Skip to main navigation Skip to search Skip to main content

Identification model for classifier combinations

  • SUNY Buffalo

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

6 Scopus citations

Abstract

This paper considers combinations of biometric matchers in identification system. We assume that the test template is matched not only against the enrolled template of claimed person identity, but also against few enrolled templates of other persons, and all matching scores are available to the combination algorithm. We present a combination method utilizing the dependencies between these scores and showing better performance than comparable traditional combination method using only matching scores related to the claimed identity.

Original languageEnglish
Title of host publicationBiometrics Symposium, BCC 2006
DOIs
StatePublished - 2006
Event2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, BCC - Baltimore, MD, United States
Duration: Sep 19 2006Sep 21 2006

Publication series

NameBiometrics Symposium, BCC 2006

Conference

Conference2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, BCC
Country/TerritoryUnited States
CityBaltimore, MD
Period09/19/0609/21/06

Fingerprint

Dive into the research topics of 'Identification model for classifier combinations'. Together they form a unique fingerprint.

Cite this