An adaptive norm algorithm for image restoration

Daniele BERTACCINI*, Raymond H. CHAN, Serena MORIGI, Fiorella SGALLARI

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

14 Citations (Scopus)

Abstract

We propose an adaptive norm strategy designed for the re-storation of images contaminated by blur and noise. Standard Tikhonov regularization can give good results with Gaussian noise and smooth images, but can over-smooth the output. On the other hand, L 1-TV (Total Variation) regularization has superior performance with some non-Gaussian noise and controls both the size of jumps and the geometry of the object boundaries in the image but smooth parts of the recovered images can be blocky. According to a coherence map of the image which is obtained by a threshold structure tensor, and can detect smooth regions and edges in the image, we apply L 2-norm or L 1-norm regularization to different parts of the image. The solution of the resulting minimization problem is obtained by a fast algorithm based on the half-quadratic technique recently proposed in [2] for L 1-TV regularization. Some numerical results show the effectiveness of our adaptive norm image restoration strategy.

Original languageEnglish
Title of host publicationScale Space and Variational Methods in Computer Vision: Third International Conference, SSVM 2011, Revised Selected Papers
EditorsAlfred M. BRUCKSTEIN, Bart M. Haar ROMENY, Alexander M. BRONSTEIN, Michael M. BRONSTEIN
PublisherSpringer Berlin Heidelberg
Pages194-205
Number of pages12
ISBN (Electronic)9783642247859
ISBN (Print)9783642247842
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event3rd International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2011 - Ein-Gedi, Israel
Duration: 29 May 20112 Jun 2011

Publication series

NameLecture Notes in Computer Science
Volume6667
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference3rd International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2011
Country/TerritoryIsrael
CityEin-Gedi
Period29/05/112/06/11

Fingerprint

Dive into the research topics of 'An adaptive norm algorithm for image restoration'. Together they form a unique fingerprint.

Cite this