Learning Probabilistic Models for Recognizing Faces under Pose Variations

M. Saquib Sarfraz, Olaf Hellwich

2008

Abstract

Recognizing a face from a novel view point poses major challenges for automatic face recognition. Recent methods address this problem by trying to model the subject specific appearance change across pose. For this, however, almost all of the existing methods require a perfect alignment between a gallery and a probe image. In this paper we present a pose invariant face recognition method centered on modeling joint appearance of gallery and probe images across pose in a probabilistic framework. We propose novel extensions in this direction by introducing to use a more robust feature description as opposed to pixel-based appearances. Using such features we put forward to synthesize the non-frontal views to frontal. Furthermore, using local kernel density estimation, instead of commonly used normal density assumption, is suggested to derive the prior models. Our method does not require any strict alignment between gallery and probe images which makes it particularly attractive as compared to the existing state of the art methods. Improved recognition across a wide range of poses has been achieved using these extensions.

References

  1. Beymer D.: Pose-invariant face recognition using real and virtual Views. M.I.T., A.I. Technical Report No.1574, March 1996.
  2. Blanz V. and Vetter T.: Face recognition based on fitting a 3D morphable model. IEEE Trans. PAMI, vol. 25, no. 9, 2003.
  3. Brunelli R. and Poggio T.: Face recognition: Features versus templates. IEEE Trans. PAMI, vol. 15, no. 10, pp. 1042-1052, 1993.
  4. Gross R., Matthews I. and Baker S.: Appearance-based face recognition and light-fields. IEEE Trans. PAMI, vol. 26, pp. 449-465, April 2004.
  5. Kanade T. and Yamada A.: Multi-subregion based probabilistic approach towards poseinvariant face recognition. in IEEE CIRA, vol. 2, pp. 954-959, 2003.
  6. Kim T. and Kittler J.: Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model image. IEEE Trans. PAMI, vol. 27, pp. 318-327, March 2005.
  7. Lee H.S., Kim D.: Generating frontal view face image for pose invariant face recognition. PR letters vol.27, No. 7, pp 747-754. 2006.
  8. Lindeberg T.: Feature detection with automatic scale selection. Int. Journal of computer vision, vol. 30 no. 2, pp 79-116, 1998.
  9. Lowe D.: Distinctive image features from scale-invariant keypoints. Int. Journal of computer vision, 2(60):91-110, 2004.
  10. Martinez A. M.: Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE Trans. PAMI, vol. 24, no. 6, pp. 748- 763, 2002.
  11. Moghaddam B. and Pentland A.: Probabilistic visual learning for object recognition. IEEE Trans. PAMI, vol. 19, no. 7, pp. 696-710, 1997.
  12. Mikolajczyk and Schmid C.: Performance evaluation of local descriptors. PAMI,27(10):31- 47, 2005.
  13. Sarfraz M.S., Hellwich O.: Head pose estimation in face recognition across pose scenarios. Int. conference on computer vision theory and applications VISAPP, 22-25 Jan, 2008.
  14. Sarfraz M.S., Hellwich O.: Performance analysis of classifiers on face recognition", 5th IEEE AICS, pp. 255-264, 2006.
  15. Sim T., Baker S., and Bsat S.: The CMU Pose, Illumination and Expression (PIE) database. 5th IEEE FG, pp. 46-51, 2002.
  16. Silverman BW., Density estimation for statistics and data analysis. Chapman and Hall. 1992.
  17. Vasilescu MA. O. and Terzopoulos D.: Multilinear analysis of image ensembles: TensorFaces. ECCV, vol. 2350, pp. 447-460, 2002.
Download


Paper Citation


in Harvard Style

Saquib Sarfraz M. and Hellwich O. (2008). Learning Probabilistic Models for Recognizing Faces under Pose Variations . In Proceedings of the 1st International Workshop on Image Mining Theory and Applications IMTA 2008 - Volume 1: IMTA, (VISIGRAPP 2008) ISBN 978-989-8111-25-8, pages 122-132. DOI: 10.5220/0002341001220132


in Bibtex Style

@conference{imta08,
author={M. Saquib Sarfraz and Olaf Hellwich},
title={Learning Probabilistic Models for Recognizing Faces under Pose Variations},
booktitle={Proceedings of the 1st International Workshop on Image Mining Theory and Applications IMTA 2008 - Volume 1: IMTA, (VISIGRAPP 2008)},
year={2008},
pages={122-132},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002341001220132},
isbn={978-989-8111-25-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Image Mining Theory and Applications IMTA 2008 - Volume 1: IMTA, (VISIGRAPP 2008)
TI - Learning Probabilistic Models for Recognizing Faces under Pose Variations
SN - 978-989-8111-25-8
AU - Saquib Sarfraz M.
AU - Hellwich O.
PY - 2008
SP - 122
EP - 132
DO - 10.5220/0002341001220132