DocumentCode
419410
Title
A robust regularised restoration algorithm based on Topkis-Veinott optimisation method
Author
Zhu, Daan ; Razaz, Moe ; Lee, Richard
Author_Institution
Sch. of Comput. Sci., East Anglia Univ., Norwich, UK
Volume
4
fYear
2004
fDate
23-26 Aug. 2004
Firstpage
705
Abstract
We present a robust iterative algorithm for restoration of blurred and noisy images. The restoration model is first regularised and then solved iteratively. An optimal regularisation parameter is estimated using the Topkis-Veinott gradient method. This restoration algorithm is compared with other competitive restoration algorithms in the literature. Experimental results are presented to demonstrate the comparative important features of our algorithm, namely, robustness in the presence of noise and high quality restoration results.
Keywords
gradient methods; image restoration; noise; optimisation; parameter estimation; stability; Topkis-Veinott optimisation method; blurred image restoration; iterative algorithm; noisy image restoration; robust regularised restoration algorithm; Additive noise; Bioinformatics; Degradation; Equations; Gradient methods; Image restoration; Iterative algorithms; Optimization methods; Parameter estimation; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on
ISSN
1051-4651
Print_ISBN
0-7695-2128-2
Type
conf
DOI
10.1109/ICPR.2004.1333870
Filename
1333870
Link To Document