Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication

C. Wright, D. Stewart, P. Miller, F. Campbell-West

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Citations (Scopus)
281 Downloads (Pure)

Abstract

This paper investigated using lip movements as a behavioural biometric for person authentication. The system was trained, evaluated and tested using the XM2VTS dataset, following the Lausanne Protocol configuration II. Features were selected from the DCT coefficients of the greyscale lip image. This paper investigated the number of DCT coefficients selected, the selection process, and static and dynamic feature combinations. Using a Gaussian Mixture Model - Universal Background Model framework an Equal Error Rate of 2.20% was achieved during evaluation and on an unseen test set a False Acceptance Rate of 1.7% and False Rejection Rate of 3.0% was achieved. This compares favourably with face authentication results on the same dataset whilst not being susceptible to spoofing attacks.
Original languageEnglish
Title of host publicationIrish Machine Vision & Image Processing Conference Proceedings 2015
EditorsRozenn Dahyot, Gerard Lacey, Kenneth Dawson-Howe, François Pitié, David Moloney
PublisherIrish Pattern Recognition & Classification Society
Pages11-18
Number of pages8
ISBN (Print)9780993420702
Publication statusPublished - 2015
EventIrish Machine Vision and Image Processing Conference 2015 - Trinity College, Dublin, Ireland
Duration: 26 Aug 201528 Aug 2015

Conference

ConferenceIrish Machine Vision and Image Processing Conference 2015
Country/TerritoryIreland
CityDublin
Period26/08/201528/08/2015

Bibliographical note

Winner of Best Student Paper Award

Keywords

  • Authentication
  • Biometrics
  • DCT

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication'. Together they form a unique fingerprint.

Cite this