Blind deconvolution using generalized cross-validation approach to regularization parameter estimation

Haiyong Liao; Kwok Po NG

doi:10.1109/TIP.2010.2073474

Blind deconvolution using generalized cross-validation approach to regularization parameter estimation

Haiyong Liao^*, Kwok Po NG

^*Corresponding author for this work

Department of Mathematics

Research output: Contribution to journal › Article › peer-review

68 Citations (Scopus)

Abstract

In this paper, we propose and present an algorithm for total variation (TV)-based blind deconvolution. Both the unknown image and blur can be estimated within an alternating minimization framework. With the generalized cross-validation (GCV) method, the regularization parameters associated with the unknown image and blur can be updated in alternating minimization steps. Experimental results confirm that the performance of the proposed algorithm is better than variational Bayesian blind deconvolution algorithms with Student's-t priors or a total variation prior.

Original language	English
Article number	5565466
Pages (from-to)	670-680
Number of pages	11
Journal	IEEE Transactions on Image Processing
Volume	20
Issue number	3
DOIs	https://doi.org/10.1109/TIP.2010.2073474
Publication status	Published - Mar 2011

Scopus Subject Areas

Software
Computer Graphics and Computer-Aided Design

User-Defined Keywords

Alternating minimization
blind deconvolution
generalized cross validation (GCV)
regularization parameters
total variation (TV)

Access to Document

10.1109/TIP.2010.2073474

Cite this

@article{85ef392d5c2e48a59d2b2362ff34fc83,

title = "Blind deconvolution using generalized cross-validation approach to regularization parameter estimation",

abstract = "In this paper, we propose and present an algorithm for total variation (TV)-based blind deconvolution. Both the unknown image and blur can be estimated within an alternating minimization framework. With the generalized cross-validation (GCV) method, the regularization parameters associated with the unknown image and blur can be updated in alternating minimization steps. Experimental results confirm that the performance of the proposed algorithm is better than variational Bayesian blind deconvolution algorithms with Student's-t priors or a total variation prior.",

keywords = "Alternating minimization, blind deconvolution, generalized cross validation (GCV), regularization parameters, total variation (TV)",

author = "Haiyong Liao and NG, {Kwok Po}",

note = "Funding Information: Manuscript received December 16, 2009; revised June 14, 2010; accepted August 27, 2010. Date of publication September 07, 2010; date of current version February 18, 2011. This work was supported in part by grants from the Hong Kong Research Grant Council and Hong Kong Baptist University Faculty Research rant. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yongyi Yang.",

year = "2011",

month = mar,

doi = "10.1109/TIP.2010.2073474",

language = "English",

volume = "20",

pages = "670--680",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Blind deconvolution using generalized cross-validation approach to regularization parameter estimation

AU - Liao, Haiyong

AU - NG, Kwok Po

N1 - Funding Information: Manuscript received December 16, 2009; revised June 14, 2010; accepted August 27, 2010. Date of publication September 07, 2010; date of current version February 18, 2011. This work was supported in part by grants from the Hong Kong Research Grant Council and Hong Kong Baptist University Faculty Research rant. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yongyi Yang.

PY - 2011/3

Y1 - 2011/3

N2 - In this paper, we propose and present an algorithm for total variation (TV)-based blind deconvolution. Both the unknown image and blur can be estimated within an alternating minimization framework. With the generalized cross-validation (GCV) method, the regularization parameters associated with the unknown image and blur can be updated in alternating minimization steps. Experimental results confirm that the performance of the proposed algorithm is better than variational Bayesian blind deconvolution algorithms with Student's-t priors or a total variation prior.

AB - In this paper, we propose and present an algorithm for total variation (TV)-based blind deconvolution. Both the unknown image and blur can be estimated within an alternating minimization framework. With the generalized cross-validation (GCV) method, the regularization parameters associated with the unknown image and blur can be updated in alternating minimization steps. Experimental results confirm that the performance of the proposed algorithm is better than variational Bayesian blind deconvolution algorithms with Student's-t priors or a total variation prior.

KW - Alternating minimization

KW - blind deconvolution

KW - generalized cross validation (GCV)

KW - regularization parameters

KW - total variation (TV)

UR - http://www.scopus.com/inward/record.url?scp=79951838700&partnerID=8YFLogxK

U2 - 10.1109/TIP.2010.2073474

DO - 10.1109/TIP.2010.2073474

M3 - Article

AN - SCOPUS:79951838700

VL - 20

SP - 670

EP - 680

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 3

M1 - 5565466

ER -

Blind deconvolution using generalized cross-validation approach to regularization parameter estimation

Abstract

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this