BEMD-Based Color–Texture Feature Fusion with Image Sharpening for Multiclass Huanglongbing Severity Classification
DOI:
https://doi.org/10.63158/journalisi.v8i5.1867Keywords:
Huanglongbing;, citrus greening, BEMD, feature fusion, multiclass classification, citrus leaf image analysisAbstract
Huanglongbing (HLB), or citrus greening disease, is one of the most destructive citrus diseases worldwide. Its symptoms often resemble nutrient deficiencies, making severity assessment difficult and subjective. This study proposes a color-texture feature fusion method to classify citrus leaf images into four HLB severity classes: healthy, mild, moderate, and severe. A dataset of 1,000 citrus leaf images from Sumanto et al. (2023), comprising 250 images per class, was used. HLB infection was validated using PCR/qPCR analysis, while severity annotations followed the original labeling protocol. Images were sharpened using a standard deviation of 0.1 and decomposed using Bidimensional Empirical Mode Decomposition (BEMD) into IMF1, IMF2, IMF3, and residue components to capture multiscale texture information. Color and texture features were fused and classified using Support Vector Machine (SVM), k-Nearest Neighbor (KNN), Random Forest (RF), and Neural Network (NN). Performance was evaluated using stratified k-fold cross-validation with out-of-fold predictions. BEMD with Color Fusion achieved the best SVM performance, with accuracy, precision, recall, and F1-score of 0.93 and computation time of 1.24 seconds. It outperformed Basic BEMD and BEMD Fusion Baseline, with accuracies of 0.77 and 0.89. These results demonstrate improved multiclass HLB severity classification, although independent field validation is required before practical deployment.
Downloads
References
[1] Sumanto, A. Buono, K. Priandana, B. P. Silalahi, and E. S. Hendrastuti, “Texture Analysis of Citrus Leaf Images Using BEMD for Huanglongbing Disease Diagnosis,” J. Online Inform., vol. 8, no. 1, pp. 115–121, 2023, doi: 10.15575/join.v8i1.1075.
[2] H. Wang, T. Cai, G. Xue, R. Jiang, J. Huang, and W. Yin, “Selecting Citrus Disease and Pest Features Based on a Flexible Elimination-Based Particle Swarm Optimization Algorithm,” Int. J. Cogn. Informatics Nat. Intell., vol. 20, no. 1, pp. 1–17, 2026, doi: 10.4018/ijcini.410773.
[3] W. Gómez-Flores, J. J. Garza-Saldaña, and S. E. Varela-Fuentes, “CitrusUAT: A dataset of orange Citrus sinensis leaves for abnormality detection using image analysis techniques,” Data Br., vol. 52, 2024, doi: 10.1016/j.dib.2023.109908.
[4] Q. Xu et al., “Identification of multiple symptoms of huanglongbing by electronic nose based on the variability of volatile organic compounds,” Ann. Appl. Biol., vol. 183, no. 2, pp. 181–195, 2023, doi: 10.1111/aab.12845.
[5] R. A. Purnama, D. Riana, M. Wahyudi, and S. Sumanto, “Comparison of SVM and KNN for BEMD-Based Texture Analysis in Huanglongbing Disease Severity Classification,” Beyond Technol. Summit Informatics Int. Conf. BTS-I2C 2025, pp. 42–47, 2025, doi: 10.1109/BTS-I2C67944.2025.11399362.
[6] N. Ye et al., “Early detection of Citrus Huanglongbing by UAV remote sensing based on MGA-UNet,” Front. Plant Sci., vol. 16, 2025, doi: 10.3389/fpls.2025.1503645.
[7] J. Menezes, R. Dharmalingam, and P. Shivakumara, “HLB Disease Detection in Omani Lime Trees Using Hyperspectral Imaging Based Techniques,” Commun. Comput. Inf. Sci., vol. 2027 CCIS, pp. 67–81, 2024, doi: 10.1007/978-3-031-53085-2_7.
[8] H. B. Barbieri, L. S. Fernandes, J. G. de M. Pontes, A. K. Pereira, and T. P. Fill, “An overview of the most threating diseases that affect worldwide citriculture: Main features, diagnose, and current control strategies,” Front. Nat. Prod., vol. 2, 2023, doi: 10.3389/fntpr.2023.1045364.
[9] A. N. Mughal et al., “Field Methods for Rapid and Noninvasive Diagnosis of Huanglongbing Through Symptomatic Evaluation and Diagnostic Testing,” Plant Prot., vol. 7, no. 3, pp. 439–447, 2023, doi: 10.33804/pp.007.03.4796.
[10] M. Younas, Z. Zheng, M. Atiq, T. Wei, and Y. Li, “Insights into the Huanglongbing pandemic focusing on transmission biology, virulence factors and multifaceted management strategies,” Pest Manag. Sci., vol. 81, no. 10, pp. 6076–6094, 2025, doi: 10.1002/ps.70073.
[11] A. Neupane, F. Shahzad, C. Bernardini, A. Levy, and T. Vashisth, “Poor shoot and leaf growth in Huanglongbing-affected sweet orange is associated with increased investment in defenses,” Front. Plant Sci., vol. 14, 2023, doi: 10.3389/fpls.2023.1305815.
[12] M. M. Dewdney, T. Vashisth, and L. M. Diepenbrock, “2023–2024 Florida Citrus Production Guide: Huanglongbing (Citrus Greening),” Edis, 2023, doi: 10.32473/edis-cg086-2023.
