Hybrid glaucoma detection model based on reflection components separation from retinal fundus images





Fundus image, Glaucoma, Specularity, Reflection components, Diffusion, CNN


The diagnosis of diseases associated to the retina is significantly aided by retinal fundus images. However, when flash illumination is used during image acquisition, specularity reflection can occur on images. The retinal image processing applications are popular now days in diseases detection such as glaucoma, diabetic retinopathy, and cataract. Many modern disease detection algorithms suffer from performance accuracy limitation due to the creation of specularity reflection problem. This research proposes a hybrid model for screening of glaucoma which includes a preprocessing step to separate specular reflections from corrupted fundus images, a segmentation step using modified U-Net CNN, a feature extraction step, and an image classification step using support vector machine (SVM) with different kernels. Firstly, the diffuse and specular components are obtained using seven existing methods and apply a filter having high emphasis with a function called similar in each component. The best method, which provides highest quality images, is chosen among the seven compared methods and the output image is used in next steps for screening of glaucoma. The experimental results of the proposed model show that in preprocessing step, maximum improvement in terms of PSNR and SSIM are 37.97 dB and 0.961 respectively. For glaucoma detection experiment the results have the accuracy, sensitivity, and specificity of 91.83%, 96.39%, and 95.37% respectively and AUROC of 0.971.


Download data is not yet available.


M. D. Abramoff, M. K. Garvin, and M. Sonka, Retinal imaging and image analysis, IEEE reviews in biomedical engineering, vol. 3, pp.169-208, 2010.

H. Wang, S. Lin, X. Liu, and S. B. Kang, Separating reflections in human iris images for illumination estimation, in Tenth IEEEInternational Conference on Computer Vision (ICCV05) Volume 1,vol. 2. IEEE, 2005, pp. 1691-1698.

D. Bhowmik, K. S. Kumar, L. Deb, S. Paswan, and A. Dutta, Glaucoma-a eye disorder its causes, risk factor, prevention and medication. The Pharma Innovation, vol. 1, no. 1, Part A, p. 66, 2012.

R. Shinde, Glaucoma detection in retinal fundus images using u-net and supervised machine learning algorithms, Intelligence-Based Medicine,vol. 5, p. 100038, 2021.

S. A. Shafer, Using color to separate reflection compo-nents, Color Research and Application, vol. 10, no. 4, pp.

-218, 1985.

R. Kola r and J. Jan, Detection of glaucomatous eye via color fundusimages using fractal dimensions, Radioengineering, vol. 17, no. 3, pp.109-114, 2008.

J. Pruthi and S. Mukherjee, Computer based early diagnosis of glaucoma in biomedical data using image processing and automated earlynerve fiber layer defects detection using feature extraction in retinalcolored stereo fundus images, International Journal of Scientific and Engineering Research, vol. 4, no. 4, p. 1822, 2013.

M. Zhou, K. Jin, S. Wang, J. Ye, and D. Qian, Color retinal image enhancement based on luminosity and contrast adjustment, IEEE Transactions on Biomedical engineering, vol. 65, no. 3, pp. 521-527, 2017.

K. Aurangzeb, S. Aslam, M. Alhussein, R. A. Naqvi, M. Arsalan, and S. I. Haider, Contrast enhancement of fundus images by employing modified pso for improving the performance of deep learning models, IEEE Access, vol. 9, pp. 47 930-47 945, 2021.

J. Wang, Y.-J. Li, and K.-F. Yang, Retinal fundus image enhancement with image decomposition and visual adaptation, Computers in Biologyand Medicine, vol. 128, p. 104116, 2021.

R. G. Ramani and J. J. Shanthamalar, Improved image processing techniques for optic disc segmentation in retinal fundus images, BiomedicalSignal Processing and Control, vol. 58, p. 101832, 2020.

J. Pruthi, K. Khanna, and S. Arora, Optic cup segmenta-tion from retinal fundus images using glowworm swarm optimization for glaucoma detection, Biomedical Signal Processing and Control, vol. 60, p. 102004,2020.

T. Nazir, A. Irtaza, and V. Starovoitov, Optic disc and optic cup segmentation for glaucoma detection from blur retinal images usingimproved mask-rcnn, International Journal of Optics, vol. 2021, 2021.

Lenka, S., and Lazarus, M. Z. (2022, December). Optic Disc Segmentation using Nonconvex Rank Approxima-tion from Retinal Fundus Images. In 2022 IEEE 2nd International Symposium on Sustainable Energy, Signal Processing and Cyber Security (iSSSC) (pp. 1-6). IEEE.

J. K. Virk, M. Singh, and M. Singh, Cup-to-disk ratio (cdr) determination for glaucoma screening, in 2015 1st International Conference onNext Generation Computing Technologies (NGCT). IEEE, 2015, pp.504-507.

R. Panda, N. B. Puhan, A. Rao, D. Padhy, and G. Panda, Recurrent neural network based retinal nerve fiber layer defect detection in earlyglaucoma, in 2017 IEEE 14th International Symposium on BiomedicalImaging (ISBI 2017). IEEE, 2017, pp. 692-695.

W. Ruengkitpinyo, P. Vejjanugraha, W. Kongprawech-non, T. Kondo, P. Bunnun, and H. Kaneko, An automatic glaucoma screening algorithm using cup-to-disc ratio and isnt rule with support vector machine, in IECON 2015-41st Annual Conference of the IEEE Industrial Electron-icsSociety. IEEE, 2015, pp. 000 517-000 521.

S. Karkuzhali and D. Manimegalai, Computational intelligencebased decision support system for glaucoma detection, BIOMEDICALRESEARCH-INDIA, vol. 28, no. 11, pp. 4737-4748, 2017.

