A YOLO-Based Framework for Accurate Identification of Wheat Mosaic Virus Disease

The serious threat Wheat Streak Mosaic Virus (WSMV) poses to wheat production is brought to light in this study's discussion of the major issue of WSMV detection in Indian wheat crops. Crop quality is severely affected by WSMV, which can be transmitted by the Wheat Curl Mite (WCM). WSMV is an RNA virus that is monopartite in structure and belongs to the Tritimovirus genus. When wheat leaves are infected with WSMV, a unique yellow mosaic pattern and slow development are observed. The disease was first identified in Nebraska in 1922. WCMs contribute to the virus's spread over the disease cycle as they act as carriers. Our research employs Deep Learning Models (DL) and the YOLO (You Only Look Once) method to tackle this issue in a novel way. The use of YOLO requires enhancing the accuracy and efficiency of detection by recognizing complex WSMV patterns. With the use of this YOLO model, the research can get 97.56% precision for wheat mosaic virus recognition. It is possible to detect diseases earlier and create specific action plans for their management with the help of this integration of DL models. By using modern methods for precise and effective WSMV detection, this research offers an important stage in safeguarding wheat output.