Blood vessels extraction using mathematical morphology

Abstract

The retinal vasculature is composed of the arteries and veins with their tributaries which are visible withinthe retinal image. The segmentation and measurement of the retinal vasculature is of primary interest in thediagnosis and treatment of a number of systemic and ophthalmologic conditions. The accurate segmentationof the retinal blood vessels is often an essential prerequisite step in the identification of retinal anatomy andpathology. In this study, we present an automated approach for blood vessels extraction using mathematicalmorphology. Two main steps are involved: enhancement operation is applied to the original retinal image inorder to remove the noise and increase contrast of retinal blood vessels and morphology operations areemployed to extract retinal blood vessels. This operation of segmentation is applied to binary image of tophattransformation. The result was compared with other algorithms and give better results. © 2013 Science Publications.