A synthesized computer recognition system for human hands
A computer recognition system for human hands is presented in this paper. The system is based on infrared images. A multi-grid normalization technique is developed to normalize the position of the hand and fingers. Sets of geometric features, Zernike moment features and algebraic features are used in a two-stage recognition scheme. The system works very well on 300 hand samples of 30 persons with a 97% discrimination rate.
Unable to display preview. Download preview PDF.
- 1.M. Turk and A. Pentland: Eigenfaces for recognition. Journal of Cognitive Neuroscience, March 1991.Google Scholar
- 2.J.H. Ma, R.L. Zhao and S.D. Ma: Infrared eigenhands for human recognition. In Proceeding of The 1st Asian Conference on Computer Vision, Osaka, Japan, 1993.Google Scholar
- 3.M.R. Teague: Image analysis via the general theory of moments. J. Opt. Soc. Am., Vol.70, No.8, August 1980.Google Scholar
- 4.B.C. Li and J. Shen: Fast computation of moment invariant. Pattern Recognition 24, 1991.Google Scholar