Salient feature point detection for image matching

Jun Liang, Yanning Zhang, Steve Maybank, Xiuwei Zhang

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

3 Scopus citations

Abstract

A saliency based feature point detector is proposed, based on a decision-theoretic formulation of saliency. The saliency of an image region is defined to be the Kullback-Leibler (K-L) divergence between the conditional probability density function (pdf) for the matching regions and a background pdf. These pdfs are modeled by elliptically symmetric distributions (ESDs). We improve the ESD models by reducing the number of parameters without any significant degradation in the modeling of image regions. Experimental results from the Middlebury stereo dataset show that 1) the accuracy of estimates of saliency is increased and 2) fewer computations are required. It is also verified that the saliency of a region can be viewed as a measurement of how suitable the region is for image matching. In the Middlebury stereo dataset, salient regions are dense, and a promising matching rate is achieved.

Original languageEnglish
Title of host publication2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages485-489
Number of pages5
ISBN (Electronic)9781479954032
DOIs
StatePublished - 3 Sep 2014
Event2nd IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Xi'an, China
Duration: 9 Jul 201413 Jul 2014

Publication series

Name2014 IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014 - Proceedings

Conference

Conference2nd IEEE China Summit and International Conference on Signal and Information Processing, IEEE ChinaSIP 2014
Country/TerritoryChina
CityXi'an
Period9/07/1413/07/14

Keywords

  • Dense image matching
  • K-L divergence
  • log-normal distribution
  • salience
  • stereo matching

Fingerprint

Dive into the research topics of 'Salient feature point detection for image matching'. Together they form a unique fingerprint.

Cite this