Hierarchical Bayesian image restoration from partially-known blurs

Author

Mesarovic, Vladimir ; Galatsanos, Nikolas ; Molina, Rafael ; Katsaggelos, Aggelos

Author_Institution

Crystal Semicond. Corp., Austin, TX, USA

Volume

5

fYear

1998

Firstpage

2905

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

Keywords

Bayes methods; digital filters; discrete Fourier transforms; image enhancement; image restoration; least squares approximations; parameter estimation; DFT; RCTLS filter; hierarchical Bayesian image restoration; partially-known blurs; regularized constrained least-squares filter; restoration filters; two-step algorithm; very large images; Algorithm design and analysis; Bayesian methods; Covariance matrix; Discrete Fourier transforms; Image restoration; Iterative algorithms; Mean square error methods; Nonlinear filters; Parameter estimation; Tomography;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.678133

Filename

678133