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

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. Traditional approaches for disease detection rely on expert knowledge and time-consuming laboratory tests, which hinder rapid and effective disease management. Therefore, this study explores 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. 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. The results of the classification experiments demonstrate the effectiveness of the proposed method. The achieved classification accuracies, ranging from 61% to 77% for different numbers of classes, the results show 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, essential for effective disease management and maintaining agricultural productivity.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. HLB, caused by gram-negative proteobacteria strains, severely impacts citrus orchards globally, resulting in economic losses. Early detection and classification of HLB-infected plants are crucial for effective disease management. Traditional approaches rely on expert knowledge and time-consuming laboratory tests, hindering rapid detection. This study explores an alternative method using the BEMD algorithm for texture feature extraction and SVM classification to improve HLB diagnosis. The BEMD algorithm decomposes citrus leaf images into Intrinsic Mode Functions (IMFs) and a residue component. Classification experiments were conducted using SVM on IMF 1, IMF 2, and residue features. The residue component provided the most outstanding level of classification accuracy, reaching 77% for two classes, 72% for three types, and 61% for four classes. In two categories, IMF 1 performed at a 72% accuracy rate, and in four other areas, it performed at a 51% accuracy rate, making it competitive. IMF 2 demonstrated lower accuracy, ranging from 43% for three classes to 57% for two categories. The findings highlight the significance of the image residue component, outperforming IMF features in HLB classification accuracy. The BEMD algorithm coupled with SVM classification presents a promising approach for accurate HLB diagnosis, surpassing the performance of previous studies using GLCM-SVM techniques. &nbsp