Skip to content
Journal article

Robust hand detection

Kolsch M, Turk M ...see all

Proceedings Sixth IEEE International Conference on Automatic Face and Gesture Recognition (2004) pp. 614-619

  • 87

    Readers

    Mendeley users who have this article in their library.
  • 119

    Citations

    Citations of this article.
  • N/A

    Views

    ScienceDirect users who have downloaded this article.
Sign in to save reference

Abstract

Vision-based hand gesture interfaces require fast and extremely robust hand detection. Here, we study view-specific hand posture detection with an object recognition method proposed by Viola and Jones. Training with this method is computationally very expensive, prohibiting the evaluation of many hand appearances for their suitability to detection. In this paper, we present a frequency analysis-based method for instantaneous estimation of class separability, without the need for any training. We built detectors for the most promising candidates, their receiver operating characteristics confirming the estimates. Next, we found that classification accuracy increases with a more expressive feature type. Lastly, we show that further optimization of training parameters yields additional detection rate improvements. In summary, we present a systematic approach to building an extremely robust hand appearance detector, providing an important step towards easily deployable and reliable vision-based hand gesture interfaces.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Get full text

Authors

  • M. Kolsch

  • M. Turk

Cite this document

Choose a citation style from the tabs below