Abstract
In this paper we present a video-based HCI-system for the recognition of 10 different hand postures in real time. Automatic removal of the forearm from the segmented hand object garantees a consistent input to the feature calculation step. An extensive comparison of three different approaches to feature extraction (Hu moments, eigencoefficients, fourier descriptors) was carried out. The combination of classifiers using different methods of feature description leads to a recognition rate of 99.5%, requiring only 15–17 ms per frame on a normal PC. The main contribution of this paper is the thourough evaluation, selection and combination of known steps.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. Schlenzig, E. Hunter, R. Jain. Vision Based Hand Gesture Interpretation using Recursive Estimation. 28th Asilomar Conf. on Signals, Systems, and Comp., 1994.
H. Birk, T. B. Moeslund. Recognizing Gestures from the Hand Alphabet Using Principal Component Analysis. Master’s Thesis, Aalborg University, 1996.
C. W. Ng, S. Ranganath. Gesture Recognition Via Pose Classification. Proc. International Conference on Pattern Recognition (ICPR’00), Vol. III, 2000, pp. 703–708.
M. Stark, M. Kohler, u. a. ZYKLOP: Ein System für den gestenbasierten Dialog mit Anwendungsprogrammen. In “Modeling-Virtual Worlds-Distributed Graphics”, W.D.-Fellner (Ed.), Infix-Verlag, 1995, pp. 69–82.
K.-H. Jo, Y. Kuno, Y. Shirai. Context-Based Recognition of Manipulative Hand Gestures for Human Computer Interaction. Proc. 3rd Asian Conference on Computer Vision, Hong Kong, China, January 1998, Vol. II, 1998.
B. Deimel, S. Schröter. Improving Hand-Gesture Recognition via Video Based Methods for the Separation of the Forearm from the Human Hand. 3rd Gesture Workshop, Gif-sur-Yvette, France, March 1999.
M. K. Hu. Visual Pattern Recognition by Moment Invariants. IRE Transactions on Information Theory IT-8, January 1962, pp. 179–187.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Funck, S. (2002). Video-Based Handsign Recognition for Intuitive Human-Computer-Interaction. In: Van Gool, L. (eds) Pattern Recognition. DAGM 2002. Lecture Notes in Computer Science, vol 2449. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45783-6_4
Download citation
DOI: https://doi.org/10.1007/3-540-45783-6_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44209-7
Online ISBN: 978-3-540-45783-1
eBook Packages: Springer Book Archive