Web-Based Hybrid Deep Learning and Machine Learning System for Automated Glaucoma Detection from fundus images
DOI:
https://doi.org/10.15662/IJEETR.2026.0802110Keywords:
Glaucoma Detection, Fundus Image Analysis, EfficientNetB0, Machine Learning, Support Vector Machine, Random Forest, Hybrid Classification, Principal Component Analysis, Cup-to-Disc Ratio (CDR), Medical Image Processing.Abstract
Glaucoma is one of the leading causes of permanent vision loss worldwide, and early detection plays a critical role in preventing severe damage. However, traditional screening methods require expert analysis of retinal fundus images, To address this proposed system presents an automated glaucoma detection system that combines deep learning and machine learning techniques within a practical web-based framework. The proposed system begins by validating whether the uploaded image is a proper retinal fundus image using structural and intensity-based checks. Once validated, the image is resized and preprocessed then passed into a pre-trained EfficientNetB0 model to extract meaningful visual features. These features are further refined using scaling and Principal Component Analysis (PCA). For classification, a hybrid approach is adopted by combining Support Vector Machine (SVM) and Random Forest classifiers. The final prediction is obtained by averaging the probability outputs of both models, which improves stability and reduces misclassification. In addition to this, the Cup-to-Disc Ratio (CDR) is estimated. The system was evaluated using a EyePACS-AIROGS-light-V2 fundus image dataset and achieved an accuracy of 84.5% along with an AUC score of 0.92, indicating reliable performance. The integration of this model into a web application enables real-time screening and report generation, making it a practical tool for early glaucoma detection
References
1. Tan, M. and Le, Q., “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” International Conference on Machine Learning (ICML), 2019.
2. He, K., Zhang, X., Ren, S. and Sun, J., “Deep Residual Learning for Image Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
3. Krizhevsky, A., Sutskever, I. and Hinton, G., “ImageNet Classification with Deep Convolutional Neural Networks,” NeurIPS, 2012.
4. Acharya, U. R., et al., “Automated Detection of Glaucoma Using Deep Learning,” Journal of Medical Systems, 2017.
5. Thakur, N. and Juneja, M., “Survey on Glaucoma Detection Using Machine Learning Techniques,” International Journal of Medical Informatics, 2018.
6. Raghavendra, U., et al., “Optic Disc and Cup Segmentation Methods for Glaucoma Detection: A Review,” IEEE Access, 2018.
7. World Health Organization, “Blindness and Vision Impairment,” 2021.
8. Kiefer, R., “EyePACS-AIROGS-light-V2 Dataset,” Kaggle, 2024.
9. Sivaswamy, J., et al., “DRISHTI-GS: Retinal Image Dataset for Glaucoma Analysis,” 2014.
10. Breiman, L., “Random Forests,” Machine Learning Journal, 2001.
11. C.Nagarajan and M.Madheswaran - ‘Stability Analysis of Series Parallel Resonant Converter with Fuzzy Logic Controller Using State Space Techniques’- Taylor &Francis, Electric Power Components and Systems, Vol.39 (8), pp.780-793, May 2011. DOI: 10.1080/15325008.2010.541746
12. C.Nagarajan and M.Madheswaran - ‘Experimental verification and stability state space analysis of CLL-T Series Parallel Resonant Converter’ - Journal of Electrical Engineering, Vol.63 (6), pp.365-372, Dec.2012. DOI: 10.2478/v10187-012-0054-2
13. C.Nagarajan and M.Madheswaran - ‘Performance Analysis of LCL-T Resonant Converter with Fuzzy/PID Using State Space Analysis’- Springer, Electrical Engineering, Vol.93 (3), pp.167-178, September 2011. DOI 10.1007/s00202-011-0203-9
14. S.Tamilselvi, R.Prakash, C.Nagarajan,“Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller” Iranian Journal Of Science And Technology-Transactions Of Electrical Engineering, DOI10.1007/s40998-025-00917-z,2025
15. S.Tamilselvi, R.Prakash, C.Nagarajan,“ Adaptive sliding mode control of multilevel grid-connected inverters using reinforcement learning for enhanced LVRT performance” Electric Power Systems Research 253 (2026) 112428, doi.org/10.1016/j.epsr.2025.112428
16. S.Thirunavukkarasu, C. Nagarajan, 2024, “Performance Investigation on OCF and SCF study in BLDC machine using FTANN Controller," Journal of Electrical Engineering And Technology, Volume 20, pages 2675–2688, (2025), doi.org/10.1007/s42835-024-02126-w
17. C. Nagarajan, M.Madheswaran and D.Ramasubramanian- ‘Development of DSP based Robust Control Method for General Resonant Converter Topologies using Transfer Function Model’- Acta Electrotechnica et Informatica Journal , Vol.13 (2), pp.18-31,April-June.2013, DOI: 10.2478/aeei-2013-0025.
