Is spectral reflectance of the face a reliable biometric?

M. Uzair, Arif Mahmood, Faisal Shafait, C. Nansen, Ajmal Mian

    Research output: Contribution to journalArticle

    16 Citations (Scopus)

    Abstract

    Over a decade ago, Pan et al. [IEEE TPAMI 25, 1552 (2003)] performed face recognition using only the spectral reflectance of the face at six points and reported around 95% recognition rate. Since their database is private, no one has been able to replicate these results. Moreover, due to the unavailability of public datasets, there has been no detailed study in the literature on the viability of facial spectral reflectance for person identification. In this study, we introduce a new public database of facial spectral reflectance profiles measured with a high precision spectrometer. For each of the 40 subjects, spectral reflectance was measured at the same six points as Pan et al. [IEEE TPAMI 25, 1552 (2003)] in multiple sessions and with time lapse. Furthermore, we sample the facial spectral reflectance from two public hyperspectral face image datasets and analyzed the data using state of the art face classification techniques. The best performing classifier achieved the maximum rank-1 identification rate of 53.8%. We conclude that facial spectral reflectance alone is not a reliable biometric for unconstrained face recognition.
    Original languageEnglish
    Pages (from-to)15160-15173
    JournalOptics Express
    Volume23
    Issue number12
    DOIs
    Publication statusPublished - 2015

    Fingerprint

    biometrics
    spectral reflectance
    classifiers
    viability
    spectrometers
    profiles

    Cite this

    Uzair, M., Mahmood, A., Shafait, F., Nansen, C., & Mian, A. (2015). Is spectral reflectance of the face a reliable biometric? Optics Express, 23(12), 15160-15173. https://doi.org/10.1364/OE.23.015160
    Uzair, M. ; Mahmood, Arif ; Shafait, Faisal ; Nansen, C. ; Mian, Ajmal. / Is spectral reflectance of the face a reliable biometric?. In: Optics Express. 2015 ; Vol. 23, No. 12. pp. 15160-15173.
    @article{e0265fbe0d6d4b108214ee022fff6a06,
    title = "Is spectral reflectance of the face a reliable biometric?",
    abstract = "Over a decade ago, Pan et al. [IEEE TPAMI 25, 1552 (2003)] performed face recognition using only the spectral reflectance of the face at six points and reported around 95{\%} recognition rate. Since their database is private, no one has been able to replicate these results. Moreover, due to the unavailability of public datasets, there has been no detailed study in the literature on the viability of facial spectral reflectance for person identification. In this study, we introduce a new public database of facial spectral reflectance profiles measured with a high precision spectrometer. For each of the 40 subjects, spectral reflectance was measured at the same six points as Pan et al. [IEEE TPAMI 25, 1552 (2003)] in multiple sessions and with time lapse. Furthermore, we sample the facial spectral reflectance from two public hyperspectral face image datasets and analyzed the data using state of the art face classification techniques. The best performing classifier achieved the maximum rank-1 identification rate of 53.8{\%}. We conclude that facial spectral reflectance alone is not a reliable biometric for unconstrained face recognition.",
    author = "M. Uzair and Arif Mahmood and Faisal Shafait and C. Nansen and Ajmal Mian",
    year = "2015",
    doi = "10.1364/OE.23.015160",
    language = "English",
    volume = "23",
    pages = "15160--15173",
    journal = "Optics Express",
    issn = "1094-4087",
    publisher = "Optical Soc Amer",
    number = "12",

    }

    Uzair, M, Mahmood, A, Shafait, F, Nansen, C & Mian, A 2015, 'Is spectral reflectance of the face a reliable biometric?' Optics Express, vol. 23, no. 12, pp. 15160-15173. https://doi.org/10.1364/OE.23.015160

    Is spectral reflectance of the face a reliable biometric? / Uzair, M.; Mahmood, Arif; Shafait, Faisal; Nansen, C.; Mian, Ajmal.

    In: Optics Express, Vol. 23, No. 12, 2015, p. 15160-15173.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Is spectral reflectance of the face a reliable biometric?

    AU - Uzair, M.

    AU - Mahmood, Arif

    AU - Shafait, Faisal

    AU - Nansen, C.

    AU - Mian, Ajmal

    PY - 2015

    Y1 - 2015

    N2 - Over a decade ago, Pan et al. [IEEE TPAMI 25, 1552 (2003)] performed face recognition using only the spectral reflectance of the face at six points and reported around 95% recognition rate. Since their database is private, no one has been able to replicate these results. Moreover, due to the unavailability of public datasets, there has been no detailed study in the literature on the viability of facial spectral reflectance for person identification. In this study, we introduce a new public database of facial spectral reflectance profiles measured with a high precision spectrometer. For each of the 40 subjects, spectral reflectance was measured at the same six points as Pan et al. [IEEE TPAMI 25, 1552 (2003)] in multiple sessions and with time lapse. Furthermore, we sample the facial spectral reflectance from two public hyperspectral face image datasets and analyzed the data using state of the art face classification techniques. The best performing classifier achieved the maximum rank-1 identification rate of 53.8%. We conclude that facial spectral reflectance alone is not a reliable biometric for unconstrained face recognition.

    AB - Over a decade ago, Pan et al. [IEEE TPAMI 25, 1552 (2003)] performed face recognition using only the spectral reflectance of the face at six points and reported around 95% recognition rate. Since their database is private, no one has been able to replicate these results. Moreover, due to the unavailability of public datasets, there has been no detailed study in the literature on the viability of facial spectral reflectance for person identification. In this study, we introduce a new public database of facial spectral reflectance profiles measured with a high precision spectrometer. For each of the 40 subjects, spectral reflectance was measured at the same six points as Pan et al. [IEEE TPAMI 25, 1552 (2003)] in multiple sessions and with time lapse. Furthermore, we sample the facial spectral reflectance from two public hyperspectral face image datasets and analyzed the data using state of the art face classification techniques. The best performing classifier achieved the maximum rank-1 identification rate of 53.8%. We conclude that facial spectral reflectance alone is not a reliable biometric for unconstrained face recognition.

    U2 - 10.1364/OE.23.015160

    DO - 10.1364/OE.23.015160

    M3 - Article

    VL - 23

    SP - 15160

    EP - 15173

    JO - Optics Express

    JF - Optics Express

    SN - 1094-4087

    IS - 12

    ER -