Browse > Article

A Study on Vision-based Robust Hand-Posture Recognition Using Reinforcement Learning  

Jang Hyo-Young (Department of Electrical Engineering and Computer Science, KAIST)
Bien Zeung-Nam (Department of Electrical Engineering and Computer Science, KAIST)
Publication Information
Journal of the Institute of Electronics Engineers of Korea CI / v.43, no.3, 2006 , pp. 39-49 More about this Journal
Abstract
This paper proposes a hand-posture recognition method using reinforcement learning for the performance improvement of vision-based hand-posture recognition. The difficulties in vision-based hand-posture recognition lie in viewing direction dependency and self-occlusion problem due to the high degree-of-freedom of human hand. General approaches to deal with these problems include multiple camera approach and methods of limiting the relative angle between cameras and the user's hand. In the case of using multiple cameras, however, fusion techniques to induce the final decision should be considered. Limiting the angle of user's hand restricts the user's freedom. The proposed method combines angular features and appearance features to describe hand-postures by a two-layered data structure and reinforcement learning. The validity of the proposed method is evaluated by appling it to the hand-posture recognition system using three cameras.
Keywords
hand-posture recognition; reinforcement learning; view-invariant;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J. Hu and M. P. Wellman, Multiagent reinforceme learning: theoretical framework and an algorithm, Proc. of Int'l Conf. of Machine Learning, 1998
2 U. Brockl-Fox, 'Realtime 3-D Interaction with up to 16 degrees of freedom from monocular video image flows,' Proc. of Int. Workshop on Automatic Face and Gesture Recognition, pp.172-178, 1995
3 H. H. Buelthoff, S. Y. Edelman, and M. J. Tarr, 'How are three-dimensional objects represented in the brain?,' A. I. memo no. 1479, Artificial intelligence lab., Massachusetts Institute of Technology, 1994
4 Jung-Bae Kim, Kwang-Hyun Park, Won-Chul Bang and Z. Zenn Bien, 'Continuous gesture recognition system for Korean sign language based on fuzzy logic and hidden markov model,' Proc. of FUZZ-IEEE, 2000
5 B. Moghaddam and A. Penmtland, 'Maximum likelihood detection of faces and hands,' Proc. of Int. Workshop on Automatic Face and Gesture Recognition, pp. 122-128, 1995
6 D. Lowe, 'Fitting parameterized, three dimensional models to images,' IEEE Trans., PAMI, vol.13, no.5, pp.441-450, 1991   DOI   ScienceOn
7 J. M. Rehg and T. Kanede, 'Visual tracking of high DOF articulated structures: an application to human hand tracking,' Proc. of ECCV'94, pp.35-46, 1994
8 Ernest Gardner, Gardner-Gray-O'Rahillv anatomy : a regional study of human structure, Saunders, 1986
9 석동일, 한국 수화의 언어학적 분석, 박사 학위 논문, 대구대학교, 1989
10 Chan-Su Lee, Sang-Won Ghyme, Chan-Jong Park, and Kwang-Yun Wohn, 'Virtual reality software and technology archive,' Proc. of the ACM symposium on virtual realityzxsdhg and technology 1998, pp.59-65, 1998   DOI
11 Mark Weiser, The Computer for 21st century, Sci. Amer., 1991