18. C.Nagarajan and M.Madheswaran - ‘DSP Based Fuzzy Controller for Series Parallel Resonant converter’- Springer, Frontiers of Electrical and Electronic Engineering, Vol. 7(4), pp. 438-446, Dec.12. DOI 10.1007/s11460-012-0212-0.
19. C.Nagarajan and M.Madheswaran - ‘Experimental Study and steady state stability analysis of CLL-T Series Parallel Resonant Converter with Fuzzy controller using State Space Analysis’- Iranian Journal of Electrical & Electronic Engineering, Vol.8 (3), pp.259-267, September 2012.
20. C.Nagarajan and M.Madheswaran, “Analysis and Simulation of LCL Series Resonant Full Bridge Converter Using PWM Technique with Load Independent Operation” has been presented in ICTES’08, a IEEE / IET International Conference organized by M.G.R.University, Chennai.Vol.no.1, pp.190-195, Dec.2007
21. Suganthi Mullainathan, Ramesh Natarajan, “An SPSS and CNN modelling based quality assessment using ceramic materials and membrane filtration techniques”, Revista Materia (Rio J.) Vol. 30, 2025, DOI: https://doi.org/10.1590/1517-7076-RMAT-2024-0721
22. M Suganthi, N Ramesh, “Treatment of water using natural zeolite as membrane filter”, Journal of Environmental Protection and Ecology, Volume 23, Issue 2, pp: 520-530,2022
23. Cortes, C. and Vapnik, V., “Support Vector Machines,” Machine Learning, 1995.
24. Bishop, C. M., Pattern Recognition and Machine Learning, Springer, 2006.
25. Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, 2016.
26. Simonyan, K. and Zisserman, A., “Very Deep Convolutional Networks (VGG),” 2014.
27. Szegedy, C., et al., “Going Deeper with Convolutions,” CVPR, 2015.
28. Esteva, A., et al., “Dermatologist-Level Classification of Skin Cancer Using Deep Neural Networks,” Nature, 2017.
29. Litjens, G., et al., “Deep Learning in Medical Image Analysis: A Survey,” Medical Image Analysis, 2017.
30. Gulshan, V., et al., “Development of a Deep Learning Algorithm for Detection of Diabetic Retinopathy,” JAMA, 2016.
31. Ronneberger, O., et al., “U-Net: Convolutional Networks for Biomedical Image Segmentation,” 2015.
32. Pedregosa, F., et al., “Scikit-learn: Machine Learning in Python,” JMLR, 2011.
33. Anand, L. (2024). AI-Powered Cloud Cybersecurity Architecture for Risk Prediction and Threat Mitigation in Healthcare and Finance. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 7(Special Issue 1), 5-12.
34. Mathew, A. Trust Is Not a Default Control: AI-Powered Social Engineering and the Need to Have New Governance.
35. Anbazhagan, K., Kumar, R., Thilagavathy, R., & Anuradha, D. (2024, March). Shortest Job First with Gateway-based Resource Management Strategy for Fog Enabled Cloud Computing. In 2024 4th International Conference on Data Engineering and Communication Systems (ICDECS) (pp. 1-6). IEEE
