Investigating Feature Level Fusion for Checking Liveness in Face-Voice Authentication

Girija Chetty, Michael Wagner

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    9 Citations (Scopus)
    3 Downloads (Pure)

    Abstract

    In this paper we propose a feature level fusion approach for checking liveness in face-voice person authentication. Liveness verification experiments conducted on two audiovisual databases, VidTIMIT and UCBN, show that feature-level fusion is indeed a powerful technique for checking liveness in systems that are vulnerable to replay attacks, as it preserves synchronisation between closely coupled modalities, such as voice and face, through various stages of authentication. An improvement in error rate of the order of 25-40% is achieved for replay attack experiments by using feature level fusion of acoustic and visual feature vectors from lip region as compared to classical late fusion approach.
    Original languageEnglish
    Title of host publicationProceedings of the Eighth International Symposium on Signal Processing and Applications
    Place of PublicationPiscataway, New Jersey, USA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages66-69
    Number of pages4
    ISBN (Print)0-7803-9244-2
    DOIs
    Publication statusPublished - 2005
    EventISSPA-2005 - Sydney, Australia
    Duration: 28 Aug 200531 Aug 2005

    Conference

    ConferenceISSPA-2005
    CountryAustralia
    CitySydney
    Period28/08/0531/08/05

      Fingerprint

    Cite this

    Chetty, G., & Wagner, M. (2005). Investigating Feature Level Fusion for Checking Liveness in Face-Voice Authentication. In Proceedings of the Eighth International Symposium on Signal Processing and Applications (pp. 66-69). Piscataway, New Jersey, USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ISSPA.2005.1580197