One-class classification in multimodal biometrie authentication

Panos Liatsis, Quang Duc Tran

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

1 Scopus citations

Abstract

Class imbalance is a major challenge in biometrie authentication, particularly in the context of two-class classification, i.e., distinguishing between genuine users and impostors. Traditional classifiers assume near-balanced class distributions and as such they do not work well when the samples of one class outnumber those of the other. Indeed, class imbalance is a common problem in multimodal biometrics, where typically impostor samples are in the order of 500:1 compared to those of genuine users. In this work, we present the use of one-class classification to enhance multimodal biometric performance in the presence of class imbalance. We consider well-known one-class classifiers, such as the Gaussian Mixture Model, k-Nearest Neighbour, etc in learning the user-specific and user-independent descriptions for the biometric decision inference. We conclude that the user-specific approach is powerful in overcoming the within-class sub-concepts problem, which commonly occurs in multimodal biometrics due to user variation.

Original languageBritish English
Title of host publication2017 International Conference on Infocom Technologies and Unmanned Systems
Subtitle of host publicationTrends and Future Directions, ICTUS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages37-42
Number of pages6
ISBN (Electronic)9781538605141
DOIs
StatePublished - 7 Feb 2018
Event2017 International Conference on Infocom Technologies and Unmanned Systems, ICTUS 2017 - Dubai, United Arab Emirates
Duration: 18 Dec 201720 Dec 2017

Publication series

Name2017 International Conference on Infocom Technologies and Unmanned Systems: Trends and Future Directions, ICTUS 2017
Volume2018-January

Conference

Conference2017 International Conference on Infocom Technologies and Unmanned Systems, ICTUS 2017
Country/TerritoryUnited Arab Emirates
CityDubai
Period18/12/1720/12/17

Keywords

  • Multimodal biometrics
  • One-class classification
  • User-independent description
  • User-specific description
  • Within-class sub-concepts problem

Fingerprint

Dive into the research topics of 'One-class classification in multimodal biometrie authentication'. Together they form a unique fingerprint.

Cite this