Head Pose Recognition Based on 2-D KPCA

Abstract:

One’s head pose can be estimated using face images. The hidden manifold of head pose in the high dimensional space can be successfully embedded into a 2 dimensional space using Kernel Principal Component Analysis (KPCA). A pose curve is gotten using KPCA train samples and new pose image is projected onto this curve. The pose angle can be estimated using interpolation method. The disadvantage of traditional linear method is conquered by using 2-D KPCA and the experimental results that the method is effective to estimate head poses. The kernel functions effects on estimation accuracy are also discussed.

• Periodical: Applied Mechanics and Materials (Volumes 373-375)
• Pages: 468-472
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.373-375.468
• Online since: August 2013
• Authors: Chun Ling Li, Yu Feng Lu
• Keywords: 2-D Kernel Principal Component Analysis, Fitting Circle, Head Pose Estimating, Manifold Learning

References

[1] K. Huang and M.M. Trivedi. Driver Head Pose and View Estimation with Single Omni directional Video Stream. Proceedings of the first International Workshop on In-Vehicle Cognitive Computer Vision Systems, in Conjunction with the Third International Conference on Computer Vision Systems, Seattle, USA, 2003: 709~714.

[2] B. Braathen, M.S. Bartlett and J.R. Movellan. 3-D Head Pose Estimation from Video by Stochastic Particle Filtering. the Eighth Annual Joint Symposium on Neural Computation, 2001: 1~7.

[3] Y. Wei, L. Fradet and T. Tan. Head Pose Estimation Using Gabor Eigenspace Modeling. IEEE International Conference on Image Processing (ICIP2002), 2002: 281~284.

DOI: 10.1109/icip.2002.1038014

[4] Y. Fu and T.S. Huang. Graph Embedded Analysis for Head Pose Estimation. Proceedings of the Seventh International Conference on Automatic Face and Gesture Recognition, 2006: CD-Room.

DOI: 10.1109/fgr.2006.60

[5] Y. Li, S. Gong and H. Liddell. Support vector regression and classification based multi-view face detection and recognition. IEEE International Conference on Automatic Face and Gesture Recognition, 2000: 300~305.

DOI: 10.1109/afgr.2000.840650

[6] S. Srinivasan and K.L. Boyer. Head Pose Estimation Using View Based Eigenspaces. the 16th International Conference on Pattern Recognition, 2002: 302~305.

DOI: 10.1109/icpr.2002.1047456

[7] V. Kruger and G. Sommer. Efficient Head Pose Estimation with Gabor Wavelet Networks. the 11th British Machine Vision Conference, 2000: CD-Room.

DOI: 10.5244/c.14.8

[8] K. I. Kim, K. Jung and H. J. Kim. Face Recognition using Kernel Principal Component Analysis. IEEE Signal Processing Letters, 2002, 9(2): 40~42.

DOI: 10.1109/97.991133

[9] Chen Jiada, Lai Jianhuang and Feng Guocan. A Novel Method for Facial Pose Discrimination and Frontal View Synthesis. Journal of Computer Research and Development, 2006, 43( 8): 1477~1484.

DOI: 10.1360/crad20060825

[10] L. Chen, L. Zhang, Y. Hu, M. Li and H. Zhang. Head pose estimation using fisher manifold learning. in: Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures, in Conjunction with ICCV2003, (2003).

DOI: 10.1109/amfg.2003.1240844