• DocumentCode
    595535
  • Title

    The ILGDB database of realistic pen-based gestural commands

  • Author

    Renau-Ferrer, N. ; Peiyu Li ; Delaye, Adrien ; Anquetil, Eric

  • Author_Institution
    INSA de Rennes, Univ. Eur. de Bretagne, Rennes, France
  • fYear
    2012
  • fDate
    11-15 Nov. 2012
  • Firstpage
    3741
  • Lastpage
    3744
  • Abstract
    In this paper, we introduce the Intuidoc-Loustic Gestures DataBase (ILGDB), a new publicly available database of realistic pen-based gestures for evaluation of recognition systems in pen-enabled interfaces. IL-GDB was collected in a real world context and in an immersive environment. As it contains a large number of unconstrained user-defined gestures, ILGDB offers a unique diversity of content that is likely to serve as a precious tool for benchmarking of gesture recognition systems. We report first baseline experimental results on the task of Writer-Dependent gesture recognition.
  • Keywords
    gesture recognition; haptic interfaces; ILGDB database; intuidoc-loustic gestures database; pen-enabled interfaces; realistic pen-based gestural commands; realistic pen-based gestures; unconstrained user-defined gestures; writer-dependent gesture recognition system; Benchmark testing; Context; Databases; Feature extraction; Gesture recognition; Support vector machines; Training;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition (ICPR), 2012 21st International Conference on
  • Conference_Location
    Tsukuba
  • ISSN
    1051-4651
  • Print_ISBN
    978-1-4673-2216-4
  • Type

    conf

  • Filename
    6460978