Spatially optimized data-level fusion of texture and shape for face recognition

    Research output: Contribution to journalArticle

    40 Citations (Scopus)

    Abstract

    Data-level fusion is believed to have the potential for enhancing human face recognition. However, due to a number of challenges, current techniques have failed to achieve its full potential. We propose spatially optimized data/pixel-level fusion of 3-D shape and texture for face recognition. Fusion functions are objectively optimized to model expression and illumination variations in linear subspaces for invariant face recognition. Parameters of adjacent functions are constrained to smoothly vary for effective numerical regularization. In addition to spatial optimization, multiple nonlinear fusion models are combined to enhance their learning capabilities. Experiments on the FRGC v2 data set show that spatial optimization, higher order fusion functions, and the combination of multiple such functions systematically improve performance, which is, for the first time, higher than score-level fusion in a similar experimental setup.
    Original languageEnglish
    Pages (from-to)859-872
    JournalIEEE Transactions on Image Processing
    Volume21
    Issue number2
    DOIs
    Publication statusPublished - 11 Aug 2012

    Fingerprint

    Face recognition
    Fusion reactions
    Textures
    Lighting
    Pixels
    Experiments

    Cite this

    @article{dfaee63d9b0848ad87c9f25f5604bdf2,
    title = "Spatially optimized data-level fusion of texture and shape for face recognition",
    abstract = "Data-level fusion is believed to have the potential for enhancing human face recognition. However, due to a number of challenges, current techniques have failed to achieve its full potential. We propose spatially optimized data/pixel-level fusion of 3-D shape and texture for face recognition. Fusion functions are objectively optimized to model expression and illumination variations in linear subspaces for invariant face recognition. Parameters of adjacent functions are constrained to smoothly vary for effective numerical regularization. In addition to spatial optimization, multiple nonlinear fusion models are combined to enhance their learning capabilities. Experiments on the FRGC v2 data set show that spatial optimization, higher order fusion functions, and the combination of multiple such functions systematically improve performance, which is, for the first time, higher than score-level fusion in a similar experimental setup.",
    author = "F.R. Al-Osaimi and Mohammed Bennamoun and Ajmal Mian",
    year = "2012",
    month = "8",
    day = "11",
    doi = "10.1109/TIP.2011.2165218",
    language = "English",
    volume = "21",
    pages = "859--872",
    journal = "IEEE Transactions on Image Processing",
    issn = "1057-7149",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    number = "2",

    }

    Spatially optimized data-level fusion of texture and shape for face recognition. / Al-Osaimi, F.R.; Bennamoun, Mohammed; Mian, Ajmal.

    In: IEEE Transactions on Image Processing, Vol. 21, No. 2, 11.08.2012, p. 859-872.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Spatially optimized data-level fusion of texture and shape for face recognition

    AU - Al-Osaimi, F.R.

    AU - Bennamoun, Mohammed

    AU - Mian, Ajmal

    PY - 2012/8/11

    Y1 - 2012/8/11

    N2 - Data-level fusion is believed to have the potential for enhancing human face recognition. However, due to a number of challenges, current techniques have failed to achieve its full potential. We propose spatially optimized data/pixel-level fusion of 3-D shape and texture for face recognition. Fusion functions are objectively optimized to model expression and illumination variations in linear subspaces for invariant face recognition. Parameters of adjacent functions are constrained to smoothly vary for effective numerical regularization. In addition to spatial optimization, multiple nonlinear fusion models are combined to enhance their learning capabilities. Experiments on the FRGC v2 data set show that spatial optimization, higher order fusion functions, and the combination of multiple such functions systematically improve performance, which is, for the first time, higher than score-level fusion in a similar experimental setup.

    AB - Data-level fusion is believed to have the potential for enhancing human face recognition. However, due to a number of challenges, current techniques have failed to achieve its full potential. We propose spatially optimized data/pixel-level fusion of 3-D shape and texture for face recognition. Fusion functions are objectively optimized to model expression and illumination variations in linear subspaces for invariant face recognition. Parameters of adjacent functions are constrained to smoothly vary for effective numerical regularization. In addition to spatial optimization, multiple nonlinear fusion models are combined to enhance their learning capabilities. Experiments on the FRGC v2 data set show that spatial optimization, higher order fusion functions, and the combination of multiple such functions systematically improve performance, which is, for the first time, higher than score-level fusion in a similar experimental setup.

    U2 - 10.1109/TIP.2011.2165218

    DO - 10.1109/TIP.2011.2165218

    M3 - Article

    VL - 21

    SP - 859

    EP - 872

    JO - IEEE Transactions on Image Processing

    JF - IEEE Transactions on Image Processing

    SN - 1057-7149

    IS - 2

    ER -