A. Li, Y. Wang, J. Cheng, and J. Liu, Combining multiple deep features for glaucoma classification, in 2018 IEEE International Conference onAcoustics, Speech and Signal Processing (ICASSP). IEEE, 2018, pp.985-989.

L. Li, M. Xu, X. Wang, L. Jiang, and H. Liu, Attention based glaucoma detection: a large-scale database and cnn model, in Proceedings of theIEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 10 571-10 580.

X. Chen, Y. Xu, S. Yan, D. W. K. Wong, T. Y. Wong, and J.Liu, Automatic feature learning for glaucoma detection based on deeplearning, in International conference on medical image computing andcomputer-assisted intervention. Springer, 2015, pp. 669-677.

H.-L. Shen, H.-G. Zhang, S.-J. Shao, and J. H. Xin, Chromaticity based separation of reflection components in a single image, PatternRecognition, vol. 41, no. 8, pp. 2461-2469, 2008.

H.-L. Shen and Q.-Y. Cai, Simple and efficient method for specularity removal in an image, Applied optics, vol. 48, no. 14, pp. 2711-2719, 2009.

H.-L. Shen and Z.-H. Zheng, Real-time highlight removal using intensity ratio, Applied optics, vol. 52, no. 19, pp. 4483-4493, 2013.

K. Ikeuchi, D. Miyazaki, R. T. Tan, and K. Ikeuchi, Separating reflection components of textured surfaces using a single image, DigitallyArchiving Cultural Objects, pp. 353-384, 2008.

Y. Akashi and T. Okatani, Separation of reflection com-ponents by sparse non-negative matrix factorization, in Computer Vision-ACCV2014: 12th Asian Conference on Computer Vision, Singapore, Singapore,November 1-5, 2014, Revised Selected Papers, Part V 12. Springer,2015, pp. 611-625.

Q. Yang, S. Wang, and N. Ahuja, Real-time specular highlight removal using bilateral filtering, in European conference on computer vision.Springer, 2010, pp. 87-100.

K.-J. Yoon, Y. Choi, and I. S. Kweon, Fast separation of reflection components using a specularity-invariant image representation, in 2006international conference on image processing. IEEE, 2006, pp. 973-976.

Thomas, N., Zefree Lazarus, M., and Gupta, S.(2020). Separation of Diffuse and Specular Reflection Components from Real-World Color Images Captured Under Flash Imaging Conditions. In Energy Systems, Drives and Automations: Proceedings of ESDA 2019 (pp.

-275). Springer Singapore.

T. Yamamoto and A. Nakazawa, General improvement method of specular component separation using high-emphasis filter and similarityfunction, ITE Transactions on Media Technology and Applications,vol. 7, no. 2, pp. 92-102, 2019.

O. Ronneberger, P. Fischer, and T. Brox, U-net: Con-volutional networks for biomedical image segmenta-tion, in Medical Image Computingand Computer-Assisted Intervention-MICCAI 2015: 18th InternationalConfer-ence, Munich, Germany, October 5-9, 2015, Proceedings, Part III18. Springer, 2015, pp. 234-241.

A. Sevastopolsky, Optic disc and cup segmentation methods for glaucoma detection with modification of

u-net convolutional neuralnetwork, Pattern Recognition and Image Analysis, vol. 27, pp. 618-624, 2017.

S. Serte and A. Serener, Graph-based saliency and ensembles of convolutional neural networks for glaucoma detection, IET ImageProcessing, vol. 15, no. 3, pp. 797-804, 2021.

S. Pathan, P. Kumar, R. M. Pai, and S. V. Bhandary, Automated segmentation and classifcation of retinal features for glaucoma diagnosis, Biomedical Signal Processing and Control, vol. 63, p. 102244, 2021.

Y. Bao, J. Wang, T. Li, L. Wang, J. Xu, J. Ye, and D. Qian, Selfadaptive transfer learning for multicenter glaucoma classification infundus retina images, in Ophthalmic Medical Image Analysis: 8thInternational Workshop, OMIA 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings 8. Springer, 2021, pp. 129-138.

P. K. Chaudhary and R. B. Pachori, Automatic diagnosis of glaucoma using two-dimensional fourier-bessel series expansion based empiricalwavelet transform, Biomedical Signal Processing and Control, vol. 64,p. 102237, 2021.

Huang, Xiaoling, Kai Jin, Jiazhu Zhu, Ying Xue, Ke Si, Chun Zhang, Sukun Meng, Wei Gong, and Juan Ye, A structure-related fine-grained deep learning system with diversity data for universal glaucoma visual field grading, Frontiers in Medicine 9, 2022.

Fan, R., Alipour, K., Bowd, C., Christopher, M., Brye, N., Proudfoot, J.A., Goldbaum, M.H., Belghith, A., Girkin, C.A., Fazio, M.A. and Liebmann, J.M., Detecting Glaucoma from Fundus Photographs Using Deep Learning without Convolutions: Transformer for Improved Generalization. Ophthalmology Science, 3(1), p.100233, 2022.

T. K. Yoo, J. Y. Choi, and H. K. Kim, Cyclegan-based deep learning technique for artifact reduction in fundus photography, Graefe’s Archive for Clinical and Experimental Ophthalmology, vol. 258, no. 8, pp. 1631–1637, 2020. https://data.mendeley.com/datasets/dh2x8v6nf8.




How to Cite

Mayaluri ZL, Lenka S. Hybrid glaucoma detection model based on reflection components separation from retinal fundus images. EAI Endorsed Trans Perv Health Tech [Internet]. 2023 Jul. 10 [cited 2024 Apr. 25];9. Available from: https://publications.eai.eu/index.php/phat/article/view/3191