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：8
页码：3341-3345
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Diabetes is a group of metabolic diseases which occurs a person who has a high blood sugar or because the body does not generates sufficient insulin. Detecting Diabetes is a necessary thing for improve the life time of patient. The fast progression of diabetes is one of the major challenges of current health care. This diabetes causes Diabetic Retinopathy, which leads to a loss of sight. Early detection of diabetes is particularly important to prevent vision loss. In most of the existing system, support vector machine is used for classifying Healthy/DM and NPDR/DM-sans samples. However, it does not handle larger number of datasets and Appropriateness of the system is low. To solve this problem, the proposed system introduced for classifying Healthy/DM and NPDR/DM-sans samples with high Appropriateness. By using an image capture device, the tongue images are captured. The captured image is pre-processed by median filter. The proximal support vector machine is a classification technique which is used for separate the diabetes mellitus and non proliferative diabetic retinopathy samples from the healthy samples by utilising three groups of features such as color, texture, and geometry. An experimental result shows that the proposed method achieves high performance in terms Meticulousness, Remember, F-measure and appropriateness
关键词：Diabetes; median filter; Proliferative ; Diabetic Retinopathy
