期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：6
页码：10334
DOI：10.15680/IJIRSET.2015.0506152
出版社：S&S Publications
摘要：Cataract is an eye disease which is responsible for vision loss and blindness. In this paper, remoteautomated cataract detection system is proposed to detect the cataract efficiently and to help patients to know theircataract condition timely, so that they can get proper treatment from doctors. The remote cataract detection system isdeployed on the cloud, so clients can access system remotely. This system mainly consists of four stages namelypreprocessing, feature extraction, classification and grading. Binary SVM is implemented to classify the fundus imageand for grading, MDA algorithm is applied. Classification is carried out for two classes i.e. non-cataract and cataract.Grading part consists of three classes i.e. mild, moderate and severe cataract. The dataset used is real-world datasetcontaining 261 images. SVM algorithm provides better results than MDA algorithm used for classification.
