. The annotated dataset used in this study comprises a diverse collection of high-resolution images of plants affected by various diseases. The dataset was manually labeled with bounding boxes and corresponding class labels, providing detailed information about the location and type of disease present in each image.YOLOV5 is used for training and detecting plant diseases. The resulting trained YOLOV5 model demonstrated superior performance in detecting and localizing plant diseases within images, achieving good performance. The proposed approach offers several advantages over traditional methods of plant disease detection.it suitable for large-scale applications. To ensure the model's accuracy, a rigorous training process was conducted, involving minimal level of data augmentation techniques. This research contributes to the ongoing efforts in precision agriculture, aiding  farmers and researchers in timely disease management, crop protection, and improved agricultural practices.