Skip to main navigation Skip to search Skip to main content

A saliency detection approach to combine LSK and color for color image

  • Xin He*
  • , Huiyun Jing
  • , Qi Han
  • , Xiamu Niu
  • *Corresponding author for this work
  • Harbin Institute of Technology

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

Abstract

Visual saliency plays an important role in biological vision. This paper proposes a novel feature-based approach of visual saliency detection for natural color images. The saliency for each pixel is determined by two features: the structure information and the color information, which represent local information of pixels. The structure information is represented by local steering kernel and the color information is represented by color values of local region around each pixel. We compare our method with the current state-of-the-art models on natural color images. Experiments on human visual fixation data and psychological patterns demonstrate that our method performs competitively for visual saliency detection task.

Original languageEnglish
Title of host publicationProceedings - 7th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2011
Pages129-132
Number of pages4
DOIs
StatePublished - 2011
Event7th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2011 - Dalian, China
Duration: 14 Oct 201116 Oct 2011

Publication series

NameProceedings - 7th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2011

Conference

Conference7th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2011
Country/TerritoryChina
CityDalian
Period14/10/1116/10/11

Keywords

  • local color feature
  • local steering kernel (LSK)
  • saliency detection
  • visual attention

Fingerprint

Dive into the research topics of 'A saliency detection approach to combine LSK and color for color image'. Together they form a unique fingerprint.

Cite this