RAV (reparameterized angle variations) algorithm for online handwriting recognition

Masakazu Kobayashi, S. Masaki, O. Miyamoto, Y. Nakagawa, Y. Komiya, T. Matsumoto

    Research output: Contribution to journalArticle

    10 Citations (Scopus)

    Abstract

    A new algorithm RAV (reparameterized angle variations) is proposed which makes explicit use of trajectory information where the time evolution of the pen coordinates plays a crucial role. The algorithm is robust against stroke connections/abbreviations as well as shape distortions, while maintaining reasonable robustness against stroke-order variations. Preliminary experiments are reported on tests against the Kuchibue_d-96-02 database from the Tokyo University of Agriculture and Technology.

    Original languageEnglish
    Pages (from-to)181-191
    Number of pages11
    JournalInternational Journal on Document Analysis and Recognition
    Volume3
    Issue number3
    DOIs
    Publication statusPublished - 2001

    Fingerprint

    Agriculture
    Trajectories
    Experiments

    Keywords

    • Online handwriting recognition
    • Pen trajectory
    • Stroke connections
    • Stroke-order variations

    ASJC Scopus subject areas

    • Software
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    Cite this

    RAV (reparameterized angle variations) algorithm for online handwriting recognition. / Kobayashi, Masakazu; Masaki, S.; Miyamoto, O.; Nakagawa, Y.; Komiya, Y.; Matsumoto, T.

    In: International Journal on Document Analysis and Recognition, Vol. 3, No. 3, 2001, p. 181-191.

    Research output: Contribution to journalArticle

    Kobayashi, Masakazu ; Masaki, S. ; Miyamoto, O. ; Nakagawa, Y. ; Komiya, Y. ; Matsumoto, T. / RAV (reparameterized angle variations) algorithm for online handwriting recognition. In: International Journal on Document Analysis and Recognition. 2001 ; Vol. 3, No. 3. pp. 181-191.
    @article{eba76d130c3241ed9f7c3ee34debb755,
    title = "RAV (reparameterized angle variations) algorithm for online handwriting recognition",
    abstract = "A new algorithm RAV (reparameterized angle variations) is proposed which makes explicit use of trajectory information where the time evolution of the pen coordinates plays a crucial role. The algorithm is robust against stroke connections/abbreviations as well as shape distortions, while maintaining reasonable robustness against stroke-order variations. Preliminary experiments are reported on tests against the Kuchibue_d-96-02 database from the Tokyo University of Agriculture and Technology.",
    keywords = "Online handwriting recognition, Pen trajectory, Stroke connections, Stroke-order variations",
    author = "Masakazu Kobayashi and S. Masaki and O. Miyamoto and Y. Nakagawa and Y. Komiya and T. Matsumoto",
    year = "2001",
    doi = "10.1007/PL00013560",
    language = "English",
    volume = "3",
    pages = "181--191",
    journal = "International Journal on Document Analysis and Recognition",
    issn = "1433-2833",
    publisher = "Springer Verlag",
    number = "3",

    }

    TY - JOUR

    T1 - RAV (reparameterized angle variations) algorithm for online handwriting recognition

    AU - Kobayashi, Masakazu

    AU - Masaki, S.

    AU - Miyamoto, O.

    AU - Nakagawa, Y.

    AU - Komiya, Y.

    AU - Matsumoto, T.

    PY - 2001

    Y1 - 2001

    N2 - A new algorithm RAV (reparameterized angle variations) is proposed which makes explicit use of trajectory information where the time evolution of the pen coordinates plays a crucial role. The algorithm is robust against stroke connections/abbreviations as well as shape distortions, while maintaining reasonable robustness against stroke-order variations. Preliminary experiments are reported on tests against the Kuchibue_d-96-02 database from the Tokyo University of Agriculture and Technology.

    AB - A new algorithm RAV (reparameterized angle variations) is proposed which makes explicit use of trajectory information where the time evolution of the pen coordinates plays a crucial role. The algorithm is robust against stroke connections/abbreviations as well as shape distortions, while maintaining reasonable robustness against stroke-order variations. Preliminary experiments are reported on tests against the Kuchibue_d-96-02 database from the Tokyo University of Agriculture and Technology.

    KW - Online handwriting recognition

    KW - Pen trajectory

    KW - Stroke connections

    KW - Stroke-order variations

    UR - http://www.scopus.com/inward/record.url?scp=0742311728&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0742311728&partnerID=8YFLogxK

    U2 - 10.1007/PL00013560

    DO - 10.1007/PL00013560

    M3 - Article

    AN - SCOPUS:0742311728

    VL - 3

    SP - 181

    EP - 191

    JO - International Journal on Document Analysis and Recognition

    JF - International Journal on Document Analysis and Recognition

    SN - 1433-2833

    IS - 3

    ER -