Biometric identification using motion history images of a speaker's lip movements

Alfredo Grunwald de la Cuesta, Jianguo Zhang, Paul Miller

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

    16 Citations (Scopus)

    Abstract

    This paper describes a new simple, but effective, approach to speaker verification using video sequences of lip movements. We use motion history images (MHI) to provide a biometric template of a spoken word for each speaker. Class-dependent correlation filters are then created by a weighted optimization of training MHI samples. Feature extraction is performed by correlating a test MHI against each correlation filter. A Bayesian classifier is deployed for classification. We carry out an extensive performance evaluation of our approach with respect to the number of training samples and different words. Results clearly show the efficacy of our method.
    Original languageEnglish
    Title of host publicationProceedings 2008 International Machine Vision and Image Processing Conference
    Subtitle of host publicationIMVIP 2008
    EditorsBryan Scotney, Philip Morrow
    Place of PublicationLos Alamitos, Calif.
    PublisherIEEE
    Pages83-88
    Number of pages6
    ISBN (Print)9780769533322
    DOIs
    Publication statusPublished - 2008
    EventIMVIP 2008 International Machine Vision and Image Processing Conference - University of Ulster, Portrush, Coleraine, Ireland
    Duration: 3 Sept 20085 Sept 2008
    http://www.compeng.ulster.ac.uk/events/imvip2008/

    Conference

    ConferenceIMVIP 2008 International Machine Vision and Image Processing Conference
    Abbreviated titleIMVIP 2008
    Country/TerritoryIreland
    CityPortrush, Coleraine
    Period3/09/085/09/08
    Internet address

    Fingerprint

    Dive into the research topics of 'Biometric identification using motion history images of a speaker's lip movements'. Together they form a unique fingerprint.

    Cite this