OSA's Digital Library

Journal of the Optical Society of America A

Journal of the Optical Society of America A

| OPTICS, IMAGE SCIENCE, AND VISION

  • Editor: Stephen A. Burns
  • Vol. 24, Iss. 4 — Apr. 1, 2007
  • pp: 973–983

Approach to blind image deconvolution by multiscale subband decomposition and independent component analysis

Ivica Kopriva  »View Author Affiliations


JOSA A, Vol. 24, Issue 4, pp. 973-983 (2007)
http://dx.doi.org/10.1364/JOSAA.24.000973


View Full Text Article

Enhanced HTML    Acrobat PDF (1015 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

A single-frame multichannel blind image deconvolution technique has been formulated recently as a blind source separation problem solved by independent component analysis (ICA). The attractive feature of this approach is that neither origin nor size of the spatially invariant blurring kernel has to be known. To enhance the statistical independence among the hidden variables, we employ multiscale analysis implemented by wavelet packets and use mutual information to locate a subband with the least dependent components, where the basis matrix is learned by means of standard ICA. We show that the proposed algorithm is capable of performing blind deconvolution of nonstationary signals that are not independent and identically distributed processes. The image poses these properties. The algorithm is tested on experimental data and compared with state-of-the-art single-frame blind image deconvolution algorithms. Our good experimental results demonstrate the viability of the proposed concept.

© 2007 Optical Society of America

OCIS Codes
(070.6020) Fourier optics and signal processing : Continuous optical signal processing
(100.1830) Image processing : Deconvolution
(100.3020) Image processing : Image reconstruction-restoration
(100.3190) Image processing : Inverse problems
(100.7410) Image processing : Wavelets

ToC Category:
Image Processing

History
Original Manuscript: May 30, 2006
Revised Manuscript: October 26, 2006
Manuscript Accepted: October 26, 2006
Published: March 14, 2007

Citation
Ivica Kopriva, "Approach to blind image deconvolution by multiscale subband decomposition and independent component analysis," J. Opt. Soc. Am. A 24, 973-983 (2007)
http://www.opticsinfobase.org/josaa/abstract.cfm?URI=josaa-24-4-973

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you wish to use one of your free member downloads to view the figures, click "Enhanced HTML" above and access the figures from the article itself or from the navigation tab.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

If you are accessing the full text through a member bundle, please use the Enhanced HTML link to gain access to the citation lists and other restricted features. Note that accessing both the PDF and HTML versions of an article will count as only one download against your account.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited