Comparison of Matched Filter and Wavelet based Blood Vessel Enhancement

M.U. Akram, S. Nasir, and S.A. Khan(Pakistan)

Keywords

Blood vessels, Matched filter, 2-D wavelet, vessel enhancement.

Abstract

Diabetic retinopathy occurs when high blood sugar damages small blood vessels in retina so blood vessel segmentation is an essential step for the diagnoses of diabetic retinopathy. An automated tool for blood vessel segmentation is useful to eye specialists for purpose of patient screening and clinical study. In this paper, we present a wavelet based method for enhancing, locating and segmenting blood vessels in images of retina. This technique is tested on publicly available STARE database of hand labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. Wavelet based enhancement method is compared with matched filter based vessel enhancement method. The validation of our retinal image vessel enhancement technique is supported by results.

Important Links:



Go Back