Retinal Blood Vessel Segmentation and Identification of Glaucoma Using Convolutional Neural Network

Abstract

Exudates are the main root cause of blindness. These exudates are looks like cotton wool spots. The damages due to increment of exudates are wet macular detection and retinopathy. Hence, the important diagnostic task is to find exudates. In this paper, we extract the blood vessels using thresholding method along with filtering the image using curvelet transformation and detect optic disc using circular Hough-man transform method. Finally we detect the exudates using adaptive thresholding method in fundus image along with boundary detection using contour boundary tracing algorithm. Measuring the vessel ratio damage ratio and damage stage of the eye based on ocular vision strategy. Identifying the eye diseases was a complicated process, our approaches made easy by using Multi resolution analysis with feature extraction process. Texture features with in fundus images are actively pursued for accurate and efficient glaucoma classification. In this paper a novel technique proposed, energy texture features extracted using CURVELET transformations which is accessible under geometry conditions where wavelets were not defined to satisfy conditions and also compared with WAVELET transformation analysis. SVM classifier is used for the classification process and feature ranking procedure under extension of multi SVM classifier. This is used for obtaining accurate results. Under the above mentioned conditions the resultant accuracy is about 97.35%.