文章基本信息

标题：Detection of Blood Vessels and Measurement of Vessel width for Diabetic Retinopathy
本地全文：下载
作者：S.Sukanya ; S.Abinaya ; Dr.D.Tamilselvi 等
期刊名称：Computer Science & Information Technology
电子版ISSN：2231-5403
出版年度：2014
卷号：4
期号：9
页码：233-246
DOI：10.5121/csit.2014.4923
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The proposed method measures the retinal blood vessel diameter to identify arteriolarnarrowing, arteriovenous (AV) nicking, branching coefficients to detect early diabeticretinopathy. It utilizes the vessel centerline and edge information to measure the width for avessel segment. From the input retinal image, the vascular network is extracted using the localentropy thresholding method. The vessel boundaries are extracted using sobel edge detectionmethod. The skeletonization operation is applied to the vascular network and mapping thevessel boundaries and the skeleton image. The branching point detection method is thenperformed to localize all crossing locations. A rotational invariant mask to search the pixelpairs from the edge image, and calculate the shortest distance pair which provides the vesselwidth (or diameter) for that cross-section. Variation in the width measurement identifies thediabetic retinopathy.
关键词：Computer Vision; Image Processing; Edge Detection; Mapping; Diabetic Retinopathy.