AAM fitting using shape parameter distribution

Youhei Shiraishi, Shinya Fujie, Tetsunori Kobayashi

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

    Abstract

    A novel constraint using shape parameter distribution into the AAM fitting method is proposed. Active appearance models (AAMs) are some of the most popular facial models. AAM-based face tracking delivers accurate alignment results. However, non-face-like shapes can also be estimated by AAMs, unlike by the conventional AAM fitting method, which only minimizes the matching error of the image. This is one of the causes for face tracking performance degradation in AAMs. A constraint using the shape parameter distribution is added in order to solve this problem.

    Original languageEnglish
    Title of host publicationEuropean Signal Processing Conference
    Pages2238-2242
    Number of pages5
    Publication statusPublished - 2012
    Event20th European Signal Processing Conference, EUSIPCO 2012 - Bucharest
    Duration: 2012 Aug 272012 Aug 31

    Other

    Other20th European Signal Processing Conference, EUSIPCO 2012
    CityBucharest
    Period12/8/2712/8/31

    Fingerprint

    Degradation

    Keywords

    • Active appearance models
    • Face tracking
    • Inverse compositional image alignment

    ASJC Scopus subject areas

    • Signal Processing
    • Electrical and Electronic Engineering

    Cite this

    Shiraishi, Y., Fujie, S., & Kobayashi, T. (2012). AAM fitting using shape parameter distribution. In European Signal Processing Conference (pp. 2238-2242). [6334037]

    AAM fitting using shape parameter distribution. / Shiraishi, Youhei; Fujie, Shinya; Kobayashi, Tetsunori.

    European Signal Processing Conference. 2012. p. 2238-2242 6334037.

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

    Shiraishi, Y, Fujie, S & Kobayashi, T 2012, AAM fitting using shape parameter distribution. in European Signal Processing Conference., 6334037, pp. 2238-2242, 20th European Signal Processing Conference, EUSIPCO 2012, Bucharest, 12/8/27.
    Shiraishi Y, Fujie S, Kobayashi T. AAM fitting using shape parameter distribution. In European Signal Processing Conference. 2012. p. 2238-2242. 6334037
    Shiraishi, Youhei ; Fujie, Shinya ; Kobayashi, Tetsunori. / AAM fitting using shape parameter distribution. European Signal Processing Conference. 2012. pp. 2238-2242
    @inproceedings{64202f839b8543a8a2aac86731ddfe61,
    title = "AAM fitting using shape parameter distribution",
    abstract = "A novel constraint using shape parameter distribution into the AAM fitting method is proposed. Active appearance models (AAMs) are some of the most popular facial models. AAM-based face tracking delivers accurate alignment results. However, non-face-like shapes can also be estimated by AAMs, unlike by the conventional AAM fitting method, which only minimizes the matching error of the image. This is one of the causes for face tracking performance degradation in AAMs. A constraint using the shape parameter distribution is added in order to solve this problem.",
    keywords = "Active appearance models, Face tracking, Inverse compositional image alignment",
    author = "Youhei Shiraishi and Shinya Fujie and Tetsunori Kobayashi",
    year = "2012",
    language = "English",
    isbn = "9781467310680",
    pages = "2238--2242",
    booktitle = "European Signal Processing Conference",

    }

    TY - GEN

    T1 - AAM fitting using shape parameter distribution

    AU - Shiraishi, Youhei

    AU - Fujie, Shinya

    AU - Kobayashi, Tetsunori

    PY - 2012

    Y1 - 2012

    N2 - A novel constraint using shape parameter distribution into the AAM fitting method is proposed. Active appearance models (AAMs) are some of the most popular facial models. AAM-based face tracking delivers accurate alignment results. However, non-face-like shapes can also be estimated by AAMs, unlike by the conventional AAM fitting method, which only minimizes the matching error of the image. This is one of the causes for face tracking performance degradation in AAMs. A constraint using the shape parameter distribution is added in order to solve this problem.

    AB - A novel constraint using shape parameter distribution into the AAM fitting method is proposed. Active appearance models (AAMs) are some of the most popular facial models. AAM-based face tracking delivers accurate alignment results. However, non-face-like shapes can also be estimated by AAMs, unlike by the conventional AAM fitting method, which only minimizes the matching error of the image. This is one of the causes for face tracking performance degradation in AAMs. A constraint using the shape parameter distribution is added in order to solve this problem.

    KW - Active appearance models

    KW - Face tracking

    KW - Inverse compositional image alignment

    UR - http://www.scopus.com/inward/record.url?scp=84869795664&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84869795664&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9781467310680

    SP - 2238

    EP - 2242

    BT - European Signal Processing Conference

    ER -