Citation :

Gurpreet Kaur, Amit Kumar Bindal, "HybridFONet: Hybrid Feature-based Optimized CNN Algorithm for Precise Ocular Disease Classification from JPG images via CNN and Pre-trained Deep Learning Models," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 8, pp. 136-153, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I8P109

Abstract

Ocular diseases, including diabetic retinopathy, cataract, glaucoma, age-related macular degeneration, hypertension-related retinal changes, myopia, and other retinal abnormalities, are major contributors to visual impairment and blindness. Manual interpretation of fundus images is reliable but time-consuming and dependent on specialist availability, making automated deep-learning-based screening important for large-scale eye-care support. This study proposes HybridFONet, a hybrid feature-based optimized CNN framework for precise multi-class ocular disease classification from JPG fundus images. The proposed method uses the ODIR-5K fundus-image database and classifies images into eight categories: Normal, Diabetes, Cataract, Glaucoma, Age-related Macular Degeneration, Myopia, Hypertension, and other abnormalities. The workflow includes image preprocessing, resizing, grayscale conversion, Butterworth band-pass filtering, data augmentation, VGG16-based transfer-feature extraction, Crow Search Optimization-based feature selection, and final classification using a one-dimensional CNN with softmax output. Experimental results show that HybridFONet achieved 96.47% accuracy, 97.29% precision, 95.58% recall, 96.32% F1-score, and a 3.53% error rate. Comparative analysis demonstrates that the proposed model outperformed VGG16, Improved AlexNet, VGG19, ResNet50, and ResNet152V2. These findings confirm that optimized deep-feature selection combined with CNN classification improves recognition accuracy, reduces the influence of redundant features, and supports reliable automated ocular-disease screening.

Keywords

Ocular disease, Crow Search Optimization, Convolutional Neural Network, Transfer Learning, Retinal imaging, Deep Learning.

References

[1] Mohammed Ramzi Mohammed, and Ashraf Fathi “Global Prevalence of Diabetic Retinopathy over the Last Decade (2015–2025): A Scoping Review,” medRxiv, pp. 1-10, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Mario A. Vasilescu, and Mioara L. Macovei, “The Perspective of using Optical Coherence Tomography in Ophthalmology: Present and Future Applications,” Diagnostics, vol. 15, no. 4, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Feifei Cao et al., “Development and Validation of a Deep Learning Model for Early Detection and Screening of Diabetic Retinopathy,” BMC Medical Informatics and Decision Making, vol. 25, no. 1, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Xiao Chun Ling et al., “Deep Learning in Glaucoma Detection and Progression Prediction: A Systematic Review and Meta-Analysis,” Biomedicines, vol. 13, no. 2, pp. 1-26, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Kalla Bharath Vardhan et al., “Eye Disease Detection using Deep Learning Models with Transfer Learning Techniques,” EAI Endorsed Transactions on Scalable Information Systems, vol. 12, no. 1, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link] 

[6] Halit Çetiner, “Cataract Disease Classification from Fundus Images with Transfer Learning based Deep Learning Model on Two Ocular Disease Datasets,” Gümüşhane University Journal of Science and Technology, vol. 13, no. 2, pp. 258-269, 2023.
[CrossRef] [Google Scholar] [Publisher Link]  

[7] Antonella Santone et al., “A Method for Ocular Disease Diagnosis through Visual Prediction Explainability,” Electronics, vol. 13, no. 14, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]   

[8] Shumoos Al-Fahdawi et al., “Fundus-DeepNet: Multi-label Deep-Learning classification System for Enhanced Detection of Multiple Ocular Diseases through Data Fusion of Fundus Images,” Information Fusion, vol. 102, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]    

[9] Celina Rieck et al., “A Novel Transformer-CNN Hybrid Deep Learning Architecture for Robust Broad-Coverage Diagnosis of Eye Diseases on Color Fundus Images,” IEEE Access, vol. 13, pp. 156285-156300, 2025.
[CrossRef] [Google Scholar] [Publisher Link]  

[10] Sara Ejaz et al., “Fundus Image Classification using Feature Concatenation for Early Diagnosis of Retinal Disease,” Digital Health, vol. 11, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Deependra Singh, Saksham Agarwal, and Subhankar Mishra, “Retinal Fundus Multi-Disease Image Classification using Hybrid CNN-Transformer-Ensemble Architectures,” Proceedings of the International Health Informatics Conference IHIC, Springer, Singapore, vol. 1113, pp. 103-120, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Ismael Abdulkareem Ali, and Sozan Abdulla Mahmood et al., “Enhancing Clinical Decision Support: A Deep Learning Approach for Automated Diagnosis of Eye Diseases from Fundus Images,” UHD Journal of Science and Technology, vol. 39, no. 2, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Geethanjali Kher et al., “DeB5-XNet: An Explainable Ensemble Model for Ocular Disease Classification using Feature Extraction and Grad-CAM,” Informatics in Medicine Unlocked, vol. 54, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]     

[14] Akshaj Singh et al., “EyeFusionNet: A Hybrid CNN-Transformer Network for Automated Diansis of Eye Diseases using Colour Fundus Imaging,” EAI Endorsed Transactions on Intelligent Systems and Machine Learning Applications, vol. 2, pp. 1-13, 2025.
[CrossRef] [Publisher Link]      

[15] Ans Ibrahim Mahameed Alqassab, M.-Á. Luque-Nieto, and Mazin Abed Mohammed, “Identification of Multiple Ocular Diseases using a Hybrid Quantum Convolutional Neural Network with Fundus Images,” Scientific Reports, pp. 1-21, 2026.
[CrossRef] [Google Scholar] [Publisher Link] 

[16] Kaggle, Ocular Disease Recognition, Kaggle, 2024. [Online]. Available: https://www.kaggle.com/datasets/andrewmvd/ocular-disease-recognition-odir5k/data

[17] Abdelazim G. Hussien et al., “Crow Search Algorithm: Theory, Recent Advances, and Applications,” IEEE Access, vol. 8, pp. 173548-173565, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Jiantao Zhao, and Lili Li, “Research on Image Classification Algorithm based on Convolutional Neural Network-Tensorflow,” Journal of Physics: Conference Series, vol. 2010, no. 1, pp. 1-7, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Jessica Ryan et al., “Harnessing Deep Learning for Ocular Disease Diagnosis,” Procedia Computer Science, vol. 245, pp. 914-923, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Nadim Mahmud Dipu, Sifatul Alam Shohan, and K.M.A Salam, “Ocular Disease Detection using Advanced Neural Network based Classification Algorithms,” Asian Journal of Convergence in Technology, vol. 7, no. 2, pp. 91-99, 2021.
[CrossRef] [Google Scholar] [Publisher Link]