Detection of Blood Vessels in the Retina Using Gabor Filters

Abstract

Quantitative analysis of the vascular architecture of the retina as well as changes in the shape, width, and tortuosity of the vessels could assist in the monitoring of the effects of diabetes, arteriosclerosis, hypertension, and premature birth on the visual system. The detection of blood vessels in the retina is an important initial step for most applications of image analysis in ophthalmology. We propose digital image processing techniques for the detection of blood vessels in the retina. The methods include the design of a bank of directionally sensitive Gabor filters. Forty images of the retina from the DRIVE database were used to evaluate the methods. High efficiency of detection of blood vessels with the area under the receiver operating characteristics curve of up to 0.95 was achieved.