Hybrid Handcrafted Feature Extraction Combined with an Assisted Region of Interest Protocol for Multi-Class Age-Related Macular Degeneration Classification
Received: 1 January 2026 | Revised: 6 February 2026 | Accepted: 13 February 2026 | Online: 20 February 2026
Corresponding author: Sri Hartati
Abstract
Age-related Macular Degeneration (AMD) is a major cause of vision impairment and may progress to blindness; thus, accurate differentiation between Dry and Wet AMD is essential for timely clinical decision-making. This study proposes a lightweight multi-class AMD classification framework from fundus images that combines an anatomically consistent Assisted Region of Interest (Assisted-ROI) protocol with a hybrid handcrafted representation. Four public datasets (ODIR, ADAM, FIVES, and RFMiD) were merged to construct a curated dataset of 597 images across three classes (Normal, Dry AMD, and Wet AMD). AMD cases were re-annotated into Dry and Wet subtypes by three ophthalmologists, while Normal labels were retained. The experiments used 5-fold cross-validation under three input scenarios: full-fundus (no ROI), Optic Disc (OD)-guided automatic ROI, and the proposed Assisted-ROI. The no-ROI baseline achieved 80.91% accuracy, the OD-guided ROI achieved 85.27%, and Assisted-ROI delivered the best performance with 90.63% accuracy. Feature ablation under identical controlled settings showed that early fusion of LBP-RIU, Haralick/GLCM texture features, and RGB color moments yielded the most discriminative representation (90.63% accuracy; 89.06% macro-F1), outperforming the best single descriptor (LBP-RIU: 83.09%). Overall, anatomically consistent ROI standardization and complementary handcrafted feature fusion improve robust multi-class AMD recognition on heterogeneous multi-source fundus data under reduced computational cost.
Keywords:
AMD classification, assisted ROI, handcrafted features fusion, LBP_RIU, GLCM, color moments, SVMDownloads
References
W. L. Wong et al., "Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis," The Lancet Global Health, vol. 2, no. 2, pp. e106–e116, Feb. 2014. DOI: https://doi.org/10.1016/S2214-109X(13)70145-1
A. R. Fernandes et al., "Exudative versus Nonexudative Age-Related Macular Degeneration: Physiopathology and Treatment Options," International Journal of Molecular Sciences, vol. 23, no. 5, Feb. 2022, Art. no. 2592. DOI: https://doi.org/10.3390/ijms23052592
U. Schmidt-Erfurth et al., "Guidelines for the management of neovascular age-related macular degeneration by the European Society of Retina Specialists (EURETINA)," British Journal of Ophthalmology, vol. 98, no. 9, pp. 1144–1167, Sept. 2014. DOI: https://doi.org/10.1136/bjophthalmol-2014-305702
H. P. N. Scholl et al., "Inter- and intra-observer variability in grading lesions of age-related maculopathy and macular degeneration," Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 241, no. 1, pp. 39–47, Jan. 2003. DOI: https://doi.org/10.1007/s00417-002-0602-8
S. T. Berkowitz, A. P. Finn, R. Parikh, A. E. Kuriyan, and S. Patel, "Ophthalmology Workforce Projections in the United States, 2020 to 2035," Ophthalmology, vol. 131, no. 2, pp. 133–139, Feb. 2024. DOI: https://doi.org/10.1016/j.ophtha.2023.09.018
M. Tounsi, E. Aram, A. T. Azar, A. Al-Khayyat, and I. K. Ibraheem, "A Comprehensive Review on Biomedical Image Classification using Deep Learning Models," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19538–19545, Feb. 2025. DOI: https://doi.org/10.48084/etasr.8728
F. Li, H. Chen, Z. Liu, X. Zhang, and Z. Wu, "Fully automated detection of retinal disorders by image-based deep learning," Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 257, no. 3, pp. 495–505, Mar. 2019. DOI: https://doi.org/10.1007/s00417-018-04224-8
P. M. Burlina, N. Joshi, M. Pekala, K. D. Pacheco, D. E. Freund, and N. M. Bressler, "Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks," JAMA Ophthalmology, vol. 135, no. 11, pp. 1170–1176, Nov. 2017. DOI: https://doi.org/10.1001/jamaophthalmol.2017.3782
