Glaucoma detection using texture features extraction

Abstract

Glaucoma is a second leading cause of the disease in the world. The World Health Organization has estimated that by 2020, about 80 million people would suffer from glaucoma. As the disease progresses, it leads to structural changes in the Optic Nerve Head (ONH). Optic Nerve Head is the region which consists of Optic Cup and Optic Disc. The region of interest is extracted from the fundus image by using Hough Transformation. It is an automated way of segmentation used to obtain the accurate results and it replaces the manual segmentation. The k-mean clustering also used for segmentation which is another approach. From the segmented ONH, the different features like Gray Level Cooccurrence Matrix (GLCM) and Markov Random Field (MRF) are extracted. As the structural changes taken place in ONH, the texture and the intensity values also changes. The features are used to classify the images as normal and glaucoma. The algorithm speed increases by applying the technique on region of interest instead of using complete image directly. Hence the algorithm results about 94% of accuracy in segmentation using Hough Transform, 84% for segmentation using k-means clustering and about 86% for classification using support vector machine.