期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：8
页码：14049
DOI：10.15680/IJIRCCE.2017.0508031
出版社：S&S Publications
摘要：Glaucoma is a disease that damages the optic nerve. It causes irremediable blindness if it is leftuntreated. This has made glaucoma detection as the main research topic in the field of medicine. Currently, there is noeffective method that can be used for low cost population-based glaucoma detection or screening. Recent studies haveshown that automated optic nerve head assessment from 2D retinal fundus images is capable of low cost populationbasedglaucoma screening.The proposed system explains a method for cup to disc ratio (CDR) assessment using 2D retinal fundus images. Inthe proposed system, the optic disc is first segmented and cup to disc ratio is calculated. In this paper, the disc is locatedusing earlier brightness based method, which performs well in our data sets for glaucoma. The segmentation estimatesthe disc boundary, but pathological changes around disc,blood vessel occlusions, and variable imaging conditionsmakes it a challenging task. Here, the disc is segmented using the self-assessed disc segmentation method, which is acombination of three approaches. It has been shown that the self-assessed method achieves more accurate discsegmentation than the individual methods.
