Audio-Visual Biometric Recognition Via Joint Sparse Representations

    Research output: Chapter in Book/Conference paperConference paper

    1 Citation (Scopus)
    12 Downloads (Pure)

    Abstract

    In this paper we present a novel audio-visual (AV) person identification system based on joint sparse representation. Video features used were vectorized raw pixel values, while ivectors were used as the audio features. Classification is performed by solving the joint sparsity optimization problem, and fusion is carried out by using the quality (confidence) assigned to each matcher. Our experimental results on the challenging MOBIO database using 100 subjects show that the system based on joint sparse representation outperforms the system based on separate sparse representations for each modality. Furthermore, we show that our newly introduced quality measure improves the system’s performance, when compared to conventionally used quality measures for sparse representation - based systems.
    Original languageEnglish
    Title of host publicationProceedings of the 23rd International Conference on Pattern Recognition (ICPR)
    EditorsEduardo Bayro-Corrochano
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages3026-3030
    ISBN (Print)9781509048465
    Publication statusPublished - 2016
    Event2016 23rd International Conference on Pattern Recognition (ICPR) - Cancun, Mexico
    Duration: 4 Dec 20168 Dec 2016

    Conference

    Conference2016 23rd International Conference on Pattern Recognition (ICPR)
    CountryMexico
    CityCancun
    Period4/12/168/12/16

    Fingerprint

    Biometrics
    Identification (control systems)
    Fusion reactions
    Pixels

    Cite this

    Primorac, R., Togneri, R., Bennamoun, M., & Sohel, F. (2016). Audio-Visual Biometric Recognition Via Joint Sparse Representations. In E. Bayro-Corrochano (Ed.), Proceedings of the 23rd International Conference on Pattern Recognition (ICPR) (pp. 3026-3030). USA: IEEE, Institute of Electrical and Electronics Engineers.
    Primorac, Rudi ; Togneri, Roberto ; Bennamoun, Mohammed ; Sohel, Ferdous. / Audio-Visual Biometric Recognition Via Joint Sparse Representations. Proceedings of the 23rd International Conference on Pattern Recognition (ICPR). editor / Eduardo Bayro-Corrochano. USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 3026-3030
    @inproceedings{42afa9ae19434a62a5ac5d224825171d,
    title = "Audio-Visual Biometric Recognition Via Joint Sparse Representations",
    abstract = "In this paper we present a novel audio-visual (AV) person identification system based on joint sparse representation. Video features used were vectorized raw pixel values, while ivectors were used as the audio features. Classification is performed by solving the joint sparsity optimization problem, and fusion is carried out by using the quality (confidence) assigned to each matcher. Our experimental results on the challenging MOBIO database using 100 subjects show that the system based on joint sparse representation outperforms the system based on separate sparse representations for each modality. Furthermore, we show that our newly introduced quality measure improves the system’s performance, when compared to conventionally used quality measures for sparse representation - based systems.",
    author = "Rudi Primorac and Roberto Togneri and Mohammed Bennamoun and Ferdous Sohel",
    year = "2016",
    language = "English",
    isbn = "9781509048465",
    pages = "3026--3030",
    editor = "Eduardo Bayro-Corrochano",
    booktitle = "Proceedings of the 23rd International Conference on Pattern Recognition (ICPR)",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Primorac, R, Togneri, R, Bennamoun, M & Sohel, F 2016, Audio-Visual Biometric Recognition Via Joint Sparse Representations. in E Bayro-Corrochano (ed.), Proceedings of the 23rd International Conference on Pattern Recognition (ICPR). IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 3026-3030, 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 4/12/16.

    Audio-Visual Biometric Recognition Via Joint Sparse Representations. / Primorac, Rudi; Togneri, Roberto; Bennamoun, Mohammed; Sohel, Ferdous.

    Proceedings of the 23rd International Conference on Pattern Recognition (ICPR). ed. / Eduardo Bayro-Corrochano. USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 3026-3030.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - Audio-Visual Biometric Recognition Via Joint Sparse Representations

    AU - Primorac, Rudi

    AU - Togneri, Roberto

    AU - Bennamoun, Mohammed

    AU - Sohel, Ferdous

    PY - 2016

    Y1 - 2016

    N2 - In this paper we present a novel audio-visual (AV) person identification system based on joint sparse representation. Video features used were vectorized raw pixel values, while ivectors were used as the audio features. Classification is performed by solving the joint sparsity optimization problem, and fusion is carried out by using the quality (confidence) assigned to each matcher. Our experimental results on the challenging MOBIO database using 100 subjects show that the system based on joint sparse representation outperforms the system based on separate sparse representations for each modality. Furthermore, we show that our newly introduced quality measure improves the system’s performance, when compared to conventionally used quality measures for sparse representation - based systems.

    AB - In this paper we present a novel audio-visual (AV) person identification system based on joint sparse representation. Video features used were vectorized raw pixel values, while ivectors were used as the audio features. Classification is performed by solving the joint sparsity optimization problem, and fusion is carried out by using the quality (confidence) assigned to each matcher. Our experimental results on the challenging MOBIO database using 100 subjects show that the system based on joint sparse representation outperforms the system based on separate sparse representations for each modality. Furthermore, we show that our newly introduced quality measure improves the system’s performance, when compared to conventionally used quality measures for sparse representation - based systems.

    M3 - Conference paper

    SN - 9781509048465

    SP - 3026

    EP - 3030

    BT - Proceedings of the 23rd International Conference on Pattern Recognition (ICPR)

    A2 - Bayro-Corrochano, Eduardo

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - USA

    ER -

    Primorac R, Togneri R, Bennamoun M, Sohel F. Audio-Visual Biometric Recognition Via Joint Sparse Representations. In Bayro-Corrochano E, editor, Proceedings of the 23rd International Conference on Pattern Recognition (ICPR). USA: IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 3026-3030