Dynamic best spectral bands selection for face recognition

Hamdi Jamel Bouchech, Sebti Foufou, Mongi Abidi

    Research output: Contribution to conferencePaper

    Abstract

    In this paper, face recognition in uncontrolled illumination conditions is investigated. A twofold contribution is proposed. First, three state-of-art algorithms, namely Multiblock Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS) are evaluated upon the IRIS-M3 face database to study their robustness against a high illumination variation conditions. Second, we propose to use visible multispectral images, provided by the same face database, to enhance the performance of the three mentioned algorithms. To reduce the high data dimensionality introduced by the use of multispectral images, we have designed a system to dynamically select the best spectral bands for each new subject. Our semi-supervised system for best spectral bands selection learn the relation between the recognition performance of each spectral band and its intrinsic quality using techniques of transfer learning and finite mixture of Gaussian for data distribution estimation. The obtained model is function of the image quality, and for each new spectral band, the likelihood ratio test is used to determine if the former belongs to either the set of good spectral bands or bad spectral bands. To the best of our knowledge, this is the first system proposed to dynamically select the best visible spectral bands for face recognition. Our results highlighted further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our subspectral images based approach to increase the accuracy of the studied algorithms by at least 21.66 % upon the proposed database. Finally, our dynamic system has shown a superiority of performance over non-dynamic systems developed for the same face database.

    Original languageEnglish (US)
    DOIs
    StatePublished - Jan 1 2014
    Event2014 48th Annual Conference on Information Sciences and Systems, CISS 2014 - Princeton, NJ, United States
    Duration: Mar 19 2014Mar 21 2014

    Other

    Other2014 48th Annual Conference on Information Sciences and Systems, CISS 2014
    CountryUnited States
    CityPrinceton, NJ
    Period3/19/143/21/14

    Fingerprint

    Face recognition
    Lighting
    Image quality
    Dynamical systems

    Keywords

    • bands selection
    • dynamic
    • Face
    • HGPP
    • LGBPHS
    • MBLBP
    • Mixture of Gaussians
    • multispectral
    • Transfer learning
    • uncontrolled illumination

    ASJC Scopus subject areas

    • Information Systems

    Cite this

    Bouchech, H. J., Foufou, S., & Abidi, M. (2014). Dynamic best spectral bands selection for face recognition. Paper presented at 2014 48th Annual Conference on Information Sciences and Systems, CISS 2014, Princeton, NJ, United States. https://doi.org/10.1109/CISS.2014.6814081

    Dynamic best spectral bands selection for face recognition. / Bouchech, Hamdi Jamel; Foufou, Sebti; Abidi, Mongi.

    2014. Paper presented at 2014 48th Annual Conference on Information Sciences and Systems, CISS 2014, Princeton, NJ, United States.

    Research output: Contribution to conferencePaper

    Bouchech, HJ, Foufou, S & Abidi, M 2014, 'Dynamic best spectral bands selection for face recognition' Paper presented at 2014 48th Annual Conference on Information Sciences and Systems, CISS 2014, Princeton, NJ, United States, 3/19/14 - 3/21/14, . https://doi.org/10.1109/CISS.2014.6814081
    Bouchech HJ, Foufou S, Abidi M. Dynamic best spectral bands selection for face recognition. 2014. Paper presented at 2014 48th Annual Conference on Information Sciences and Systems, CISS 2014, Princeton, NJ, United States. https://doi.org/10.1109/CISS.2014.6814081
    Bouchech, Hamdi Jamel ; Foufou, Sebti ; Abidi, Mongi. / Dynamic best spectral bands selection for face recognition. Paper presented at 2014 48th Annual Conference on Information Sciences and Systems, CISS 2014, Princeton, NJ, United States.
    @conference{11a66977de4846da9215c10d0a8e7157,
    title = "Dynamic best spectral bands selection for face recognition",
    abstract = "In this paper, face recognition in uncontrolled illumination conditions is investigated. A twofold contribution is proposed. First, three state-of-art algorithms, namely Multiblock Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS) are evaluated upon the IRIS-M3 face database to study their robustness against a high illumination variation conditions. Second, we propose to use visible multispectral images, provided by the same face database, to enhance the performance of the three mentioned algorithms. To reduce the high data dimensionality introduced by the use of multispectral images, we have designed a system to dynamically select the best spectral bands for each new subject. Our semi-supervised system for best spectral bands selection learn the relation between the recognition performance of each spectral band and its intrinsic quality using techniques of transfer learning and finite mixture of Gaussian for data distribution estimation. The obtained model is function of the image quality, and for each new spectral band, the likelihood ratio test is used to determine if the former belongs to either the set of good spectral bands or bad spectral bands. To the best of our knowledge, this is the first system proposed to dynamically select the best visible spectral bands for face recognition. Our results highlighted further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our subspectral images based approach to increase the accuracy of the studied algorithms by at least 21.66 {\%} upon the proposed database. Finally, our dynamic system has shown a superiority of performance over non-dynamic systems developed for the same face database.",
    keywords = "bands selection, dynamic, Face, HGPP, LGBPHS, MBLBP, Mixture of Gaussians, multispectral, Transfer learning, uncontrolled illumination",
    author = "Bouchech, {Hamdi Jamel} and Sebti Foufou and Mongi Abidi",
    year = "2014",
    month = "1",
    day = "1",
    doi = "10.1109/CISS.2014.6814081",
    language = "English (US)",
    note = "2014 48th Annual Conference on Information Sciences and Systems, CISS 2014 ; Conference date: 19-03-2014 Through 21-03-2014",

