期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：5
页码：1780-1783
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Diabetic retinopathy is the most common diabeticeye disease and a leading cause of blindness. However, if thesymptoms are identified earlier and a proper treatment isprovided through regular screenings, blindness can be avoided.In order to fasten the process of detection of diabeticretinopathy image processing techniques are used to detect theexistence of exudates in the retinal images. In this paper, todiagnose diabetic retinopathy, three methods like ColorHistogram Thresholding, Probabilistic Neural network (PNN)and Support vector machine (SVM) are described and theirperformances are compared.
