Please use this identifier to cite or link to this item:
Title: Detection of retinal blood vessels based on nonlinear projections
Authors: Zhang, Y. 
Hsu, W. 
Lee, M.L. 
Keywords: Adaptive thresholding
Image decomposition
Nonlinear orthogonal projection
Parameter selection
Retinal imaging
Vessel detection
Issue Date: 2009
Citation: Zhang, Y., Hsu, W., Lee, M.L. (2009). Detection of retinal blood vessels based on nonlinear projections. Journal of Signal Processing Systems 55 (1-3) : 103-112. ScholarBank@NUS Repository.
Abstract: An automated method for blood vessel segmentation is presented in this paper. The approach uses the nonlinear orthogonal projection to capture the features of vessel networks, and derives a novel local adaptive thresholding algorithm for vessel detection. By embedding in a kind of image decomposition model, the selection of system parameter which reflects the size of concerned convex set is examined. This approach differs from previously known methods in that it uses matched filtering, vessel tracking or supervised methods. The algorithm was tested on two publicly available databases: the DRIVE and the STARE. By comparison with hand-labeled ground truth, an average accuracy of 96.1% is achieved on the former database, and an average accuracy of 90.8% is achieved on the later database. © 2008 Springer Science+Business Media, LLC.
Source Title: Journal of Signal Processing Systems
ISSN: 19398018
DOI: 10.1007/s11265-008-0179-5
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Feb 18, 2019


checked on Feb 18, 2019

Page view(s)

checked on Jan 27, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.