S. Kadry, V. Rajinikanth, R. González Crespo, and E. Verdú, "Automated detection of age-related macular degeneration using a pre-trained deep-learning scheme," The Journal of Supercomputing, vol. 78, no. 5, pp. 7321–7340, Apr. 2022. DOI: https://doi.org/10.1007/s11227-021-04181-w
O. Mamyrbayev et al., "Hybrid Neural Architectures Combining Convolutional and Recurrent Networks for the Early Detection of Retinal Pathologies," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25150–25157, Aug. 2025. DOI: https://doi.org/10.48084/etasr.11521
A. García-Floriano, Á. Ferreira-Santiago, O. Camacho-Nieto, and C. Yáñez-Márquez, "A machine learning approach to medical image classification: Detecting age-related macular degeneration in fundus images," Computers & Electrical Engineering, vol. 75, pp. 218–229, May 2019. DOI: https://doi.org/10.1016/j.compeleceng.2017.11.008
U. R. Acharya et al., "Automated screening tool for dry and wet age-related macular degeneration (ARMD) using pyramid of histogram of oriented gradients (PHOG) and nonlinear features," Journal of Computational Science, vol. 20, pp. 41–51, May 2017. DOI: https://doi.org/10.1016/j.jocs.2017.03.005
S. Khalid et al., "Automated diagnosis system for age related macular degeneration using hybrid features set from fundus images," International Journal of Imaging Systems and Technology, vol. 31, no. 1, pp. 236–252, Mar. 2021. DOI: https://doi.org/10.1002/ima.22456
I. F. Kallel and S. Kammoun, "Hybrid human-artificial intelligence system for early detection and classification of AMD from fundus image," Signal, Image and Video Processing, vol. 18, no. 5, pp. 4779–4796, July 2024. DOI: https://doi.org/10.1007/s11760-024-03115-2
N. Li, T. Li, C. Hu, K. Wang, and H. Kang, "A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection," in Benchmarking, Measuring, and Optimizing, 2021, pp. 177–193. DOI: https://doi.org/10.1007/978-3-030-71058-3_11
H. Fang et al., "ADAM Challenge: Detecting Age-Related Macular Degeneration From Fundus Images," IEEE Transactions on Medical Imaging, vol. 41, no. 10, pp. 2828–2847, July 2022. DOI: https://doi.org/10.1109/TMI.2022.3172773
K. Jin et al., "FIVES: A Fundus Image Dataset for Artificial Intelligence based Vessel Segmentation," Scientific Data, vol. 9, no. 1, Aug. 2022, Art. no. 475. DOI: https://doi.org/10.1038/s41597-022-01564-3
S. Pachade et al., "Retinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research," Data, vol. 6, no. 2, Feb. 2021. DOI: https://doi.org/10.3390/data6020014
K. Zuiderveld, "Contrast limited adaptive histogram equalization," in Graphics Gems IV, Academic Press Professional, Inc., 1994, pp. 474–485. DOI: https://doi.org/10.1016/B978-0-12-336156-1.50061-6
T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971–987, July 2002. DOI: https://doi.org/10.1109/TPAMI.2002.1017623
R. M. Haralick, K. Shanmugam, and I. Dinstein, "Textural Features for Image Classification," IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, Nov. 1973. DOI: https://doi.org/10.1109/TSMC.1973.4309314
M. A. Stricker and M. Orengo, "Similarity of color images," in Storage and Retrieval for Image and Video Databases III, Mar. 1995, vol. 2420, pp. 381–392. DOI: https://doi.org/10.1117/12.205308
B. Schölkopf and A. J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, 2002. DOI: https://doi.org/10.7551/mitpress/4175.001.0001
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, June 2002. DOI: https://doi.org/10.1613/jair.953
R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2, May 1995, pp. 1137–1143.
G. Zeng, "On the confusion matrix in credit scoring and its analytical properties," Communications in Statistics - Theory and Methods, vol. 49, no. 9, pp. 2080–2093, May 2020. DOI: https://doi.org/10.1080/03610926.2019.1568485
Downloads
How to Cite
License
Copyright (c) 2026 Leonardo Petra Refialy, Sri Hartati, Sigit Priyanta, Supanji Supanji, Mohammad Eko Prayogo, Firman Setya Wardhana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
