New approach to texture saliency based on intrinsic relationship among texture features

  • Chen Xi
  • , Huo Hong
  • , Fang Tao*
  • , Li Deren
  • *Corresponding author for this work

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

1 Scopus citations

Abstract

We revisited texture saliency, took it to color images, introduced it to airborne remote sensing image processing and then deduced an objective evaluation to local and global saliency. We proposed a model to implement saliency computation, decomposed input image into three channels, cut down the computational expense to the lowest level, extracted texture saliency from the different channels respectively, combined them in an innovative way, and then detected the saliency hierarchy. Distinct from previous approaches in the domain, our method based on biological model and had clear physical meaning. Our method could robustly work no matter how complex the input images were.

Original languageEnglish
Title of host publicationMIPPR 2007
Subtitle of host publicationRemote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
DOIs
StatePublished - 2007
Externally publishedYes
EventMIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications - Wuhan, China
Duration: 15 Nov 200717 Nov 2007

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6790
ISSN (Print)0277-786X

Conference

ConferenceMIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications
Country/TerritoryChina
CityWuhan
Period15/11/0717/11/07

Keywords

  • Computational attention
  • Global saliency
  • Image analysis
  • Local saliency
  • Remote sensing
  • Texture saliency
  • Visual attention
  • Visual search

Fingerprint

Dive into the research topics of 'New approach to texture saliency based on intrinsic relationship among texture features'. Together they form a unique fingerprint.

Cite this