Machine Learning Approach for Gesture Recognition Based on Automatic Feature Selection

  • Xiubo Liang
  • Franck Multon
  • Weidong Geng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7660)


In this paper we propose a machine learning approach to design strong classifiers based on the most relevant combination of 1444 weak classifiers based on pose parameters. This classifier is embedded in a three-layers recognition system which enables us to recognize 70 different gestures performed by various users with high style variability; the recognition ratio is 97.5% with our approach.


gesture recognition sign language machine learning HMM automatic feature selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fang, G., Gao, W., Zhao, D.: Large vocabulary sign language recognition based on hierarchical decision trees. In: ICMI 2003, pp. 125–131 (2003)Google Scholar
  2. 2.
    Munib, Q., Habeeb, M., Takruri, B., et al.: American sign language (ASL) recognition based on Hough transform and neural networks. Expert Systems with Applications 32(1), 24–37 (2007)CrossRefGoogle Scholar
  3. 3.
    Yang, R., Sarkar, S.: Coupled grouping and matching for sign and gesture recognition. Comput. Vis. Image Underst. 113(6), 663–681 (2009)CrossRefGoogle Scholar
  4. 4.
    Liang, X., Li, Q., Zhang, X., Zhang, S., Geng, W.: Performance-driven motion choreographing with accelerometers. Computer Animation and Virtual Worlds 20(2-3), 89–99 (2009)CrossRefGoogle Scholar
  5. 5.
    Viola, P., Jones, M.: Robust Real-Time Face Detection. Int. J. Comput. Vision 57, 137–154 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Xiubo Liang
    • 1
  • Franck Multon
    • 2
    • 3
  • Weidong Geng
    • 4
  1. 1.College of Software TechnologyZhejiang UniversityNingboChina
  2. 2.M2S, University Rennes2RennesFrance
  3. 3.MimeTICINRIA Rennes, Campus Universitaire de BeaulieuRennesFrance
  4. 4.State Key Lab of CAD&CGZhejiang UniversityHangzhouChina

Personalised recommendations