Abstract
Gesture recognition is an appealing tool for natural interface with computers especially for physically impaired persons. In this paper, it is proposed to use Hypercolumn model (HCM), which is constructed by hierarchically piling up Self-organizing maps (SOM), as an image recognition system for gesture recognition, since the HCM allows alleviating many difficulties associated with gesture recognition. It is, however, required for on-line systems to reduce the recognition time to the range of normal video camera rates. To achieve this, the Randomized HCM (RHCM), which is derived from HCM by replacing SOM with randomized SOM, is introduced. With RHCM algorithm, the recognition time is drastically reduced without accuracy deterioration. The experimental results to recognize hand gestures using RHCM are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Davis J. and Shah M.: Recognizing Hand Gestures, ECCV’94, (1994) 331–340
Kameda Y., Minoh M. and Ikeda K.: Three Dimension Pose Estimation Of An Articulated Object From Its Silhouette Image, ACCV’93 (1993) 612–615
Freeman W. and Roth M.: Orientation Histgrams For Hand Gesture Recognition, Int. Workshop on Automatic Face-and Gesture-Recognition, IEEE Computer Society (1995)
Tsuruta N., Taniguchi R. and Amamiya M.: Hypercolumn Model: A Combination Model of Hierarchical Self-Organizing Maps and Neocognitron for Image Recognition, System and Computer in Japan, Vol. 31, No. 2 (2000) 49–61
Tsuruta N., Taniguchi R. and Amamiya M.: Hypercolumn Model: A Modified Model of Neocognitron Using Hierarchical Self-Organizing Maps, IWANN’99, Vol. 1 (1999) 840–849
Kohonen T.: Self-organizing maps, Springer Series in Information Sciences (1995)
Tobely T. El., Yoshiki Y., Tsuda R., Tsuruta N. and Amamiya M., Randomized Self-Organizing Maps and Its Application, 6th Int. Conf. on Soft Computing, IIZUKA 2000 (2000) 207–214
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tsuruta, N., Yoshiki, Y., Tobely, T.E. (2001). A Randomized Hypercolumn Model and Gesture Recognition. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_27
Download citation
DOI: https://doi.org/10.1007/3-540-45720-8_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42235-8
Online ISBN: 978-3-540-45720-6
eBook Packages: Springer Book Archive