Advanced Image Processing and Feature Extraction Approaches For Detecting Wheat Yellow Rust Disease

Wheat, the most significant crop on earth, is necessary for food security and sustainable agriculture. However, damage to wheat harvests, including wheat disease, can result in food problems. Technology-based solutions can help detect crop health concerns more effectively than manual labor alone, which will stop the spread of illnesses. Since different situations can affect crops differently and create varying degrees of harm, the research work and study must focus on wheat rust disorders such as wheat leaf rust, stem rust, and yellow rust. The study uses image analysis of wheat fields to try and characterize the many signs and symptoms of infected crops. Image preprocessing techniques such as region-based, HSV, L*a*b, single and dual bands, etc. were created by it. The study uses the yellow rust image dataset to extract LBP and GLCM texture properties. The study employed various techniques to enhance the quality of the images and retrieved dependable elements for an effective illness classification. These methods define RGB, HSV, and L*a*b, among other color spaces. The analysis of the current method, such as the CNN-CGL CM HSV joint method that fused HSV and SVM, produced a 92.4% accuracy rate, which is more accurate than previous techniques.