RustBuster: Advanced Wheat Rust Recognition with BlendMask Model

Wheat rust, a catastrophic fungal scourge that can lead to the massive decline of wheat crops world over is truly a global concern that if not checked on time, can lead to widespread devastation of agricultural productivity and food security. The standard rust disease diagnostic methods are reported to have several disadvantages such as precision and effectiveness, inaccuracy, and lack of timeliness, which might cause concurrent widespread destruction of the harvest. Techniques like Deep Learning (DL), that have recently raised as very probable solutions, have been developed for solving this problem. This work showcases the monopoly of DL technologies in the classifications of wheat diseases and reviews their complex impact on wheats as well as formerly published works which celebrate the progress achieved in CNN and further improved selections such as GhostNetV2. By using the up-to-date deep learning techniques and a massive 1250 pixels of wheat photos in high resolution, the proposed method incorporated both. Architecture of the BlendMask model is a main focus in reasoning behind the Blender module and the use ofFCOS detection. Evaluation metrics that take into accountboth precisions, recall and F1-score-being the performance evaluation metrics of our BlendMask model indicate the effectiveness of our model in this area. The data’s evaluation shows that the precession is 99.45%, therecall is 97.32% and the F1-score is 92.89% which outperform existing methods. The comparative study, operating in the current mode, clearly bring out the fact that the BlendMask model is more precise and effective over the two approaches. The future research endeavors are aimed at the expansion and refinement of the model for different crop climate zones, creating user-friendly applications and introduction of diversified disease recognition approaches. Providing quick technologies to farmers to help early disease detection allows sustainable farming techniques in relation to the crops to develop and the emergence of new risks to be tackled.