A Novel 5x5 Edge Detection Operator for BloodVessel Images

摘要

Background: Blood vessel appearance is an important indicator for many diagnoses, including diabetes, hypertension, and arteriosclerosis.Aims: Blood Vessel edge detection in retinal images is very important in medical image processing. A lot of algorithms have been suggested for extracting medical image edges.Methodology: In this paper a new 5x5 edge detection masks are proposed based on the finite difference method.Results: The proposed method is applied on a set of blood vessel images and we obtained good results in comparison with 5x5 Sobel mask.