EAI Endorsed Transactions on Pervasive Health and Technology Research Article Hybrid glaucoma detection model based on reflection components separation from retinal fundus images Satyabrata Lenka 1 , Zefree Lazarus Mayaluri 2,∗ 1,2 Department of Electrical Engineering, C. V. Raman Global University, Bhubaneswar, Odisha, India Abstract 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 preprocessing step for specularity removal from corrupted fundus images using a modified dichromatic reflection model. We develope 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. Keywords: Fundus image, Glaucoma, Specularity, Diffusion, CNN Received on 30 March 2023; accepted on 28 May 2023; published on 10 July 2023 Copyright © 2023 Yavuz et al, licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC- SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited. doi:10.4108/eetpht.9.3191 1. Introduction In recent years, retinal imaging has become a common tool in the medical diagnosis of visual illnesses as glaucoma, cataract, and diabetic retinopathy [1]. Fundus cameras are frequently used to obtain retinal images, which depict the internal anatomies such as the optic disc, retinal vessels, and optic cup. By conducting a thorough investigation of these retinal images, it is confirmed that the changes found in these retinal structures are symptomatic of a pathological condition connected to diseases like glaucoma and diabetic retinopathy. Retinal image analysis is thus a ∗ Corresponding author. Email: zefree.lazarus@cgu-odisha.ac.in practical and beneficial diagnostic technique. In reality, by determining the root cause of the issue, analysis of retinal images can be helpful in classifying the stages of eye diseases. So, the image processing approaches mainly depends on the quality of the images, which further depends on the illumination level of the light sources. Whenever light enters into the eye and passes through a transparent protective layer called the cornea, much light are specularly reflected due to the curvature surface of eye. The light then falls onto the retina which senses the visual signals by passing through the pupil and lens. As there is no internal light in the eye, an external source provides light at the time of image capturing. The retinal fundus 1 EAI Endorsed Transactions on Pervasive Health and Technology 2023 | Volume 9