Dynamic Hand Gesture Recognition Using Kinematic Features Based on Hidden Markov Model

  • Haibo Pang
  • Youdong Ding
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 227)


The ability to recognize humans and their activities by vision is a key for a machine to interact intelligently and effortlessly with a human machine interface environment. In this paper, we exploit multiple cues including divergence features, vorticity features, and hand motion direction vector. Divergence fields and vorticity fields are derived from the optical flow for hand gesture recognition in hand gesture videos. We perform principle component analysis method to extract their features, and find the hand cancroids position for all frames by using hand tracking algorithm, acquire the motion direction vector. At last, we use the traditional HMM to verify these features. In our experiments, we had experimented 12 isolated gestures. The experimental results show these features have good performance.


Hand gesture recognition Kinematic features Principal component analysis Motion direction vector Hidden Markov model 



This work is supported partially by Shanghai Educational Committee Leading Academic Discipline Project (No. J50103) and Shanghai Science and Technology Key Research Project (11511503300).


  1. 1.
    Johansson G (1973) Visual perception of biological motion and a model for its analysis. Percept Psychophysics 4(14):201–211CrossRefGoogle Scholar
  2. 2.
    Mitra S, Acharya T (2007) Gesture recognition: a survey. IEEE Trans Syst Man Cybern Part C Appl Rev 37(3):311–324Google Scholar
  3. 3.
    Pavlovic V, Sharma R, Huang T (1997) Visual interpretation of hand gestures for human–computer interaction: a review. IEEE Trans Pattern Anal Mach Intell 19(7):677–695CrossRefGoogle Scholar
  4. 4.
    Aggarwal J, Cai Q (1999) Human motion analysis—a review. Comput Vis Image Underst 73(3):428–440CrossRefGoogle Scholar
  5. 5.
    Just A, Marcel S (2009) A comparative study of two state-of-the-art sequence processing techniques for hand gesture recognition. Comput Vis Image Underst 1(13):532–543CrossRefGoogle Scholar
  6. 6.
    Kale A, Rajagopalan A, Sundaresan A, Cuntoor N, RoyChowdhury A, Krueger V, Chellappa R (2004) Identification of humans using gait. IEEE Trans Image Process 13(9):1163–1173CrossRefGoogle Scholar
  7. 7.
    Du Y, Chen F, Xu W, Li Y (2006) Recognizing interaction activities using dynamic Bayesian network. In: Proceedings of IEEE international conference on pattern recognition, vol 3(1). Hong Kong, China, pp 618–621Google Scholar
  8. 8.
    Kang H, Lee CW, Jung K (2004) Recognition-based gesture spotting in video games. Pattern Recogn Lett (25):1701–1714Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina

Personalised recommendations