Reference point-based SIFT feature matching

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

Abstract

Aiming to solve the high computational and time consuming problem in SIFT feature matching, this paper presents an improved SIFT feature matching algorithm based on reference point. The algorithm starts from selecting a suitable reference point in the feature descriptor space when SIFT features are extracted. In the feature matching stage, this paper uses the Euclidean distance between descriptor vectors of the feature point to be matched and the reference point to make a fast filtration which removes most of the features that could not be matched. For the remaining SIFT features, Best-bin-first (BBF) algrithm is utilized to obtain precise matches. Experimental results demonstrate that the proposed matching algorithm achieves good effectiveness in image matching, and takes only about 60 percent of the time that the traditional matching algorithm takes.

Original languageEnglish
Title of host publicationVehicle, Mechatronics and Information Technologies II
PublisherTrans Tech Publications
Pages2670-2673
Number of pages4
ISBN (Print)9783038350606
DOIs
StatePublished - 2014
EventInternational Conference on Vehicle and Mechanical Engineering and Information Technology, VMEIT 2014 - Beijing, China
Duration: 19 Feb 201420 Feb 2014

Publication series

NameApplied Mechanics and Materials
Volume543-547
ISSN (Print)1660-9336
ISSN (Electronic)1662-7482

Conference

ConferenceInternational Conference on Vehicle and Mechanical Engineering and Information Technology, VMEIT 2014
Country/TerritoryChina
CityBeijing
Period19/02/1420/02/14

Keywords

  • Feature matching
  • Reference distance
  • Reference point
  • SIFT

Fingerprint

Dive into the research topics of 'Reference point-based SIFT feature matching'. Together they form a unique fingerprint.

Cite this