Integrating YOLOv and GPT-4 for Automated Plant Disease Detection and Management

Abstract

This paper presents an innovative approach to agricultural disease management by integrating YOLOv9-C, a state-of-the-art object detection model, with GPT-4, an advanced language model. We trained YOLOv9-C on a PlantDoc dataset comprising images of various plant diseases. Upon detecting a disease, the system interacts with GPT-4o, which references a preloaded PDF containing detailed information about each disease, to suggest appropriate actions. This fusion of computer vision and large language models aims to assist farmers and agricultural professionals in promptly diagnosing and managing plant diseases, thereby enhancing crop health and productivity.