Haralick features based automated glaucoma classification using back propagation neural network

Abstract

According to recent researches, glaucoma, an optic nerve disease, is considered as one of the major causes which can lead to blindness. It has affected a huge number of people worldwide. Rise in intraocular pressure of the eye leads to the disease resulting in progressive and permanent visual loss. Texture of normal retinal image and glaucoma image is different. Here texture property of the total image has been extracted from both with and without glaucoma image. In this work, Haralick features have been used to distinguish between normal and glaucoma affected retina. Extracted features have been utilized to train the back propagation neural network. Classification of glaucoma affected eye is successfully achieved with an accuracy of 96%.