3-D face recognition using curvelet local features

    Research output: Contribution to journalArticle

    38 Citations (Scopus)

    Abstract

    In this letter, we present a robust single modality feature-based algorithm for 3-D face recognition. The proposed algorithm exploits Curvelet transform not only to detect salient points on the face but also to build multi-scale local surface descriptors that can capture highly distinctive rotation/displacement invariant local features around the detected keypoints. This approach is shown to provide robust and accurate recognition under varying illumination conditions and facial expressions. Using the well-known and challenging FRGC v2 dataset, we report a superior performance compared to other algorithms, with a 97.83% verification rate for probes with all facial expressions. © 2013 IEEE.
    Original languageEnglish
    Pages (from-to)172-175
    Number of pages4
    JournalIEEE Signal Processing Letters
    Volume21
    Issue number2
    Early online date13 Dec 2013
    DOIs
    Publication statusPublished - Feb 2014

    Fingerprint

    Curvelet
    Local Features
    Face recognition
    Face Recognition
    3D
    Facial Expression
    Salient point
    Curvelet Transform
    Modality
    Descriptors
    Illumination
    Probe
    Lighting
    Face
    Invariant

    Cite this

    @article{92925d96bbab4370bbd76f1d477a70b7,
    title = "3-D face recognition using curvelet local features",
    abstract = "In this letter, we present a robust single modality feature-based algorithm for 3-D face recognition. The proposed algorithm exploits Curvelet transform not only to detect salient points on the face but also to build multi-scale local surface descriptors that can capture highly distinctive rotation/displacement invariant local features around the detected keypoints. This approach is shown to provide robust and accurate recognition under varying illumination conditions and facial expressions. Using the well-known and challenging FRGC v2 dataset, we report a superior performance compared to other algorithms, with a 97.83{\%} verification rate for probes with all facial expressions. {\circledC} 2013 IEEE.",
    author = "S. Elaiwat and Mohammed Bennamoun and Farid Boussa{\"i}d and Amar El-Sallam",
    year = "2014",
    month = "2",
    doi = "10.1109/LSP.2013.2295119",
    language = "English",
    volume = "21",
    pages = "172--175",
    journal = "IEEE Signal Processing Letters",
    issn = "1070-9908",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    number = "2",

    }

    3-D face recognition using curvelet local features. / Elaiwat, S.; Bennamoun, Mohammed; Boussaïd, Farid; El-Sallam, Amar.

    In: IEEE Signal Processing Letters, Vol. 21, No. 2, 02.2014, p. 172-175.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - 3-D face recognition using curvelet local features

    AU - Elaiwat, S.

    AU - Bennamoun, Mohammed

    AU - Boussaïd, Farid

    AU - El-Sallam, Amar

    PY - 2014/2

    Y1 - 2014/2

    N2 - In this letter, we present a robust single modality feature-based algorithm for 3-D face recognition. The proposed algorithm exploits Curvelet transform not only to detect salient points on the face but also to build multi-scale local surface descriptors that can capture highly distinctive rotation/displacement invariant local features around the detected keypoints. This approach is shown to provide robust and accurate recognition under varying illumination conditions and facial expressions. Using the well-known and challenging FRGC v2 dataset, we report a superior performance compared to other algorithms, with a 97.83% verification rate for probes with all facial expressions. © 2013 IEEE.

    AB - In this letter, we present a robust single modality feature-based algorithm for 3-D face recognition. The proposed algorithm exploits Curvelet transform not only to detect salient points on the face but also to build multi-scale local surface descriptors that can capture highly distinctive rotation/displacement invariant local features around the detected keypoints. This approach is shown to provide robust and accurate recognition under varying illumination conditions and facial expressions. Using the well-known and challenging FRGC v2 dataset, we report a superior performance compared to other algorithms, with a 97.83% verification rate for probes with all facial expressions. © 2013 IEEE.

    U2 - 10.1109/LSP.2013.2295119

    DO - 10.1109/LSP.2013.2295119

    M3 - Article

    VL - 21

    SP - 172

    EP - 175

    JO - IEEE Signal Processing Letters

    JF - IEEE Signal Processing Letters

    SN - 1070-9908

    IS - 2

    ER -