Recognition of glaucoma in fundus images using deep learning techniques and improve optic disc and optic cup segmentation

Abstract

Glaucoma is a perpetual damage of optic nerves which cause of newlinefractional or complete visual misfortune. The fundamental reason for this newlineillness is the increment of the intra-ocular pressure inside the eye which harms newlinethe optic nerve. It is projected that about 11 million people would be blind newlinefrom glaucoma by (2020) and it is the second leading cause for blindness newlineworldwide. Early-stage recognition of glaucoma is significant for eye disease newlinediagnosis. In this study, deep learning based techniques have been proposed newlinefor the recognition of glaucoma images from retinal fundus images. newlineInitially, an optimization-based Aging-SVM classifier has been newlineproposed for the recognition of glaucoma images from retinal fundus images. newlineThe performance of this method has been compared with different evolution newlineparameters such as Accuracy, Sensitivity and Specificity. The outcomes show newlinethat the proposed Aging-SVM classifier delivers 95% accuracy and it has been newlineimproved by 14% when compared with texture-based recognition system. newlineThe precise segmentation of optic disc and cup is yet an evolving newlineissue. Most of the segmentation based glaucoma recognition methods depends newlineon the handcrafted features. It affects the overall performance of the glaucom newline