Extraction of Retinal Blood Vessels from Color Fundus

Retinal image analysis is an active field of research for identifying different types of diseases that affect the Retina. The extraction and analysis of retinal vasculature is an essential part of several practical applications such as detection of hypertension, Diabetic Retinopathy, stroke and cardiovascular diseases that affects eye. The proposed method consists of four stages: In the first stage we enhance the original retinal image to increase their contrast and eliminate the non uniform illumination in retinal images. The second stage involves a 2D Gabor filter which is capable of tuning to specific frequencies, thus allowing noise filtering and vessel enhancement in a single step. The next stage involves segmentation of blood vessels by an edge detection approach that separates the vascular network from the background and the final stage includes some morphological operations for obtaining better results. This proposed method may be used for determination of arteriolar to venular diameter ratio in retinal images. This process is basis for the AVR calculation i.e. for the calculation of average diameter of arteries to veins. Keywords— Retina, Retinal vasculature, Blood vessels, Diabetic Retinopathy, Non uniform illumination, 2D Gabor filter, AVR