Blind Image Restoration Using a Block-Stationary Signal Model

Author

Bishop, Tom E. ; Hopgood, James R.

Author_Institution

IDCOM, Edinburgh Univ.

Volume

2

fYear

2006

fDate

14-19 May 2006

Abstract

We present a novel method for blind image restoration which is a multidimensional extension of an approach used successfully for audio restoration. A nonstationary image model is used to increase reliability of blur estimates. This source model consists of a separate autoregressive model in each region of the image. A hierarchical Bayesian model for the observations is used, and a maximum marginalised a posteriori (MMAP) blur estimate is obtained by optimising the resulting probability density function

Keywords

Bayes methods; autoregressive processes; image restoration; maximum likelihood estimation; audio restoration; autoregressive model; blind image restoration; block-stationary signal model; blur estimation reliability; hierarchical Bayesian model; maximum marginalised a posteriori blur estimation; nonstationary image model; probability density function; Autoregressive processes; Bayesian methods; Cost function; Image restoration; Maximum likelihood estimation; Multidimensional systems; Optical signal processing; Parameter estimation; Reliability engineering; Signal restoration;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on

Conference_Location

Toulouse

ISSN

1520-6149

Print_ISBN

1-4244-0469-X

Type

conf

DOI

10.1109/ICASSP.2006.1660477

Filename

1660477