Authors:
Alauddin Bhuiyan
1
;
Ryo Kawasaki
1
;
Ecosse Lamoureux
2
;
Kotagiri Ramamohanarao
1
and
Tien Y. Wong
2
Affiliations:
1
The University of Melbourne, Australia
;
2
The University of Melbourne and National University of Singapore, Australia
Keyword(s):
Retinal image, Vessel segmentation, Canny edge detection, Gaussian smoothing, Region growing technique, Edge profiling.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Detection and Identification
;
Medical Image Detection, Acquisition, Analysis and Processing
Abstract:
Retinal blood vessel changes (e.g., vessel caliber) are important indicators for earlier diagnosis of cardiovascular diseases. To quantify the changes automatically, a reliable vessel detection is essential. However, blood vessel detection in retinal image is complicated by a huge variation in a number of factors such as local contrast, vessel width and vessel central reflex. In this paper, we propose a new technique to detect retinal blood vessels which is able to address these issues. The core of the technique is a new vessel edge selection method which combines the method of finding edge pattern and edge profiling techniques. Experimental results show that 92.40% success rate in the identification of vessel start-points and 88.73% success rate in tracking the major vessels.