Multi-class Plant Leaf Disease Classification on Real-Time Images Using YOLO V7

Agriculture faces a significant challenge with leaf disease, which can lead to substantial decreases in crop productivity. Deep learning techniques, particularly the YOLO (You Only Look Once) algorithm, have gained popularity for effectively detecting and categorizing plants diseases in real time. This research presents a leaf disease detection and classification system utilizing YOLO v7, which benefits from a diverse and current dataset obtained from real-time field images. This dataset allows for precise training and evaluation of plant disease detection models in real-world scenarios, offering valuable insights into the effectiveness of the YOLO v7 algorithm. By training on a large collection of images of plants, the system achieves high accuracy (96%) in identifying various leaf diseases such as leaf spot, rust, and early blight. Utilizing this technology, farmers will be able to take preventative measures and decrease crop losses through early disease diagnosis and intervention due to the quick and effective object identification capabilities of YOLO v7.