Abstract
We present a robust front-end pose classification/estimation procedure to be used in face recognition scenarios. A novel discriminative feature description that encodes underlying shape well and is insensitive to illumination and other common variations in facial appearance, such as skin color etc., is proposed. Using such features we generate a pose similarity feature space (PSFS) that turns the multi-class problem into two-class by using inter-pose and intra-pose similarities. A new classification procedure is laid down which models this feature space and copes well with discriminating between nearest poses. For a test image it outputs a measure of confidence or so called posterior probability for all poses without explicitly estimating underlying densities. The pose estimation system is evaluated using CMU Pose, Illumination and Expression (PIE) database.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bingpeng, M., Wenchao, Z., Shiguang, S., Xilin, C., Wen, C.: Robust Head Pose Estimation Using LGBP. In: ICPR, vol. 2, pp. 512–515 (2006)
Shiguang, S., Xilin, C., Wen, G.: Histogram of Gabor Phase Patterns (HGPP):A Novel Object Representation Approach for Face Recognition. IEEE Trans. on Image Processing 16(1), 57–68 (2007)
Gong, S., McKenna, S., Collins, J.: An investigation into face pose distributions. In: FG, p. 265 (1996)
Kovesi, P.D.: Phase congruency: A low-level image invariant. Psychological Research 64, 136–148 (2000)
Kovesi, P.D.: Phase congruency detects corners and edges. In: Proc. Australian pattern recognition society conference, pp. 309–318 (2003)
Lee, H.S., Kim, D.: Generating frontal view face image for pose invariant face recognition. PR letters 27(7), 747–754 (2006)
Morrone, M.C., Owens, R.A.: Feature detection from local energy. PR Letters 6, 303–313 (1987)
Patnaik, R., Casasent, D.P.: MINACE-filter-based facial pose estimation. In: Biometric Technology for Human Identification. Proc. SPIE, pp. 460–467 (2005)
Rowley, H.A., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE PAMI 20(1), 23–38 (1998)
Robbins, B., Owens, R.: 2D feature detection via local energy. Image and Vision Computing 15, 353–368 (1997)
Sarfraz, M.S., Hellwich, O.: Probabilistic Learning for Fully Automatic Face Recognition across Pose. Image and Vision Computing (2009), doi:10.1016/j.imavis.2009.07.008
Schapire, R., Singer, Y.: Improved boosting algorithms using confidence-related predictions. Machine Learning 37, 297–336 (1999)
Sim, T., Baker, S., Bsat, M.: The CMU Pose, Illumination and Expression (PIE) database. In: Proc. Fifth IEEE FG, pp. 46–51 (2002)
Grundig, M., Hellwich, O.: 3D Head Pose Estimation with Symmetry Based Illumination Model in Low Resolution Video. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 45–53. Springer, Heidelberg (2004)
Yuan, C., Casasent, D.P.: Face recognition and verification with pose and illumination variations and imposer rejection. In: Biometric Technology for Human Identification. Proc. SPIE (2005)
Zhao, S., Gao, Y.: Automated Face Pose Estimation Using Elastic Energy Models. In: The 18th ICPR, vol. 4, pp. 618–621 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sarfraz, M.S., Hellwich, O. (2009). On Head Pose Estimation in Face Recognition. In: Ranchordas, A., Araújo, H.J., Pereira, J.M., Braz, J. (eds) Computer Vision and Computer Graphics. Theory and Applications. VISIGRAPP 2008. Communications in Computer and Information Science, vol 24. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10226-4_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-10226-4_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10225-7
Online ISBN: 978-3-642-10226-4
eBook Packages: Computer ScienceComputer Science (R0)