Development of a Model for Detection and Grading of Stem Rust in Wheat Using Deep Learning

Stem rust is a highly prevalent and damaging fungal disease that affects wheat crops worldwide. It is caused by the Puccinia graminis f. sp. tritici fungus, and can significantly reduce wheat production and quality, by 10% to 50%. In severe cases, it causes up to a 90% decrease in grain yield if left uncontrolled. Manual diagnosis by pathologists and experts which use visual inspection is usually costly, time-consuming, and prone to errors. Moreover, the scarcity of pathologists in rural areas poses a challenge in detecting and grading wheat stem rust. To address these issues, this study presents a system for automated detection and classification of wheat stem rust based on the modified Cobbs scale (CIMMYT) guidelines. The system employs image pre-processing techniques such as adaptive thresholding for segmentation and the Gabor filter for feature extraction which enhances textural features to identify key disease characteristics. For disease classification, a deep learning approach was utilized which employs a 12-way Softmax to assign specific classes: Resistant (tR), Moderately resistant (MR), and Susceptible (S). The proposed model is trained and tested using an image dataset collected in collaboration with pathologists from Haramaya University. The proposed model achieves a training accuracy of 92.02% and a testing accuracy of 92.01% in grading wheat stem rust, outperforming state-of-the-art models such as CNN. The study's main achievements are achieved in the areas of real-time monitoring, and grading precision. Real-time monitoring provides timely updates on disease presence and severity, enabling proactive management and minimizing crop losses. Grading precision offers a quantitative assessment of disease damage, facilitating targeted treatment strategies and resource allocation.