Saliency detection via combining global shape and local cue estimation

Qiang Qi, Muwei Jian, Yikang Yin, Junyu Dong, Wenyin Zhang, Hui Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

284 Downloads (Pure)

Abstract

Recently, saliency detection has become a hot issue in computer vision. In this paper, a novel framework for image saliency detection is introduced by modeling global shape and local cue estimation simultaneously. Firstly, Quaternionic Distance Based Weber Descriptor (QDWD), which was initially designed for detecting outliers in color images, is used to model the salient object shape in an image. Secondly, we detect local saliency based on the reconstruction error by using a locality-constrained linear coding algorithm. Finally, by integrating global shape with local cue, a reliable saliency map can be computed and estimated. Experimental results, based on two widely used and openly available databases, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency detection algorithms.
Original languageEnglish
Title of host publicationIntelligence Science and Big Data Engineering
EditorsY. Sun, L. Zhang, J. Yang, H. Huang
PublisherSpringer
Pages325-334
Number of pages10
ISBN (Electronic)978-3319677774
ISBN (Print)978-3319677767
DOIs
Publication statusPublished - 14 Sept 2017
EventIScIDE 2017: International Conference on Intelligence Science and Big Data Engineering - Dalian, China
Duration: 23 Sept 201724 Sept 2017

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10559
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceIScIDE 2017: International Conference on Intelligence Science and Big Data Engineering
Country/TerritoryChina
CityDalian
Period23/09/1724/09/17

Keywords

  • saliency detection
  • QDWD
  • locality-constrained linear coding
  • local cue

Fingerprint

Dive into the research topics of 'Saliency detection via combining global shape and local cue estimation'. Together they form a unique fingerprint.

Cite this