Abstract
An advanced real-time system for gesture recognition is presented, which is able to recognize complex dynamic gestures, such as ”hand waving”, ”spin”, ”pointing”, and ”head moving”. The recognition is based on global motion features, extracted from each difference image of the image sequence. The system uses Hidden Markov Models (HMMs) as statistical classifier. These HMMs are trained on a database of 24 isolated gestures, performed by 14 different people. With the use of global motion features, a recognition rate of 92.9% is achieved for a person and background independent recognition.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Claudette Cédras and Mubarak Shah. Motion-Based Recognition: A Survey. Image and Vision Computing, 13(2):129–155, 1995.
Aaron Bobick and James Davis. An Apperance-Based Representation of Action. In Proc. IEEE Int. Conf. on Pattern Recognition (ICPR-96), pages 307–312, Vienna, Austria, August 1996.
Thad Starner and Alex Pentland. Visual Recognition of American Sign Language Using Hidden Markov Models. In International Workshop on Automatic Face and Gesture Recognition, Zurich, Switzerland, 1995.
Polly K. Pook. Teleassistance: Using deictic gestures to control robot action. Technical Report TR594, University of Rochester, Computer Science Department, September 1995.
Mike Schuster and Gerhard Rigoll. Fast Online Video Image Sequence Recognition with Statistical Methods. In Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pages 3450–3453, Atlanta, May 1996.
Gerhard Rigoll and Andreas Kosmala. New improved Feature Extraction Methods for Real-Time High Performance Image Sequence Recognition. In Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), pages 2901–2904, Munich, April 1997.
Lawrence R. Rabiner. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc. of the IEEE, 77(2):257–285, 1989.
Stefan Eickeler, Andreas Kosmala, and Gerhard Rigoll. A New Approach to Content-Based Video Indexing Using Hidden Markov Models. In Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), pages 149–154, Louvain-la-Neuve, Belgium, June 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag
About this paper
Cite this paper
Rigoll, G., Kosmala, A., Eickeler, S. (1998). High performance real-time gesture recognition using Hidden Markov Models. In: Wachsmuth, I., Fröhlich, M. (eds) Gesture and Sign Language in Human-Computer Interaction. GW 1997. Lecture Notes in Computer Science, vol 1371. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0052990
Download citation
DOI: https://doi.org/10.1007/BFb0052990
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64424-8
Online ISBN: 978-3-540-69782-4
eBook Packages: Springer Book Archive