Hand Shape Extraction and Understanding by Virtue of Multiple Cues Fusion Technology

In order that information included in the hand shape can be extracted for gesture communication aiming to the new technology of Human Computer Interaction, hand shape should be reliably extracted based on image sequences. In this paper a hand shape extraction approach is proposed. By using multiple cues such as motion and color information, embedded in image sequences, a set of complicated hand shapes which compromise a small dictionary of hand postures, can be reliably extracted within a rather sophisticated environment, In this paper the proposed shape extraction strategy is addressed and preliminary results are indicated to prove its effectiveness.

[1]  Yoshiaki Shirai,et al.  Hand gesture estimation and model refinement using monocular camera-ambiguity limitation by inequality constraints , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[2]  Ying Wu,et al.  Capturing articulated human hand motion: a divide-and-conquer approach , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[3]  谷口 倫一郎,et al.  Appearance-based Recognition of Hand Shapes for Sign Language in Low Resolution Image , 2000 .

[4]  Matthew Turk,et al.  View-based interpretation of real-time optical flow for gesture recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.