Determination of the severity level of yellow rust disease in wheat by using convolutional neural networks

Abstract

Yellow rust disease caused by Puccinia striiformis f. sp. tritici, a pathogen in wheat, results in significant losses in wheat production worldwide due to its high destructive property. On the other side, yellow rust can be taken under control by growing resistant cultivars, by the application of fungicides, and by the use of appropriate cultural practices. Thus, it is crucial to detect the disease at an early stage. The current study offers to use computerized models in determining the infection type of yellow rust disease in wheat. Herein, a deep convolutional neural networks-based model, named Yellow-Rust-Xception, was proposed. The model inputs the wheat leaf image and classifies it as no disease, resistant, moderately resistant, moderately susceptible, or susceptible according to the rust severity, i.e. percentage. The convolutional neural networks, a state-of-art approach, have layered structures those inspired by the human brain and able to learn discriminative features from data automatically; thus networks performance match and even surpass humans in task-specific applications, a newly developed dataset containing yellow rust-infected wheat leaf images, was used to train, validate, and test Yellow-Rust-Xception, in result, the test accuracy was 91%. Thus, Yellow-Rust-Xception can be used in determining wheat yellow rust and its severity level.