Skip to main navigation Skip to search Skip to main content

Saliency detection: A self-adaption sparse representation approach

  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

Saliency detection is essential to visual attention modelling and various computer vision tasks. Representation and measurement are two important issues for saliency models. Good representation and reasonable measurement are both critical issues in modelling visual saliency mechanism. For every input image, we obtain a self-adaptive dictionary that describes the image content effectively and image prior that forces sparsity in every location in the image using the K-SVD algorithm. For saliency measurement, background firing rate (BFR) is defined for each sparse features and it is followed by feature activation rate (FAR) computation to measure the bottom-up visual saliency.

Original languageEnglish
Title of host publicationProceedings - 6th International Conference on Image and Graphics, ICIG 2011
PublisherIEEE Computer Society
Pages461-465
Number of pages5
ISBN (Print)9780769545417
DOIs
StatePublished - 2011
Externally publishedYes
Event6th International Conference on Image and Graphics, ICIG 2011 - Hefei, Anhui, China
Duration: 12 Aug 201115 Aug 2011

Publication series

NameProceedings - 6th International Conference on Image and Graphics, ICIG 2011

Conference

Conference6th International Conference on Image and Graphics, ICIG 2011
Country/TerritoryChina
CityHefei, Anhui
Period12/08/1115/08/11

Keywords

  • Background firing rate
  • Feature activation rate
  • K-svd algorithm
  • Saliency detection
  • Selfadaptive
  • Visual attention model

Fingerprint

Dive into the research topics of 'Saliency detection: A self-adaption sparse representation approach'. Together they form a unique fingerprint.

Cite this