Hybrid Face Recognition Based on Real-Time Multi-camera Stereo-Matching

  • J. Hensler
  • K. Denker
  • M. Franz
  • G. Umlauf
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6939)


Multi-camera systems and GPU-based stereo-matching methods allow for a real-time 3d reconstruction of faces. We use the data generated by such a 3d reconstruction for a hybrid face recognition system based on color, accuracy, and depth information. This system is structured in two subsequent phases: geometry-based data preparation and face recognition using wavelets and the AdaBoost algorithm. It requires only one reference image per person. On a data base of 500 recordings, our system achieved detection rates ranging from 95% to 97% with a false detection rate of 2% to 3%. The computation of the whole process takes around 1.1 seconds.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Denker, K., Umlauf, G.: Accurate real-time multi-camera stereo-matching on the gpu for 3d reconstruction. Journal of WSCG 19, 9–16 (2011)Google Scholar
  2. 2.
    Pan, G., Han, S., Wu, Z., Wang, Y.: 3D face recognition using mapped depth images. In: IEEE Conf. on Computer Vision and Pattern Recognition, pp. 175–181 (2005)Google Scholar
  3. 3.
    Turk, M., Pentland, A.: Eigenfaces for recognition. Cognitive Neuroscience 3, 71–86 (1991)CrossRefGoogle Scholar
  4. 4.
    Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: SIGGRAPH 1999, pp. 187–194 (1999)Google Scholar
  5. 5.
    Blanz, V., Romdhani, S.: Face identification across different poses and illuminations with a 3d morphable model. In: Int’l. Conf. on Automatic Face and Gesture Recognition, pp. 202–2007 (2002)Google Scholar
  6. 6.
    Weyrauch, B., Huang, J., Heisele, B., Blanz, V.: Component-based face recognition with 3d morphable models. In: Workshop on Face Processing in Video, pp. 1–5 (2003)Google Scholar
  7. 7.
    Lee, Y., Song, H., Yang, U., Shin, H., Sohn, K.: Local feature based 3D face recognition. In: Kanade, T., Jain, A., Ratha, N.K. (eds.) AVBPA 2005. LNCS, vol. 3546, pp. 909–918. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Lee, J., Kuo, C., Hus, C.: 3d face recognition system based on feature analysis and support vector machine. In: IEEE TENCON 2004, pp. 144–147 (2004)Google Scholar
  9. 9.
    Cook, J., Ch, V., Sridharan, S., Fookes, C.: Face recognition from 3d data using iterative closest point algorithm and Gaussian mixture models. In: 2nd Int’l. Symp. 3D Data Processing, Visualization, and Transmission, pp. 502–509 (2004)Google Scholar
  10. 10.
    Wang, J., Oliveira, M.: A hole-filling strategy for reconstruction of smooth surfaces in range images. In: SIBGRAPI 2003, pp. 11–18 (2003)Google Scholar
  11. 11.
    Besl, P., McKay, N.: A method for registration of 3-D shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence, 239–256 (1992)Google Scholar
  12. 12.
    Rusinkiewicz, S., Levoy, M.: Efficient variants of the ICP algorithm. In: 3dim, p. 145. IEEE Computer Society, Los Alamitos (2001)Google Scholar
  13. 13.
    Freedman, D., Diaconis, P.: On the histogram as a density estimator: L2 theory. Probability Theory and Related Fields 57, 453–476 (1981)zbMATHGoogle Scholar
  14. 14.
    Lamard, M., Cazuguel, G., Quellec, G., Bekri, L., Roux, C., Cochener, B.: Content based image retrieval based on wavelet transform coefficients distribution. In: 29th IEEE Conf. of the Engineering in Medicine and Biology Society, pp. 4532–4535 (2007)Google Scholar
  15. 15.
    Varanasi, M., Aazhang, B.: Parametric generalized Gaussian density estimation. J. of the Acoustical Society of America 86, 1404 (1989)CrossRefGoogle Scholar
  16. 16.
    Do, M., Vetterli, M.: Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance. IEEE Trans. on Image Processing 11, 146–158 (2002)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22, 79–86 (1951)MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Hensler, J., Blaich, M., Bittel, O.: Improved door detection fusing camera and laser rangefinder data with AdaBoosting. In: 3rd Int.’l Conf. on Agents and Artificial Intelligence, pp. 39–48 (2011)Google Scholar
  19. 19.
    Schapire, R.: A brief introduction to boosting. In: International Joint Conference on Artificial Intelligence, vol. 16, pp. 1401–1406 (1999)Google Scholar
  20. 20.
    Bowyer, K., Chang, K., Flynn, P.: A survey of approaches and challenges in 3d and multi-modal 3d+2d face recognition. Computer Vision and Image Understanding 101, 1–15 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • J. Hensler
    • 1
  • K. Denker
    • 1
  • M. Franz
    • 1
  • G. Umlauf
    • 1
  1. 1.University of Applied SciencesConstanceGermany

Personalised recommendations