Face Recognition from Images with High Pose Variations by Transform Vector Quantization

  • Amitava Das
  • Manoj Balwani
  • Rahul Thota
  • Prasanta Ghosh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4338)


Pose and illumination variations are the most dominating and persistent challenges haunting face recognition, leading to various highly-complex 2D and 3D model based solutions. We present a novel transform vector quantization (TVQ) method which is fast and accurate and yet significantly less complex than conventional methods. TVQ offers a flexible and customizable way to capture the pose variations. Use of transform such as DCT helps compressing the image data to a small feature vector and judicious use of vector quantization helps to capture the various poses into compact codebooks. A confidence measure based sequence analysis allows the proposed TVQ method to accurately recognize a person in only 3-9 frames (less than 1/2 a second) from a video sequence of images with wide pose variations.


Feature Vector Face Recognition Discrete Cosine Transform Face Image Identification Accuracy 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gersho, A., Gray, R.: Vector Quantization and Signal Compression. Kluwer Academic Publishers, Dordrecht (1992)MATHGoogle Scholar
  2. 2.
    Rao, K., Yip, P.: Discrete Cosine Transform – Algorithms, Advantages, Applications. Academic Publisher, London (1990)MATHGoogle Scholar
  3. 3.
    Zhao, W., Chellappa, R., Rosenfeld, A., Phillips, P.J.: Face recognition: A literature survey. ACM Computing Surveys 35, 399–458 (2003)CrossRefGoogle Scholar
  4. 4.
    Zhou, S., Krueger, V., Chellappa, R.: Probabilistic recognition of human faces from video. Computer Vision and Image Understanding 91, 214–245 (2003)CrossRefGoogle Scholar
  5. 5.
    Kuang-Chih Lee, H., Ming-Hsuan Yang, J., Kriegman, D.: Video-based face recognition using probabilistic appearance manifolds. In: Proc. IEEE CVPR, pp. 313–320 (2003)Google Scholar
  6. 6.
    Turk, M., Pentland, A.: Eigenfaces for recognition. Journal of Cognitive Neuroscience 3(1), 71–86 (1991)CrossRefGoogle Scholar
  7. 7.
    Moghaddam, B., Pentland, A.: Face recognition using view-based and modular eigenspaces. In: Automatic Systems for the Identification and Inspection of Humans. SPIE, vol. 2277 (1994)Google Scholar
  8. 8.
    Phillips P., Grother P., Micheals R., Blackburn D., Tabassi E., and Bone J.: Face recognition vendor test 2002: Evaluation report. Technical Report NISTIR 6965 (2003),
  9. 9.
    Yang, M., Kriegman, D., Ahuja, N.: Detecting Faces in Images: A Survey. IEEE Trans. PAMI 24, 34–58 (2002)Google Scholar
  10. 10.
    Li, Y., Gong, S., Liddell, H.: Video-based face recognition using identity surfaces. Technical report, Queen Mary, University of London (2001)Google Scholar
  11. 11.
    Biuk, Z., Loncaric, S.: Face Recognition from Multi-Pose Image Sequence. In: Proceedings of 2nd Intl. Symposium on Image and Signal Processing, pp. 319–324 (2001)Google Scholar
  12. 12.
    Krueger, V., Zhou, S.: Exemplar-based face recognition from video. In: Proc. ECCV, pp. 732–746 (2002)Google Scholar
  13. 13.
    Aggarwal, G., Roy-Chowdhury, A., Chellappa, R.: A system identification approach for video-based face recognition. In: Proc. ICPR, pp. 23–26 (2004)Google Scholar
  14. 14.
    Gong, S., Psarrou, A., Katsouli, I., Palavouzis, P.: Tracking and Recognition of Face Sequences. In: European Workshop on Combined Real and Synthetic Image Processing for Broadcast and Video Production (1994)Google Scholar
  15. 15.
    Hafed, Z., Levine, M.: Face recognition using the discrete cosine transform. Int. J. Comput. Vision 43(3), 167–188 (2001)MATHCrossRefGoogle Scholar
  16. 16.
    Howell, A., Buxton, H.: Towards unconstrained face recognition from image sequences. In: Proc. Intl. Conf. on Automatic Face Recognition, pp. 224–229 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Amitava Das
    • 1
  • Manoj Balwani
    • 1
  • Rahul Thota
    • 1
  • Prasanta Ghosh
    • 1
  1. 1.Microsoft Research IndiaBangaloreIndia

Personalised recommendations