Abstract
Fungi disease affects walnut trees worldwide because it damages the canopies of the trees and can easily spread to neighboring trees, resulting in low quality and less yield. The fungal disease can be treated relatively easily, and the main goal is preventing its spread by automatic early-detection systems. Recently, machine learning techniques have achieved promising results in many applications in the agricultural field, including plant disease detection. In this paper, an automatic machine learning-based detection method for identifying walnut diseases is proposed. The proposed method first resizes a leaf's input image and pre-processes it using intensity adjustment and histogram equalization. After that, the detected infected area of the leaf is segmented using the Otsu thresholding algorithm. The proposed method extracts color and shape features from the leaf's segmented area using the gray level co-occurrence matrix (GLCM) and color moments. Finally, the extracted features are provided to the back-propagation neural network (BPNN) classifier to detect and classify walnut leaf diseases. Experimental results demonstrate that the proposed method's detection accuracy is 95.3%, which is significantly higher than those of the state-of-the-art techniques. The proposed method assists farmers in detecting diseases affecting walnut trees and thus enables them to generate more revenue by improving the productivity and quality of their walnuts.