Multivariate quasi-Laplacian mixture models for wavelet-based image denoising

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper we introduce a class of multivariate quasi-Laplacian models as a generalization of the single-variable Laplacian distribution to multi-dimensions. A mixture model is used as the wavelet coefficient prior for the wavelet-based Bayesian image denoising algorithm. As a multivariate probability model, it is able to capture the intra-scale or inter-scale dependencies among wavelet coefficients. Two special cases are studied for orthogonal transform based image denoising. Efficient parameter estimation methods and denoising rules are derived for the two cases. Denoising results are compared with existing techniques in both PSNR values and visual qualities.

Original languageEnglish (US)
Title of host publication2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings
Pages2625-2628
Number of pages4
DOIs
StatePublished - 2006
Event2006 IEEE International Conference on Image Processing, ICIP 2006 - Atlanta, GA, United States
Duration: Oct 8 2006Oct 11 2006

Other

Other2006 IEEE International Conference on Image Processing, ICIP 2006
CountryUnited States
CityAtlanta, GA
Period10/8/0610/11/06

Fingerprint

Image denoising
Parameter estimation

Keywords

  • Image restoration
  • Wavelet transforms

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Shi, F., & Selesnick, I. (2006). Multivariate quasi-Laplacian mixture models for wavelet-based image denoising. In 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings (pp. 2625-2628). [4107107] https://doi.org/10.1109/ICIP.2006.313048

Multivariate quasi-Laplacian mixture models for wavelet-based image denoising. / Shi, Fei; Selesnick, Ivan.

2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings. 2006. p. 2625-2628 4107107.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shi, F & Selesnick, I 2006, Multivariate quasi-Laplacian mixture models for wavelet-based image denoising. in 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings., 4107107, pp. 2625-2628, 2006 IEEE International Conference on Image Processing, ICIP 2006, Atlanta, GA, United States, 10/8/06. https://doi.org/10.1109/ICIP.2006.313048
Shi F, Selesnick I. Multivariate quasi-Laplacian mixture models for wavelet-based image denoising. In 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings. 2006. p. 2625-2628. 4107107 https://doi.org/10.1109/ICIP.2006.313048
Shi, Fei ; Selesnick, Ivan. / Multivariate quasi-Laplacian mixture models for wavelet-based image denoising. 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings. 2006. pp. 2625-2628
@inproceedings{bc239428a38f456bbdefb3ce6def481e,
title = "Multivariate quasi-Laplacian mixture models for wavelet-based image denoising",
abstract = "In this paper we introduce a class of multivariate quasi-Laplacian models as a generalization of the single-variable Laplacian distribution to multi-dimensions. A mixture model is used as the wavelet coefficient prior for the wavelet-based Bayesian image denoising algorithm. As a multivariate probability model, it is able to capture the intra-scale or inter-scale dependencies among wavelet coefficients. Two special cases are studied for orthogonal transform based image denoising. Efficient parameter estimation methods and denoising rules are derived for the two cases. Denoising results are compared with existing techniques in both PSNR values and visual qualities.",
keywords = "Image restoration, Wavelet transforms",
author = "Fei Shi and Ivan Selesnick",
year = "2006",
doi = "10.1109/ICIP.2006.313048",
language = "English (US)",
isbn = "1424404819",
pages = "2625--2628",
booktitle = "2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings",

}

TY - GEN

T1 - Multivariate quasi-Laplacian mixture models for wavelet-based image denoising

AU - Shi, Fei

AU - Selesnick, Ivan

PY - 2006

Y1 - 2006

N2 - In this paper we introduce a class of multivariate quasi-Laplacian models as a generalization of the single-variable Laplacian distribution to multi-dimensions. A mixture model is used as the wavelet coefficient prior for the wavelet-based Bayesian image denoising algorithm. As a multivariate probability model, it is able to capture the intra-scale or inter-scale dependencies among wavelet coefficients. Two special cases are studied for orthogonal transform based image denoising. Efficient parameter estimation methods and denoising rules are derived for the two cases. Denoising results are compared with existing techniques in both PSNR values and visual qualities.

AB - In this paper we introduce a class of multivariate quasi-Laplacian models as a generalization of the single-variable Laplacian distribution to multi-dimensions. A mixture model is used as the wavelet coefficient prior for the wavelet-based Bayesian image denoising algorithm. As a multivariate probability model, it is able to capture the intra-scale or inter-scale dependencies among wavelet coefficients. Two special cases are studied for orthogonal transform based image denoising. Efficient parameter estimation methods and denoising rules are derived for the two cases. Denoising results are compared with existing techniques in both PSNR values and visual qualities.

KW - Image restoration

KW - Wavelet transforms

UR - http://www.scopus.com/inward/record.url?scp=78649868087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649868087&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2006.313048

DO - 10.1109/ICIP.2006.313048

M3 - Conference contribution

SN - 1424404819

SN - 9781424404810

SP - 2625

EP - 2628

BT - 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings

ER -