期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2013
卷号：4
期号：6-4
出版社：Seventh Sense Research Group
摘要：A Diabetic Retinopathy is retinopathy caused by complications of diabetes, which can eventually lead to blindness. Early stage of vision loss diagnosis is one of the challenge processes. In this project prior Diabetic retinopathy diagnosis implement based on SVM classifier. To improve the classifier accuracy depends upon the retinal blood vessel features. For blood vessel extraction proposes a function based on the evaluation of measurable features describing retinal blood vasculature. This paper proposes a function for vessel segmentation assessment based on vascular tree descriptive features with the aim of supplementing the existing quality evaluation functions (QEFs). Specifically, this new proposed function, denoted by CAL, evaluates vessel connectivity, area and length in a segmented image in comparison with those in a referencestandard image. Thus, this function is sensitive to vasculature features such as connectivity, area and length, and supplements widelyused metrics based on contingency tables.
关键词：Diabetic Retinopathy; SVM Classifier; quality evaluation function
