Abstract
In this paper, we present a head gesture recognition algorithm that is based on the tracking technique developed by Kanade, Luca, and Tomasi (KaLuTo) and a one-class-in-one neural network algorithm. In our method, human skin colors are used to detect the head from complex backgrounds and the KaLuTo algorithm is applied to detect and track feature points on the head. Feature points tracked in successive frames are used to construct a feature vector as the input to the one-class-in-one neural network, which is employed to classify the head gestures into different classes. This method can offer some robustness to different background conditions. Experimental results prove the effectiveness of this method
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
Jianbo Shi and Carlo Tomasi: Good features to track. IEEE conference on Computer Vision and Pattern Recognition, Seattle, June 1994.
Takahiro Otsuka and Jun Ohya: Real-time estimation of head motion using weak perspective epipolar geometry. Proc. of Fourth IEEE Workshop on Applications of Computer Vision, pp. 220–225, Oct. 1998.
S. H. Lin, S. Y. Kung, and L. J. Lin: Face Recognition/Detection by Probabilistic Decision-Based Neural Network. IEEE Trans. Neural Network, Vol. 8, Jan. 1997.
Y. shin and J. Ghosh: The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation. Int. Conf. on Neural Networks, Seattle, I:12–18,1991.
Jinshan Tang: Head gesture classification and definition. Research proposal, ATR, Dec. 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tang, J., Nakatsu, R. (2000). A Head Gesture Recognition Algorithm. In: Tan, T., Shi, Y., Gao, W. (eds) Advances in Multimodal Interfaces — ICMI 2000. ICMI 2000. Lecture Notes in Computer Science, vol 1948. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-40063-X_10
Download citation
DOI: https://doi.org/10.1007/3-540-40063-X_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41180-2
Online ISBN: 978-3-540-40063-9
eBook Packages: Springer Book Archive