LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION

Jihun Hamm, Daniel D. Lee

Abstract

In this paper we tackle the problem of learning the appearances of a person’s face from images with both unknown pose and illumination. The unknown, simultaneous change in pose and illumination makes it difficult to learn 3D face models from data without manual labeling and tracking of features. In comparison, image-based models do not require geometric knowledge of faces but only the statistics of data itself, and therefore are easier to train with images with such variations. We take an image-based approach to the problem and propose a generative model of a warped illumination subspace. Image variations due to illumination change are accounted for by a low-dimensional linear subspace, whereas variations due to pose change are approximated by a geometric warping of images in the subspace. We demonstrate that this model can be efficiently learned via MAP estimation and multiscale registration techniques. With this learned warped subspace we can jointly estimate the pose and the lighting conditions of test images and improve recognition of faces under novel poses and illuminations. We test our algorithm with synthetic faces and real images from the CMU PIE and Yale face databases. The results show improvements in prediction and recognition performance compared to other standard methods.

References

  1. Basri, R. and Jacobs, D. W. (2003). Lambertian reflectance and linear subspaces. IEEE Trans. Pattern Analysis and Machine Intelligence, 25(2):218-233.
  2. Capel, D. and Zisserman, A. (2003). Computer vision applied to super resolution. IEEE Signal Processing Magazine, 20(3):75-86.
  3. Capel, D. P. and Zisserman, A. (2001). Super-resolution from multiple views using learnt image models. In CVPR, volume 2, pages 627-634.
  4. Epstein, R., Hallinan, P., and Yuille, A. (1995). 5 2 Eigenimages suffice: An empirical investigation of low-dimensional lighting models. In Proceedings of IEEE Workshop on Physics-Based Modeling in Computer Vision, pages 108-116.
  5. Frey, B. J. and Jojic, N. (1999). Transformed component analysis: Joint estimation of spatial transformations and image components. In ICCV, page 1190, Washington, DC, USA. IEEE Computer Society.
  6. and Gross, R., Matthews, I., and Baker, S. (2002a). Eigen light-fields and face recognition across pose. In FGR 7802: Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, page 3, Washington, DC, USA. IEEE Computer Society.
  7. Gross, R., Matthews, I., and Baker, S. (2002b). Fisher lightfields for face recognition across pose and illumination. In Proceedings of the 24th DAGM Symposium on Pattern Recognition, pages 481-489, London, UK. Springer-Verlag.
  8. Gunturk, B. K., Batur, A. U., Altunbasak, Y., III, M. H. H., and Mersereau, R. M. (2003). Eigenface-domain super-resolution for face recognition. IEEE Trans. Image Processing, 12(5):597-606.
  9. Hallinan, P. (1994). A low-dimensional representation of human faces for arbitrary lighting conditions. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, pages 995-999.
  10. Hardie, R. C., Barnard, K. J., and Armstrong, E. E. (1997). Joint MAP registration and high-resolution image estimation using a sequence of undersampled images. IEEE Trans. Image Processing, 6(12):1621-1633.
  11. Ramamoorthi, R. (2002). Analytic PCA construction for theoretical analysis of lighting variability in images of a Lambertian object. IEEE Trans. Pattern Analysis and Machine Intelligence, 24(10):1322-1333.
  12. Sim, T., Baker, S., and Bsat, M. (2003). The CMU pose, illumination, and expression (PIE) database. IEEE Trans. Pattern Analysis and Machine Intelligence, 25(12):1615 - 1618.
  13. Tipping, M. E. and Bishop, C. M. (2002). Bayesian image super-resolution. In Becker, S., Thrun, S., and Obermayer, K., editors, NIPS, pages 1279-1286. MIT Press.
  14. Turk, M. and Pentland, A. P. (1991). Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71- 86.
  15. Vasconcelos, N. and Lippman, A. (2005). A multiresolution manifold distance for invariant image similarity. IEEE Trans. Multimedia, 7(1):127-142.
  16. Zhou, S. K. and Chellappa, R. (2004). Illuminating light field: Image-based face recognition across illuminations and poses. In FGR, pages 229-234. IEEE Computer Society.
Download


Paper Citation


in Harvard Style

Hamm J. and D. Lee D. (2008). LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 219-226. DOI: 10.5220/0001076502190226


in Bibtex Style

@conference{visapp08,
author={Jihun Hamm and Daniel D. Lee},
title={LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={219-226},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001076502190226},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION
SN - 978-989-8111-21-0
AU - Hamm J.
AU - D. Lee D.
PY - 2008
SP - 219
EP - 226
DO - 10.5220/0001076502190226