A regularization approach to joint blur identification and image restoration

Yu Li You, M. Kaveh

Research output: Contribution to journalArticlepeer-review

345 Scopus citations


The primary difficulty with blind image restoration, or joint blur identification and image restoration, is insufficient information. This calls for proper incorporation of a priori knowledge about the image and the point-spread function (PSF). A well-known space-adaptive regularization method for image restoration is extended to address this problem. This new method effectively utilizes, among others, the piecewise smoothness of both the image and the PSF. It attempts to minimize a cost function consisting of a restoration error measure and two regularization terms (one for the image and the other for the blur) subject to other hard constraints. A scale problem inherent to the cost function is identified, which, if not properly treated, may hinder the minimization/blind restoration process. Alternating minimization is proposed to solve this problem so that algorithmic efficiency as well as simplicity is significantly increased. Two implementations of alternating minimization based on steepest descent and conjugate gradient methods are presented. Good performance is observed with numerically and photographically blurred images, even though no stringent assumptions about the structure of the underlying blur operator is made.

Original languageEnglish (US)
Pages (from-to)416-428
Number of pages13
JournalIEEE Transactions on Image Processing
Issue number3
StatePublished - 1996

Bibliographical note

Funding Information:
Manuscript received August 26, 1994; revised June 26, 1995. This work was supported by the BMDO/IST program managed by the Office of Naval Research under Contract N00014-92-J-1911. The associate editor coordinating the review of this paper and approving it for publication was Prof. Xinhua Zhuang. The authors are with the Department of Electrical Engineering, University of Minnesota, Minneapolis, MN 55455 USA (email: kaveh@ee.umn.edu). Publisher Item Identifier S 1057-7 149(96)0 1802-7.


Dive into the research topics of 'A regularization approach to joint blur identification and image restoration'. Together they form a unique fingerprint.

Cite this