Abstract
This paper proposes a method for estimating continuous face directions with the discrete face direction feature classes. The feature classes are composed by the linear discriminant analysis of the “four directional features” that are extracted from some people’s faces looking in speci.ed directions. Estimation by a single camera gives ambiguous results for non-frontal view of faces. Especially, it is impossible from the back of the face. However, integrating the information from the multiple cameras allows more precise face direction estimation. Experiments show that our proposed method can achieve a mean error of at most 8° and a variance of 22.4 for all face directions.
This is a preview of subscription content, log in via an institution to check access.
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
Chen, Q., Wu, H., Fukumoto, T. and Yachida, M.: 3d head pose estimation without feature tracking. 3rd International Conference on Automatic Face and Gesture Recognition FG98 (April 1998) 88–93
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press (1990)
Hongo, H. et al.: Focus of attention for face and hand gesture recognition using multiple cameras. 4th International Conference on Automatic Face and Gesture Recognition FG2000 (March 2000) 156–161
Kaneko, M. and Hasegawa, O.: Processing of face images and its application. IEICE Trans. Information and Systems E82-D(3) (March 1999) 589–600
Kuriyama, S., Yamamoto, K. et al.: Face recognition by using hyper feature fields. Technical Report of IEICE Pattern Recognition and Media Understanding 99 (Nov. 1999) 105–110
Matsumoto, Y. and Zelinsky, A.: An algorithm for real-time stereo vision implementation of head pose and gaze direction measurement. 4th International Conference on Automatic Face and Gesture Recognition FG2000 (March 2000) 499–504
Pappu, R. and Beardsley, P.: A qualitative approach to classifying gaze direction. 3rd International Conference on Automatic Face and Gesture Recognition FG98 (April 1998) 160–165
Pentland, A.: Looking at people: Sensing for ubiquitous and wearable computing. IEEE Trans. Pattern Analysis and Machine Intelligence 22(1) (January 2000) 107–118
Wu, Y. and Toyama, K.: Wide-range, person-and illumination-insensitive head orientation estimation. 4th International Conference on Automatic Face and Gesture Recognition FG2000 (March 2000) 183–188
Yasumoto, M., Hongo, H. et al.: A consideration of face direction estimation and face recognition. Proc. of Meeting on Image Recognition and Understanding MIRU2000 I (July 2000) 469–474
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
Yasumoto, M., Hongo, H., Watanabe, H., Yamamoto, K. (2000). Face Direction Estimation using Multiple Cameras for Human Computer Interaction. 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_29
Download citation
DOI: https://doi.org/10.1007/3-540-40063-X_29
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