    }

    TY - CONF

    T1 - Dynamic best spectral bands selection for face recognition

    AU - Bouchech, Hamdi Jamel

    AU - Foufou, Sebti

    AU - Abidi, Mongi

    PY - 2014/1/1

    Y1 - 2014/1/1

    N2 - In this paper, face recognition in uncontrolled illumination conditions is investigated. A twofold contribution is proposed. First, three state-of-art algorithms, namely Multiblock Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS) are evaluated upon the IRIS-M3 face database to study their robustness against a high illumination variation conditions. Second, we propose to use visible multispectral images, provided by the same face database, to enhance the performance of the three mentioned algorithms. To reduce the high data dimensionality introduced by the use of multispectral images, we have designed a system to dynamically select the best spectral bands for each new subject. Our semi-supervised system for best spectral bands selection learn the relation between the recognition performance of each spectral band and its intrinsic quality using techniques of transfer learning and finite mixture of Gaussian for data distribution estimation. The obtained model is function of the image quality, and for each new spectral band, the likelihood ratio test is used to determine if the former belongs to either the set of good spectral bands or bad spectral bands. To the best of our knowledge, this is the first system proposed to dynamically select the best visible spectral bands for face recognition. Our results highlighted further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our subspectral images based approach to increase the accuracy of the studied algorithms by at least 21.66 % upon the proposed database. Finally, our dynamic system has shown a superiority of performance over non-dynamic systems developed for the same face database.

    AB - In this paper, face recognition in uncontrolled illumination conditions is investigated. A twofold contribution is proposed. First, three state-of-art algorithms, namely Multiblock Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS) are evaluated upon the IRIS-M3 face database to study their robustness against a high illumination variation conditions. Second, we propose to use visible multispectral images, provided by the same face database, to enhance the performance of the three mentioned algorithms. To reduce the high data dimensionality introduced by the use of multispectral images, we have designed a system to dynamically select the best spectral bands for each new subject. Our semi-supervised system for best spectral bands selection learn the relation between the recognition performance of each spectral band and its intrinsic quality using techniques of transfer learning and finite mixture of Gaussian for data distribution estimation. The obtained model is function of the image quality, and for each new spectral band, the likelihood ratio test is used to determine if the former belongs to either the set of good spectral bands or bad spectral bands. To the best of our knowledge, this is the first system proposed to dynamically select the best visible spectral bands for face recognition. Our results highlighted further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our subspectral images based approach to increase the accuracy of the studied algorithms by at least 21.66 % upon the proposed database. Finally, our dynamic system has shown a superiority of performance over non-dynamic systems developed for the same face database.

    KW - bands selection

    KW - dynamic

    KW - Face

    KW - HGPP

    KW - LGBPHS

    KW - MBLBP

    KW - Mixture of Gaussians

    KW - multispectral

    KW - Transfer learning

    KW - uncontrolled illumination

    UR - http://www.scopus.com/inward/record.url?scp=84901459452&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84901459452&partnerID=8YFLogxK

    U2 - 10.1109/CISS.2014.6814081

    DO - 10.1109/CISS.2014.6814081

    M3 - Paper

    ER -