Share Email Print

Proceedings Paper

An efficient algorithm for measurement of retinal vessel diameter from fundus images based on directional filtering
Author(s): Xuchu Wang; Yanmin Niu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Automatic measurement of vessels from fundus images is a crucial step for assessing vessel anomalies in ophthalmological community, where the change in retinal vessel diameters is believed to be indicative of the risk level of diabetic retinopathy. In this paper, a new retinal vessel diameter measurement method by combining vessel orientation estimation and filter response is proposed. Its interesting characteristics include: (1) different from the methods that only fit the vessel profiles, the proposed method extracts more stable and accurate vessel diameter by casting this problem as a maximal response problem of a variation of Gabor filter; (2) the proposed method can directly and efficiently estimate the vessel's orientation, which is usually captured by time-consuming multi-orientation fitting techniques in many existing methods. Experimental results shows that the proposed method both retains the computational simplicity and achieves stable and accurate estimation results.

Paper Details

Date Published: 4 February 2011
PDF: 4 pages
Proc. SPIE 7752, PIAGENG 2010: Photonics and Imaging for Agricultural Engineering, 77521N (4 February 2011); doi: 10.1117/12.888298
Show Author Affiliations
Xuchu Wang, Chongqing Univ. (China)
Yanmin Niu, Chongqing Normal Univ. (China)

Published in SPIE Proceedings Vol. 7752:
PIAGENG 2010: Photonics and Imaging for Agricultural Engineering
Honghua Tan, Editor(s)

© SPIE. Terms of Use
Back to Top