Blind deconvolution of images using optimal sparse representations

Michael M. Bronstein; Alexander M. Bronstein; Michael Zibulevsky; Yehoshua Y. Zeevi

doi:10.1109/TIP.2005.847322

Blind deconvolution of images using optimal sparse representations

Michael M. Bronstein^*, Alexander M. Bronstein, Michael Zibulevsky, Yehoshua Y. Zeevi

^*Corresponding author for this work

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

Abstract

The relative Newton algorithm, previously proposed for quasi-maximum likelihood blind source separation and blind deconvolution of one-dimensional signals is generalized for blind deconvolution of images. Smooth approximation of the absolute value is used as the nonlinear term for sparse sources. In addition, we propose a method of sparsification, which allows blind deconvolution of arbitrary sources, and show how to find optimal sparsifying transformations by supervised learning.

Original language	English
Pages (from-to)	726-736
Number of pages	11
Journal	IEEE Transactions on Image Processing
Volume	14
Issue number	6
DOIs	https://doi.org/10.1109/TIP.2005.847322
State	Published - Jun 2005
Externally published	Yes

Keywords

Blind deconvolution
Quasi-maximum likelihood
Relative Newton optimization
Sparse representations

Access to Document

10.1109/TIP.2005.847322

Cite this

@article{20c4c7418fc34df48f61b29b5c394bb5,

title = "Blind deconvolution of images using optimal sparse representations",

abstract = "The relative Newton algorithm, previously proposed for quasi-maximum likelihood blind source separation and blind deconvolution of one-dimensional signals is generalized for blind deconvolution of images. Smooth approximation of the absolute value is used as the nonlinear term for sparse sources. In addition, we propose a method of sparsification, which allows blind deconvolution of arbitrary sources, and show how to find optimal sparsifying transformations by supervised learning.",

keywords = "Blind deconvolution, Quasi-maximum likelihood, Relative Newton optimization, Sparse representations",

author = "Bronstein, {Michael M.} and Bronstein, {Alexander M.} and Michael Zibulevsky and Zeevi, {Yehoshua Y.}",

note = "Funding Information: Manuscript received January 3, 2004; revised June 14, 2004. This work was supported in part by the HASSIP Research Network Program HPRN-CT-2002-00285 and in part by the European Commission and by the Ollendorff Minerva Center. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Vincent Caselles.",

year = "2005",

month = jun,

doi = "10.1109/TIP.2005.847322",

language = "אנגלית",

volume = "14",

pages = "726--736",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

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

number = "6",

}

TY - JOUR

T1 - Blind deconvolution of images using optimal sparse representations

AU - Bronstein, Michael M.

AU - Bronstein, Alexander M.

AU - Zibulevsky, Michael

AU - Zeevi, Yehoshua Y.

N1 - Funding Information: Manuscript received January 3, 2004; revised June 14, 2004. This work was supported in part by the HASSIP Research Network Program HPRN-CT-2002-00285 and in part by the European Commission and by the Ollendorff Minerva Center. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Vincent Caselles.

PY - 2005/6

Y1 - 2005/6

N2 - The relative Newton algorithm, previously proposed for quasi-maximum likelihood blind source separation and blind deconvolution of one-dimensional signals is generalized for blind deconvolution of images. Smooth approximation of the absolute value is used as the nonlinear term for sparse sources. In addition, we propose a method of sparsification, which allows blind deconvolution of arbitrary sources, and show how to find optimal sparsifying transformations by supervised learning.

AB - The relative Newton algorithm, previously proposed for quasi-maximum likelihood blind source separation and blind deconvolution of one-dimensional signals is generalized for blind deconvolution of images. Smooth approximation of the absolute value is used as the nonlinear term for sparse sources. In addition, we propose a method of sparsification, which allows blind deconvolution of arbitrary sources, and show how to find optimal sparsifying transformations by supervised learning.

KW - Blind deconvolution

KW - Quasi-maximum likelihood

KW - Relative Newton optimization

KW - Sparse representations

UR - http://www.scopus.com/inward/record.url?scp=20444411101&partnerID=8YFLogxK

U2 - 10.1109/TIP.2005.847322

DO - 10.1109/TIP.2005.847322

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:20444411101

SN - 1057-7149

VL - 14

SP - 726

EP - 736

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

IS - 6

ER -

Blind deconvolution of images using optimal sparse representations

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this