[13] M. E. Dwiastuti, A. Sugiyatno, N. F. Devy, and Hardiyanto, “The Effect of Interstock on the Development of Huanglongbing Disease and Vegetative Growth of Three Commercial Citrus Varieties in Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 1172, no. 1, 2023, doi: 10.1088/1755-1315/1172/1/012034.
[14] H. A. Zain, S. P. Wastutiningsih, and S. Subejo, “Comparing Farmers Capacity in Dealing with Huanglongbing Disease (A Case Study in Jember Regency),” Agro Ekon., vol. 36, no. 1, p. 38, 2025, doi: 10.22146/ae.98681.
[15] Q. Xu, J. Cai, L. Ma, B. Tan, Z. Li, and L. Sun, “Custom-Developed Reflection–Transmission Integrated Vision System for Rapid Detection of Huanglongbing Based on the Features of Blotchy Mottled Texture and Starch Accumulation in Leaves,” Plants, vol. 12, no. 3, 2023, doi: 10.3390/plants12030616.
[16] Q. Frederick et al., “Supervised Hyperspectral Band Selection Using Texture Features for Classification of Citrus Leaf Diseases with YOLOv8 †,” Sensors, vol. 25, no. 4, 2025, doi: 10.3390/s25041034.
[17] J. G. de Moraes Pontes et al., “Mass spectrometry imaging as a potential technique for diagnostic of Huanglongbing disease using fast and simple sample preparation,” Sci. Rep., vol. 10, no. 1, 2020, doi: 10.1038/s41598-020-70385-4.
[18] K. Yan et al., “Three-dimensional fluorescence spectral characteristic of flavonoids for citrus Huanglongbing disease early detection,” Microchem. J., vol. 208, 2025, doi: 10.1016/j.microc.2024.112263.
[19] K. Yan et al., “Citrus huanglongbing detection: A hyperspectral data-driven model integrating feature band selection with machine learning algorithms,” Crop Prot., vol. 188, 2025, doi: 10.1016/j.cropro.2024.107008.
[20] S. Sumanto, R. Adi Purnama, Hendra Supendar, Ade Christian, T. V. Rizki irdian, and Kaisar Ages Querio, “Real-Time Detection of Huanglongbing (HLB) Disease in Citrus Leaves Using Enhanced YOLO V8 Algorithm,” Komputasi J. Ilm. Ilmu Komput. dan Mat., vol. 23, no. 1, pp. 1–7, 2026, doi: 10.33751/komputasi.v23i1.82.
[21] Z. Zheng, Y. Zhang, and L. Sun, “Improved YOLOv8-Based Algorithm for Citrus Leaf Disease Detection,” IEEE Access, vol. 13, no. May, pp. 105888–105900, 2025, doi: 10.1109/ACCESS.2025.3579074.
[22] E. Aswini and C. Vijayakumaran, “Auto Detector for Huanglongbing Citrus Greening Disease using YOLOV7,” 2023 World Conf. Commun. Comput. WCONF 2023, pp. 1–6, 2023, doi: 10.1109/WCONF58270.2023.10235043.
[23] B. N. Garza, V. Ancona, J. Enciso, H. L. Perotto-Baldivieso, M. Kunta, and C. Simpson, “Quantifying citrus tree health using true color UAV images,” Remote Sens., vol. 12, no. 1, 2020, doi: 10.3390/rs12010170.
[24] F. Dai et al., “Detection Method of Citrus Psyllids With Field High-Definition Camera Based on Improved Cascade Region-Based Convolution Neural Networks,” Front. Plant Sci., vol. 12, 2022, doi: 10.3389/fpls.2021.816272.
[25] L. Yang, Q. Dong, D. Lin, and X. Lü, “TongueNet: a multi-modal fusion and multi-label classification model for traditional Chinese Medicine tongue diagnosis,” Front. Physiol., vol. 16, 2025, doi: 10.3389/fphys.2025.1527751.
[26] S. Sharma Chaudhary Sarwan Kumar Himachal Pradesh Krishi Vishvavidyalaya, S. Bharadwaj, A. Kumar Das, S. Sharma, S. Gujarathi, and S. Mena, “Raman Spectroscopy for the Early Detection of Huanglongbing and Citrus Canker in Plants: A Review,” pp. 1–29, 2023, doi: 10.48550/arXiv.2509.02255.
[27] W. Xie, F. Feng, and H. Zhang, “A Detection Algorithm for Citrus Huanglongbing Disease Based on an Improved YOLOv8n,” Sensors, vol. 24, no. 14, 2024, doi: 10.3390/s24144448.
[28] L. Yang, T. Zhang, F. Lu, and M. Zhang, “Multifractal Image Texture Analysis Combined with 2D Empirical Mode Decomposition,” 2023 4th Int. Semin. Artif. Intell. Netw. Inf. Technol. AINIT 2023, pp. 764–770, 2023, doi: 10.1109/AINIT59027.2023.10212874.
[29] X. Sun et al., “Research on Face Image Denoising Method Based on Adaptive Bidimensional Empirical Mode Decomposition and Stochastic Resonance Method,” Proc. - 2023 6th Int. Conf. Electron. Electr. Eng. Technol. EEET 2023, pp. 18–24, 2023, doi: 10.1109/EEET61723.2023.00037.
[30] C. He et al., “Combining multicolor fluorescence imaging with multispectral reflectance imaging for rapid citrus Huanglongbing detection based on lightweight convolutional neural network using a handheld device,” Comput. Electron. Agric., vol. 194, 2022, doi: 10.1016/j.compag.2022.106808.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Author's Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
