A method of gender classification by integrating facial, hairstyle, and clothing images

Kazuya Ueki, Hiromitsu Komatsu, Satoshi Imaizumi, Kenichi Kaneko, Satoshi Imaizumi, Nobuhiro Sekine, Jiro Katto, Tetsunori Kobayashi

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

    22 Citations (Scopus)

    Abstract

    This paper presents a method of gender classification by integrating facial, hairstyle, and clothing images. Initially, input images are separated into facial, hairstyle and clothing regions, and independently learned PCAs and GMMs based on thousands of sample images are applied to each region. The classification results are then integrated into a single score using some known priors based on the Bayes rule. Experimental results showed that our integration strategy significantly reduced error rate in gender classification compared with the conventional facial only approach.

    Original languageEnglish
    Title of host publicationProceedings - International Conference on Pattern Recognition
    EditorsJ. Kittler, M. Petrou, M. Nixon
    Pages446-449
    Number of pages4
    Volume4
    DOIs
    Publication statusPublished - 2004
    EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge
    Duration: 2004 Aug 232004 Aug 26

    Other

    OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
    CityCambridge
    Period04/8/2304/8/26

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Computer Vision and Pattern Recognition
    • Hardware and Architecture

    Cite this

    Ueki, K., Komatsu, H., Imaizumi, S., Kaneko, K., Imaizumi, S., Sekine, N., ... Kobayashi, T. (2004). A method of gender classification by integrating facial, hairstyle, and clothing images. In J. Kittler, M. Petrou, & M. Nixon (Eds.), Proceedings - International Conference on Pattern Recognition (Vol. 4, pp. 446-449) https://doi.org/10.1109/ICPR.2004.1333798

    A method of gender classification by integrating facial, hairstyle, and clothing images. / Ueki, Kazuya; Komatsu, Hiromitsu; Imaizumi, Satoshi; Kaneko, Kenichi; Imaizumi, Satoshi; Sekine, Nobuhiro; Katto, Jiro; Kobayashi, Tetsunori.

    Proceedings - International Conference on Pattern Recognition. ed. / J. Kittler; M. Petrou; M. Nixon. Vol. 4 2004. p. 446-449.

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

    Ueki, K, Komatsu, H, Imaizumi, S, Kaneko, K, Imaizumi, S, Sekine, N, Katto, J & Kobayashi, T 2004, A method of gender classification by integrating facial, hairstyle, and clothing images. in J Kittler, M Petrou & M Nixon (eds), Proceedings - International Conference on Pattern Recognition. vol. 4, pp. 446-449, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, 04/8/23. https://doi.org/10.1109/ICPR.2004.1333798
    Ueki K, Komatsu H, Imaizumi S, Kaneko K, Imaizumi S, Sekine N et al. A method of gender classification by integrating facial, hairstyle, and clothing images. In Kittler J, Petrou M, Nixon M, editors, Proceedings - International Conference on Pattern Recognition. Vol. 4. 2004. p. 446-449 https://doi.org/10.1109/ICPR.2004.1333798
    Ueki, Kazuya ; Komatsu, Hiromitsu ; Imaizumi, Satoshi ; Kaneko, Kenichi ; Imaizumi, Satoshi ; Sekine, Nobuhiro ; Katto, Jiro ; Kobayashi, Tetsunori. / A method of gender classification by integrating facial, hairstyle, and clothing images. Proceedings - International Conference on Pattern Recognition. editor / J. Kittler ; M. Petrou ; M. Nixon. Vol. 4 2004. pp. 446-449
    @inproceedings{873599bbbc1341a88b05d861bc4186f7,
    title = "A method of gender classification by integrating facial, hairstyle, and clothing images",
    abstract = "This paper presents a method of gender classification by integrating facial, hairstyle, and clothing images. Initially, input images are separated into facial, hairstyle and clothing regions, and independently learned PCAs and GMMs based on thousands of sample images are applied to each region. The classification results are then integrated into a single score using some known priors based on the Bayes rule. Experimental results showed that our integration strategy significantly reduced error rate in gender classification compared with the conventional facial only approach.",
    author = "Kazuya Ueki and Hiromitsu Komatsu and Satoshi Imaizumi and Kenichi Kaneko and Satoshi Imaizumi and Nobuhiro Sekine and Jiro Katto and Tetsunori Kobayashi",
    year = "2004",
    doi = "10.1109/ICPR.2004.1333798",
    language = "English",
    isbn = "0769521282",
    volume = "4",
    pages = "446--449",
    editor = "J. Kittler and M. Petrou and M. Nixon",
    booktitle = "Proceedings - International Conference on Pattern Recognition",

    }

    TY - GEN

    T1 - A method of gender classification by integrating facial, hairstyle, and clothing images

    AU - Ueki, Kazuya

    AU - Komatsu, Hiromitsu

    AU - Imaizumi, Satoshi

    AU - Kaneko, Kenichi

    AU - Imaizumi, Satoshi

    AU - Sekine, Nobuhiro

    AU - Katto, Jiro

    AU - Kobayashi, Tetsunori

    PY - 2004

    Y1 - 2004

    N2 - This paper presents a method of gender classification by integrating facial, hairstyle, and clothing images. Initially, input images are separated into facial, hairstyle and clothing regions, and independently learned PCAs and GMMs based on thousands of sample images are applied to each region. The classification results are then integrated into a single score using some known priors based on the Bayes rule. Experimental results showed that our integration strategy significantly reduced error rate in gender classification compared with the conventional facial only approach.

    AB - This paper presents a method of gender classification by integrating facial, hairstyle, and clothing images. Initially, input images are separated into facial, hairstyle and clothing regions, and independently learned PCAs and GMMs based on thousands of sample images are applied to each region. The classification results are then integrated into a single score using some known priors based on the Bayes rule. Experimental results showed that our integration strategy significantly reduced error rate in gender classification compared with the conventional facial only approach.

    UR - http://www.scopus.com/inward/record.url?scp=10044221726&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=10044221726&partnerID=8YFLogxK

    U2 - 10.1109/ICPR.2004.1333798

    DO - 10.1109/ICPR.2004.1333798

    M3 - Conference contribution

    SN - 0769521282

    VL - 4

    SP - 446

    EP - 449

    BT - Proceedings - International Conference on Pattern Recognition

    A2 - Kittler, J.

    A2 - Petrou, M.

    A2 - Nixon, M.

    ER -