Gesture recognition from image motion based on subspace method and HMM

  • Yoshio Iwai
  • Tadashi Rata
  • Masahiko Yachida
Poster Session III
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)


This paper proposes a method to recognize human gestures from an image sequence based on Hidden Markov Model and Karhunen-Lo`eve Transform. As our method uses the motion vector field of the scene for recognition, it is robust for variety in the background of the scene and it doesn't require the users to wear a sensor or a marker. The motion vector field of the scene is projected to an eigen-subspace for data compression and is used as the input symbols for the HMM. View-based methods generally fail when the user translates. Our method is robust for recognition to the user's translation because the recognition window automatically fits the user by tracking the user's face.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Katsuhiko Takahashi, Susumu Seki, and Ryuichi Oka. Spotting recognition of human gestures from motion images. PRU 92-157, IEICE, Mar 1993.Google Scholar
  2. 2.
    Junji Yamato, Shoji Kurakake, Akira Tomono, and Kenichiro Ishii. Human action recognition using HMM with category-separated vector quantization. IEICE, J77D-II(7):1311–1318, Jul 1994.Google Scholar
  3. 3.
    Lee W. Campbell, David A. Becker, Ali Azarbayejani, Aaron F. Bobick, and Alex Pentland. Invariant features for 3D gesture recognition. In International Conference on Automatic Face and Gesture Recognition, pp. 157–162, Killington, Oct 1996.Google Scholar
  4. 4.
    Takahiro Watanabe, Akitoshi Tsukamoto, Chil-Woo Lee, and Masahiko Yachida. Gesture recognition using multiple silhouette models for a real-time interactive system. In Asian Conference on Computer Vision, Vol. 2, pp. 235–239, 1995.Google Scholar
  5. 5.
    Shigeki Nagaya, Susumu Seki, and Ryuichi Oka. A theoretical consideration of pattern space trajectory-for gesture spotting recognition. In International Conference on Automatic Face and Gesture Recognition, pp. 72–77, Oct 1996.Google Scholar
  6. 6.
    Haiyuan Wu, Qian Chen, and Masahiko Yachida. A fuzzy theory based face detector. In International Conference on Pattern Recognition, Vol. 3, pp. 406–410, 1996.Google Scholar
  7. 7.
    Errki Oja. Subspace Methods of Pattern Recognition. Research Studies Press, 1983.Google Scholar
  8. 8.
    Hiroshi Murase and Shree K. Nayar. 3d object recognition from appearance — parametric eigenspace method. IEICE, J77-D-II(11):2179–2187, Nov 1994.Google Scholar
  9. 9.
    Lawrence R. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of IEEE., 77(2):257–285, 1989.Google Scholar
  10. 10.
    G. Rigoll, A. Kosmala, J. Rottland, and C. Neukirchen. A comparison between continuous and discrete density hidden markov models for cursive handwriting recognition. Vol. 2, pp. 205–209, 1996.Google Scholar
  11. 11.
    Hiroshi Murase and Shree K. Nayar. Illumination planning for object recognition in structure environments. pp. 31–38, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Yoshio Iwai
    • 1
  • Tadashi Rata
    • 1
  • Masahiko Yachida
    • 1
  1. 1.Department of Systems and Human ScienceOsaka UniversityToyonaka OsakaJapan

Personalised recommendations