Texture Analysis of Citrus Leaf Images Using BEMD for Huanglongbing Disease Diagnosis

Abstract

Plant diseases significantly threaten agricultural productivity, necessitating accurate identification and classification of plant lesions for improved crop quality. Citrus plants, belonging to the Rutaceae family, are highly susceptible to diseases such as citrus canker, black spot, and the devastating Huanglongbing (HLB) disease. Conventional disease detection methods rely on expert knowledge and time-consuming laboratory tests, which hinder rapid and effective disease management. This study aims to explore an alternative method that combines the Bidimensional Empirical Mode Decomposition (BEMD) algorithm for texture feature extraction and Support Vector Machine (SVM) classification to improve HLB diagnosis in citrus plants. The method used in this research involves the BEMD algorithm decomposes citrus leaf images into Intrinsic Mode Functions (IMFs) and a residue component. Classification experiments were conducted using SVM on the IMFs and residue features. This research found that the achieved classification accuracies, ranging from 61% to 77% for varying numbers of classes, indicate that the residue component achieved the highest classification accuracy, outperforming the IMF features. The combination of the BEMD algorithm and SVM classification presents a promising approach for accurate HLB diagnosis, surpassing the performance of previous studies that utilized GLCM-SVM techniques. This research contributes to developing efficient and reliable methods for early detection and classification of HLB-infected plants, which are essential for effective disease management and the preservation of agricultural productivity.