Combining color and geometry for local image matching

Baptiste Mazin, Julie Delon, Yann Gousseau

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

Abstract

This paper introduces a generic way to incorporate color information into local, SIFT-like descriptors, in view of image matching. First, a new color descriptor, relying on local hue histograms, is introduced. Second, we describe a procedure permitting the automatic setting of matching parameters when matching images using both geometric and color information. Experiments on a color image database show that our SIFT+Hue combination performs significantly better than classical color descriptors.

Original languageEnglish
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages2677-2680
Number of pages4
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference21st International Conference on Pattern Recognition, ICPR 2012
Country/TerritoryJapan
CityTsukuba
Period11/11/1215/11/12

Fingerprint

Dive into the research topics of 'Combining color and geometry for local image matching'. Together they form a unique fingerprint.

Cite this