A POCS-based Constrained Total Least Squares Algorithm for Image Restoration

There are no files associated with this record.

Title A POCS-based Constrained Total Least Squares Algorithm for Image Restoration
Author Gan, Xiangchao; Liew, Alan Wee-Chung; Yan, Hong
Journal Name Journal of Visual Communication and Image Representation
Year Published 2006
Place of publication USA
Publisher Academic Press
Abstract In image restoration, the region of support of the point spread function is often much smaller than the size of the observed degraded image and this property is utilized in many image deconvolution algorithms. For the constrained total least squares (CTLS)-based algorithm, it means that the solution of the CTLS algorithm should retain the block-circulant and sparse structure of the degradation matrix simultaneously. In real image restoration problems, the CTLS method often involves large-scale computation and is often solved using Mesarovic et al.'s algorithm. However, there is concern about whether their algorithm preserves the sparse structure of the degradation matrix. In this paper, we prove that by imposing an extra constraint, the sparse structure in their algorithm can be preserved. Then, we use the projection onto convex sets algorithm to find a solution to this extended formulation. Our experimental study indicates that the proposed method performs competitively, and often better, in terms of visual and objective evaluations.
Peer Reviewed Yes
Published Yes
Publisher URI http://www.sciencedirect.com/science/journal/10473203
Alternative URI http://dx.doi.org/10.1016/j.jvcir.2006.02.002
Volume 17
Issue Number 5
Page from 986
Page to 1003
ISSN 1047-3203
Date Accessioned 2007-04-27
Language en_AU
Research Centre Institute for Integrated and Intelligent Systems
Faculty Faculty of Engineering and Information Technology
Subject PRE2009-Image Processing
URI http://hdl.handle.net/10072/21793
Publication Type Journal Articles (Refereed Article)
Publication Type Code c1x

Show simple item record

Griffith University copyright notice