Hierarchical Bayesian image restoration from partially-known blurs

Vladimir Mesarovic; Nikolas Galatsanos; Rafael Molina; Aggelos Katsaggelos

doi:10.1109/ICASSP.1998.678133

Hierarchical Bayesian image restoration from partially-known blurs

Vladimir Mesarovic, Nikolas Galatsanos, Rafael Molina, Aggelos Katsaggelos

MRC - Materials Research Center

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

A number of restoration filters have been proposed for the restoration problem from partially-known blurs. Previously we proposed the regularized constrained least-squares filter (RCTLS) and showed that it has a number of advantages over previous ones (Mesarovic et al. 1995). However, the problem of estimating the parameters that define the RCTLS filter has not yet been addressed. In this paper we propose a two-step algorithm based on the hierarchical Bayesian approach to simultaneously restore the image and estimate the parameters of the RCTLS restoration filter. The algorithm is derived in the DFT domain; thus, it is very efficient even for very large images.

Original language	English (US)
Title of host publication	Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Pages	2905-2908
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.1998.678133
State	Published - 1998
Event	1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 - Seattle, WA, United States Duration: May 12 1998 → May 15 1998

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	5
ISSN (Print)	1520-6149

Other

Other	1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Country/Territory	United States
City	Seattle, WA
Period	5/12/98 → 5/15/98

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.1998.678133

Cite this

Mesarovic, V., Galatsanos, N., Molina, R., & Katsaggelos, A. (1998). Hierarchical Bayesian image restoration from partially-known blurs. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 (pp. 2905-2908). Article 678133 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 5). https://doi.org/10.1109/ICASSP.1998.678133

@inproceedings{659c758e230c4ec69667a34c8e564f5d,

title = "Hierarchical Bayesian image restoration from partially-known blurs",

abstract = "A number of restoration filters have been proposed for the restoration problem from partially-known blurs. Previously we proposed the regularized constrained least-squares filter (RCTLS) and showed that it has a number of advantages over previous ones (Mesarovic et al. 1995). However, the problem of estimating the parameters that define the RCTLS filter has not yet been addressed. In this paper we propose a two-step algorithm based on the hierarchical Bayesian approach to simultaneously restore the image and estimate the parameters of the RCTLS restoration filter. The algorithm is derived in the DFT domain; thus, it is very efficient even for very large images.",

author = "Vladimir Mesarovic and Nikolas Galatsanos and Rafael Molina and Aggelos Katsaggelos",

year = "1998",

doi = "10.1109/ICASSP.1998.678133",

language = "English (US)",

isbn = "0780344286",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "2905--2908",

booktitle = "Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998",

note = "1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 ; Conference date: 12-05-1998 Through 15-05-1998",

}

Mesarovic, V, Galatsanos, N, Molina, R & Katsaggelos, A 1998, Hierarchical Bayesian image restoration from partially-known blurs. in Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998., 678133, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 5, pp. 2905-2908, 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998, Seattle, WA, United States, 5/12/98. https://doi.org/10.1109/ICASSP.1998.678133

Hierarchical Bayesian image restoration from partially-known blurs. / Mesarovic, Vladimir; Galatsanos, Nikolas; Molina, Rafael et al.
Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998. 1998. p. 2905-2908 678133 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Hierarchical Bayesian image restoration from partially-known blurs

AU - Mesarovic, Vladimir

AU - Galatsanos, Nikolas

AU - Molina, Rafael

AU - Katsaggelos, Aggelos

PY - 1998

Y1 - 1998

N2 - A number of restoration filters have been proposed for the restoration problem from partially-known blurs. Previously we proposed the regularized constrained least-squares filter (RCTLS) and showed that it has a number of advantages over previous ones (Mesarovic et al. 1995). However, the problem of estimating the parameters that define the RCTLS filter has not yet been addressed. In this paper we propose a two-step algorithm based on the hierarchical Bayesian approach to simultaneously restore the image and estimate the parameters of the RCTLS restoration filter. The algorithm is derived in the DFT domain; thus, it is very efficient even for very large images.

AB - A number of restoration filters have been proposed for the restoration problem from partially-known blurs. Previously we proposed the regularized constrained least-squares filter (RCTLS) and showed that it has a number of advantages over previous ones (Mesarovic et al. 1995). However, the problem of estimating the parameters that define the RCTLS filter has not yet been addressed. In this paper we propose a two-step algorithm based on the hierarchical Bayesian approach to simultaneously restore the image and estimate the parameters of the RCTLS restoration filter. The algorithm is derived in the DFT domain; thus, it is very efficient even for very large images.

UR - http://www.scopus.com/inward/record.url?scp=0031620120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031620120&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1998.678133

DO - 10.1109/ICASSP.1998.678133

M3 - Conference contribution

AN - SCOPUS:0031620120

SN - 0780344286

SN - 9780780344280

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2905

EP - 2908

BT - Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998

T2 - 1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998

Y2 - 12 May 1998 through 15 May 1998

ER -

Mesarovic V, Galatsanos N, Molina R, Katsaggelos A. Hierarchical Bayesian image restoration from partially-known blurs. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998. 1998. p. 2905-2908. 678133. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.1998.678133

Hierarchical Bayesian image restoration from partially-known blurs

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this