A comparative study of best spectral bands selection systems for face recognition

Hamdi Bouchech, Sebti Foufou

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Multispectral images (MI) have shown promising capabilities to solve problems resulting from high illumination variation in face recognition. However, the use of MI, with the huge number of captured spectral bands for each subject, is impractical unless a system for best spectral bands selection (BSBS) is used. In this work, first we give an up to date overview of the existing BSBS techniques proposed for face recognition. We aim to highlight the imporatnce of this component of MI based systems. The reviewed techniques are then experimented using the multispectral face database IRIS - M3 to compare their performances. To the best of our knowledge this is the first study that reviews and compares existing techniques for BSBS. The Obtained results emphasized the importance of setting up techniques for BSBS with MI based systems as well as the need for new techniques that investigate better the increasing speed of image processing tools.

    Original languageEnglish (US)
    Title of host publication2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014
    PublisherIEEE Computer Society
    Pages609-613
    Number of pages5
    Volume2014
    ISBN (Electronic)9781479971008
    DOIs
    StatePublished - Jan 1 2014
    Event2014 11th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2014 - Doha, Qatar
    Duration: Nov 10 2014Nov 13 2014

    Other

    Other2014 11th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2014
    CountryQatar
    CityDoha
    Period11/10/1411/13/14

    Fingerprint

    Face recognition
    Image processing
    Lighting

    Keywords

    • Best Spectral Bands Selection
    • IRIS - M
    • Multispectral images
    • review

    ASJC Scopus subject areas

    • Computer Networks and Communications
    • Computer Science Applications
    • Hardware and Architecture
    • Signal Processing
    • Control and Systems Engineering
    • Electrical and Electronic Engineering

    Cite this

    Bouchech, H., & Foufou, S. (2014). A comparative study of best spectral bands selection systems for face recognition. In 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014 (Vol. 2014, pp. 609-613). [7073255] IEEE Computer Society. https://doi.org/10.1109/AICCSA.2014.7073255

    A comparative study of best spectral bands selection systems for face recognition. / Bouchech, Hamdi; Foufou, Sebti.

    2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014. Vol. 2014 IEEE Computer Society, 2014. p. 609-613 7073255.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Bouchech, H & Foufou, S 2014, A comparative study of best spectral bands selection systems for face recognition. in 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014. vol. 2014, 7073255, IEEE Computer Society, pp. 609-613, 2014 11th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2014, Doha, Qatar, 11/10/14. https://doi.org/10.1109/AICCSA.2014.7073255
    Bouchech H, Foufou S. A comparative study of best spectral bands selection systems for face recognition. In 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014. Vol. 2014. IEEE Computer Society. 2014. p. 609-613. 7073255 https://doi.org/10.1109/AICCSA.2014.7073255
    Bouchech, Hamdi ; Foufou, Sebti. / A comparative study of best spectral bands selection systems for face recognition. 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014. Vol. 2014 IEEE Computer Society, 2014. pp. 609-613
    @inproceedings{24e02d56b6474a92891138c592590886,
    title = "A comparative study of best spectral bands selection systems for face recognition",
    abstract = "Multispectral images (MI) have shown promising capabilities to solve problems resulting from high illumination variation in face recognition. However, the use of MI, with the huge number of captured spectral bands for each subject, is impractical unless a system for best spectral bands selection (BSBS) is used. In this work, first we give an up to date overview of the existing BSBS techniques proposed for face recognition. We aim to highlight the imporatnce of this component of MI based systems. The reviewed techniques are then experimented using the multispectral face database IRIS - M3 to compare their performances. To the best of our knowledge this is the first study that reviews and compares existing techniques for BSBS. The Obtained results emphasized the importance of setting up techniques for BSBS with MI based systems as well as the need for new techniques that investigate better the increasing speed of image processing tools.",
    keywords = "Best Spectral Bands Selection, IRIS - M, Multispectral images, review",
    author = "Hamdi Bouchech and Sebti Foufou",
    year = "2014",
    month = "1",
    day = "1",
    doi = "10.1109/AICCSA.2014.7073255",
    language = "English (US)",
    volume = "2014",
    pages = "609--613",
    booktitle = "2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - A comparative study of best spectral bands selection systems for face recognition

    AU - Bouchech, Hamdi

    AU - Foufou, Sebti

    PY - 2014/1/1

    Y1 - 2014/1/1

    N2 - Multispectral images (MI) have shown promising capabilities to solve problems resulting from high illumination variation in face recognition. However, the use of MI, with the huge number of captured spectral bands for each subject, is impractical unless a system for best spectral bands selection (BSBS) is used. In this work, first we give an up to date overview of the existing BSBS techniques proposed for face recognition. We aim to highlight the imporatnce of this component of MI based systems. The reviewed techniques are then experimented using the multispectral face database IRIS - M3 to compare their performances. To the best of our knowledge this is the first study that reviews and compares existing techniques for BSBS. The Obtained results emphasized the importance of setting up techniques for BSBS with MI based systems as well as the need for new techniques that investigate better the increasing speed of image processing tools.

    AB - Multispectral images (MI) have shown promising capabilities to solve problems resulting from high illumination variation in face recognition. However, the use of MI, with the huge number of captured spectral bands for each subject, is impractical unless a system for best spectral bands selection (BSBS) is used. In this work, first we give an up to date overview of the existing BSBS techniques proposed for face recognition. We aim to highlight the imporatnce of this component of MI based systems. The reviewed techniques are then experimented using the multispectral face database IRIS - M3 to compare their performances. To the best of our knowledge this is the first study that reviews and compares existing techniques for BSBS. The Obtained results emphasized the importance of setting up techniques for BSBS with MI based systems as well as the need for new techniques that investigate better the increasing speed of image processing tools.

    KW - Best Spectral Bands Selection

    KW - IRIS - M

    KW - Multispectral images

    KW - review

    UR - http://www.scopus.com/inward/record.url?scp=84988252417&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84988252417&partnerID=8YFLogxK

    U2 - 10.1109/AICCSA.2014.7073255

    DO - 10.1109/AICCSA.2014.7073255

    M3 - Conference contribution

    VL - 2014

    SP - 609

    EP - 613

    BT - 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014

    PB - IEEE Computer Society

    ER -