15 April 1994 Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction
Author Affiliations +
Interaction in virtual reality environments is still a challenging task. Static hand posture recognition is currently the most common and widely used method for interaction using glove input devices. In order to improve the naturalness of interaction, and thereby decrease the user-interface learning time, there is a need to be able to recognize dynamic gestures. In this paper we describe our approach to overcoming the difficulties of dynamic gesture recognition (DGR) using neural networks. Backpropagation neural networks have already proven themselves to be appropriate and efficient for posture recognition. However, the extensive amount of data involved in DGR requires a different approach. Because of features such as topology preservation and automatic-learning, Kohonen Feature Maps are particularly suitable for the reduction of the high dimensional data space that is the result of a dynamic gesture, and are thus implemented for this task.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Klaus Boehm, Klaus Boehm, Wolfgang Broll, Wolfgang Broll, Michael A. Sokolewicz, Michael A. Sokolewicz, } "Dynamic gesture recognition using neural networks: a fundament for advanced interaction construction", Proc. SPIE 2177, Stereoscopic Displays and Virtual Reality Systems, (15 April 1994); doi: 10.1117/12.173889; https://doi.org/10.1117/12.173889


Gestural interfaces for immersive environments
Proceedings of SPIE (February 28 2014)
Natural interaction for unmanned systems
Proceedings of SPIE (May 22 2015)
A computer control system using a virtual keyboard
Proceedings of SPIE (February 14 2015)
High-velocity teleoperated rover
Proceedings of SPIE (July 22 1999)
Interpretation of the function of the striate cortex
Proceedings of SPIE (April 14 2000)

Back to Top