Blind restoration of blurred photographs via AR modelling and MCMC

Author

Bishop, Tom E. ; Molina, Rafael ; Hopgood, James R.

Author_Institution

Sch. of Eng. & Electron., Univ. of Edinburgh, Edinburgh

fYear

2008

fDate

12-15 Oct. 2008

Firstpage

669

Lastpage

672

Abstract

We propose a new image and blur prior model, based on non-stationary autoregressive (AR) models, and use these to blindly deconvolve blurred photographic images, using the Gibbs sampler. As far as we are aware, this is the first attempt to tackle a real-world blind image deconvolution (BID) problem using Markov chain Monte Carlo (MCMC) methods. We give examples with simulated and real out-of-focus images, which show the state-of-the-art results that the proposed approach provides.

Keywords

Markov processes; Monte Carlo methods; autoregressive processes; deconvolution; image restoration; image sampling; Gibbs sampler; MCMC; Markov chain Monte Carlo method; blind restoration; blurred photographic image; deconvolution; nonstationary autoregressive model; Bayesian methods; Deconvolution; Degradation; Image processing; Image restoration; Maximum likelihood estimation; Monte Carlo methods; Parameter estimation; Signal processing; Signal restoration; Bayesian methods; Blind Deconvolution; Gibbs Sampler; Learned Image Prior; Nonstationary Image Models;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on

Conference_Location

San Diego, CA

ISSN

1522-4880

Print_ISBN

978-1-4244-1765-0

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2008.4711843

Filename

4711843