Skip to main navigation Skip to search Skip to main content

Image super-resolution via dual-dictionary learning and sparse representation

  • Jian Zhang*
  • , Chen Zhao
  • , Ruiqin Xiong
  • , Siwei Ma
  • , Debin Zhao
  • *Corresponding author for this work
  • School of Computer Science and Technology, Harbin Institute of Technology
  • Peking University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Learning-based image super-resolution aims to reconstruct high-frequency (HF) details from the prior model trained by a set of high-and low-resolution image patches. In this paper, HF to be estimated is considered as a combination of two components: main high-frequency (MHF) and residual high-frequency (RHF), and we propose a novel image super-resolution method via dual-dictionary learning and sparse representation, which consists of the main dictionary learning and the residual dictionary learning, to recover MHF and RHF respectively. Extensive experimental results on test images validate that by employing the proposed two-layer progressive scheme, more image details can be recovered and much better results can be achieved than the state-of-the-art algorithms in terms of both PSNR and visual perception.

Original languageEnglish
Title of host publicationISCAS 2012 - 2012 IEEE International Symposium on Circuits and Systems
PublisherIEEE Computer Society
Pages1688-1691
Number of pages4
ISBN (Electronic)9781467302197
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 IEEE International Symposium on Circuits and Systems, ISCAS 2012 - Seoul, Korea, Republic of
Duration: 20 May 201223 May 2012

Publication series

NameISCAS 2012 - 2012 IEEE International Symposium on Circuits and Systems

Conference

Conference2012 IEEE International Symposium on Circuits and Systems, ISCAS 2012
Country/TerritoryKorea, Republic of
CitySeoul
Period20/05/1223/05/12

Keywords

  • dictionary learning
  • image interpolation
  • sparse representation
  • super-resolution

Fingerprint

Dive into the research topics of 'Image super-resolution via dual-dictionary learning and sparse representation'. Together they form a unique fingerprint.

Cite this