Skip to main navigation Skip to search Skip to main content

Verifying fingerprint match by local correlation methods

  • SUNY Buffalo

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

7 Scopus citations

Abstract

Most fingerprint matching algorithms are based on finding correspondences between minutiae in two fingerprints. In this paper we present a modification of minutiae matching method, which utilizes correlation scores between the local neighborhood areas of corresponding minutiae pairs and the edges that connect neighboring matched minutiae pairs. Minutiae based matching approach considers the overall minutiae distribution pattern between the two fingerprints. Neighborhood correlation score represents the local similarity between the matched pair of minutiae. Edge correlation score gives the resemblance of areas that in between the two corresponding minutiae pairs. Thus, both the global minutiae distribution structure and the local matching similarity between the two fingerprints are considered for final decision. The described matching approach has been tested on FVC2002's DB1 and DB3 database. The experimental results confirm the effectiveness of combining matching scores of different origin - minutia matching score and local correlation matching scores.

Original languageEnglish
Title of host publicationIEEE Conference on Biometrics
Subtitle of host publicationTheory, Applications and Systems, BTAS'07
DOIs
StatePublished - 2007
Event1st IEEE International Conference on Biometrics: Theory, Applications, and Systems, BTAS '07 - Crystal City, VA, United States
Duration: Sep 27 2007Sep 29 2007

Publication series

NameIEEE Conference on Biometrics: Theory, Applications and Systems, BTAS'07

Conference

Conference1st IEEE International Conference on Biometrics: Theory, Applications, and Systems, BTAS '07
Country/TerritoryUnited States
CityCrystal City, VA
Period09/27/0709/29/07

Fingerprint

Dive into the research topics of 'Verifying fingerprint match by local correlation methods'. Together they form a unique fingerprint.

Cite this