An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting

Matthias Wimmer, Shinya Fujie, Freek Stulp, Tetsunori Kobayashi, Bernd Radig

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

    2 Citations (Scopus)

    Abstract

    Due to their use of information contained in texture, Active Appearance Models (AAM) generally outperform Active Shape Models (ASM) in terms of fitting accuracy. Although many extensions and improvements over the original AAM have been proposed, on of the main drawbacks of AAMs remains its dependence on good initial model parameters to achieve accurate fitting results. In this paper, we determine the initial model parameters for AAM fitting with ASM fitting, and use machine learning techniques to improve the scope and accuracy of ASM fitting. Combining the precision of AAM fitting with the large radius of convergence of learned ASM fitting improves the results by an order of magnitude, as our empirical evaluation n a database of publicly available benchmark images demonstrates.

    Original languageEnglish
    Title of host publication2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
    DOIs
    Publication statusPublished - 2008
    Event2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 - Amsterdam
    Duration: 2008 Sep 172008 Sep 19

    Other

    Other2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
    CityAmsterdam
    Period08/9/1708/9/19

    Fingerprint

    Learning systems
    Textures

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction
    • Electrical and Electronic Engineering

    Cite this

    Wimmer, M., Fujie, S., Stulp, F., Kobayashi, T., & Radig, B. (2008). An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 [4813465] https://doi.org/10.1109/AFGR.2008.4813465

    An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting. / Wimmer, Matthias; Fujie, Shinya; Stulp, Freek; Kobayashi, Tetsunori; Radig, Bernd.

    2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813465.

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

    Wimmer, M, Fujie, S, Stulp, F, Kobayashi, T & Radig, B 2008, An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting. in 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008., 4813465, 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008, Amsterdam, 08/9/17. https://doi.org/10.1109/AFGR.2008.4813465
    Wimmer M, Fujie S, Stulp F, Kobayashi T, Radig B. An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting. In 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008. 4813465 https://doi.org/10.1109/AFGR.2008.4813465
    Wimmer, Matthias ; Fujie, Shinya ; Stulp, Freek ; Kobayashi, Tetsunori ; Radig, Bernd. / An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting. 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008. 2008.
    @inproceedings{0da83a7417f944e497958edbb2db3123,
    title = "An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting",
    abstract = "Due to their use of information contained in texture, Active Appearance Models (AAM) generally outperform Active Shape Models (ASM) in terms of fitting accuracy. Although many extensions and improvements over the original AAM have been proposed, on of the main drawbacks of AAMs remains its dependence on good initial model parameters to achieve accurate fitting results. In this paper, we determine the initial model parameters for AAM fitting with ASM fitting, and use machine learning techniques to improve the scope and accuracy of ASM fitting. Combining the precision of AAM fitting with the large radius of convergence of learned ASM fitting improves the results by an order of magnitude, as our empirical evaluation n a database of publicly available benchmark images demonstrates.",
    author = "Matthias Wimmer and Shinya Fujie and Freek Stulp and Tetsunori Kobayashi and Bernd Radig",
    year = "2008",
    doi = "10.1109/AFGR.2008.4813465",
    language = "English",
    isbn = "9781424421541",
    booktitle = "2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008",

    }

    TY - GEN

    T1 - An ASM fitting method based on machine learning that provides a robust parameter initialization for AAM fitting

    AU - Wimmer, Matthias

    AU - Fujie, Shinya

    AU - Stulp, Freek

    AU - Kobayashi, Tetsunori

    AU - Radig, Bernd

    PY - 2008

    Y1 - 2008

    N2 - Due to their use of information contained in texture, Active Appearance Models (AAM) generally outperform Active Shape Models (ASM) in terms of fitting accuracy. Although many extensions and improvements over the original AAM have been proposed, on of the main drawbacks of AAMs remains its dependence on good initial model parameters to achieve accurate fitting results. In this paper, we determine the initial model parameters for AAM fitting with ASM fitting, and use machine learning techniques to improve the scope and accuracy of ASM fitting. Combining the precision of AAM fitting with the large radius of convergence of learned ASM fitting improves the results by an order of magnitude, as our empirical evaluation n a database of publicly available benchmark images demonstrates.

    AB - Due to their use of information contained in texture, Active Appearance Models (AAM) generally outperform Active Shape Models (ASM) in terms of fitting accuracy. Although many extensions and improvements over the original AAM have been proposed, on of the main drawbacks of AAMs remains its dependence on good initial model parameters to achieve accurate fitting results. In this paper, we determine the initial model parameters for AAM fitting with ASM fitting, and use machine learning techniques to improve the scope and accuracy of ASM fitting. Combining the precision of AAM fitting with the large radius of convergence of learned ASM fitting improves the results by an order of magnitude, as our empirical evaluation n a database of publicly available benchmark images demonstrates.

    UR - http://www.scopus.com/inward/record.url?scp=67650699768&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=67650699768&partnerID=8YFLogxK

    U2 - 10.1109/AFGR.2008.4813465

    DO - 10.1109/AFGR.2008.4813465

    M3 - Conference contribution

    SN - 9781424421541

    BT - 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008

    ER -