Computers and Electrical Engineering 73 (2019) 245–258 Contents lists available at ScienceDirect Computers and Electrical Engineering journal homepage: www.elsevier.com/locate/compeleceng Segmentation of retinal blood vessels from ophthalmologic Diabetic Retinopathy images  T. Jemima Jebaseeli a,∗ , C. Anand Deva Durai b , J. Dinesh Peter a a Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore 641114,Tamilnadu, India b Department of Computer Science and Engineering, King Khalid University, Abha 61421, Saudi Arabia a r t i c l e i n f o Article history: Received 12 September 2017 Revised 20 November 2018 Accepted 29 November 2018 Keywords: Diabetic Retinopathy Fundus image Retina Image segmentation Feature extraction Deep learning SVM Blood vessel Ophthalmology Neural network a b s t r a c t The most prominent ophthalmic cause of blindness is Diabetic Retinopathy (DR). This reti- nal disease is characterized by variation in diameter of the retinal blood vessel and the new blood vessel growth inside the retina. A system to enhance the quality of the seg- mentation result over the pathological retinal images has been proposed. The proposed method uses Contrast Limited Adaptive Histogram Equalization (CLAHE) for preprocessing and Tandem Pulse Coupled Neural Network (TPCNN) model for automatic feature vectors generation then classification and extraction of the retinal blood vessels via Deep Learn- ing Based Support Vector Machine (DLBSVM). The proposed approach is assessed over the standard public fundus image databases to evaluate the performance. The results render that these techniques improve the segmentation results with an average value of 74.45% sensitivity, 99.40% specificity, and 99.16% accuracy. The results evoke that the proposed method is a suitable alternative for supervised techniques. © 2018 Elsevier Ltd. All rights reserved. 1. Introduction Diabetic Retinopathy (DR) is a disease that occurs among patients with Type-II diabetes. People may lose their vision if it is not recognized and treated early. At the advanced stage, it leads to detachment of retina from the eye [1]. DR makes the outer retinal layer thick. While these layers develop it spurts out the elements inside the retina and causes leakage of blood vessels and hemorrhages. The lipids and proteins inside the retinal layers produced as a tiny blot of exudates, microaneurysms, and cotton wool spots in the eye [2]. There are diverse segmentation procedures recommended by various researchers. In any case, these techniques work just on fundus images with no pathological impacts [3]. There are difficulties in segmenting the vascular vessel treemap without any discontinuities. Azzopardi et al. [4] designed a Bar-selective Combination Of Shifted Filter Responses (BCOS- FIRE) filter. Its parameters influence the performance of the filter. Wilfred Franklin and Edward Rajan [5] have proposed the Multilayer Perceptron Neural Network to detect the retinal vessels. The weight of the feedforward network is changed using the backpropagation algorithm for its depiction. Since it is a kind of pixel processing based approach, it has a less amount  This paper is for CAEE special section SI-eoth. Reviews processed and recommended for publication to the Editor-in-Chief by Guest Editor Dr. Jia-Shing Sheu. ∗ Corresponding author. E-mail address: jemima_jeba@karunya.edu (T.J. Jebaseeli). https://doi.org/10.1016/j.compeleceng.2018.11.024 0045-7906/© 2018 Elsevier Ltd. All rights reserved.