Joint Blurred Image Restoration with Partially Known Information

Author

Wu, Qing ; Wang, Xing-Ce ; Guo, Ping

Author_Institution

Image Process. & Pattern Recognition Lab., Beijing Normal Univ.

fYear

2006

fDate

13-16 Aug. 2006

Firstpage

3853

Lastpage

3858

Abstract

A new restoration method for joint blurred images with partially known information is proposed in this paper. The joint blur is assumed to be motion blurs and defocus blur mixed together. Under the condition of two blur effects are supposed to be independent linear shift-invariant processes and motion blur parameter can be obtained with known information, a reduced update Kalman filter (RUKF) is used for degraded image restoration and the best defocus point spread function (PSF) parameter is determined based on the maximum entropy principle (MEP). Experimental results with real images show that the proposed approach works well

Keywords

Kalman filters; image motion analysis; image restoration; maximum entropy methods; parameter estimation; Kalman filter; defocus blur; joint blurred image restoration; linear shift-invariant process; maximum entropy principle; motion blur parameter; partially known information; point spread function parameter; Autocorrelation; Cybernetics; Degradation; Entropy; Frequency estimation; Image processing; Image restoration; Machine learning; Neural networks; Parameter estimation; Pattern recognition; Wavelet domain; Joint blurred image; Maximum entropy principle; PSF estimation; Reduced update Kalman filter;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2006 International Conference on

Conference_Location

Dalian, China

Print_ISBN

1-4244-0061-9

Type

conf

DOI

10.1109/ICMLC.2006.258734

Filename

4028743