Git Recognition with Incomplete GEI Based on Random Forests

Abstract:

Abstract. This paper proposes an incomplete GEI gait recognition method based on Random Forests. There are numerous methods exist for git recognition,but they all lead to high dimensional feature spaces. To address the problem of high dimensional feature space, we propose the use of the Random Forest algorithm to rank features' importance . In order to efficiently search throughout subspaces, we apply a backward feature elimination search strategy.This demonstrate static areas of a GEI also contain useful information.Then, we project the selected feature to a low-dimensional feature subspace via the newly proposed two-dimensional locality preserving projections (2DLPP) method.Asa sequence,we further improve the discriminative power of the extracted features. Experimental results on the CASIA gait database demonstrate the effectiveness of the proposed method.

• Periodical: Applied Mechanics and Materials (Volumes 519-520)
• Pages: 661-666
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.519-520.661
• Online since: February 2014
• Authors: Qing Zhu, Jie Zhang*
• Keywords: 2DLPP, Gait Recognition, Incomplete GEI, Random Forest Algorithm

References

[1] G. Johansson, Visual perception of biological motion and a model for its analysis, Atten. Percept. Psychophysiol. 14 (2) (1973) 201–211.

[2] C. BenAbdelkader, R. Cutler, L. Davis, Gait recognition using image self-similarity,J. Appl. Signal Process. (2004) 572–585.

DOI: 10.1155/s1110865704309236

[3] J. Hayfron-Acquah, M. Nixon, J. Carter, Automatic gait recognition by symmetry analysis, Pattern Recognit. Lett. 24 (13) (2003) 2175–2183.

DOI: 10.1016/s0167-8655(03)00086-2

[4] D. Tao, X. Li, X. Wu, S. Maybank, General tensor discriminant analysis and gabor features for gait recognition, IEEE Trans. Pattern Anal. Mach. Intell. (2007) 1700–1715.

DOI: 10.1109/tpami.2007.1096

[5] J. Han, B. Bhanu, Individual recognition using gait energy image, IEEE Trans. Pattern Anal. Mach. Intell. 28 (2) (2006)316–322.

DOI: 10.1109/tpami.2006.38

[6] C. Chen, J. Liang, H. Zhao, H. Hu, J. Tian, Frame difference energy image for gait recognition with incomplete silhouettes, Pattern Recognit. Lett. 30 (11) (2009) 977–984.

DOI: 10.1016/j.patrec.2009.04.012

[7] K. Bashir, T. Xiang, S. Gong, Feature selection on gait energy image for human identification, IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2008, p.985–988.

DOI: 10.1109/icassp.2008.4517777

[8] K. Bashir, T. Xiang, S. Gong, Gait recognition using gait entropy image, 3rd International Conference on Crime Detection and Prevention, IET, 2009, p.1–6.

DOI: 10.1049/ic.2009.0230

[9] D. Aha, R. Bankert, A comparative evaluation of sequential feature selection algorithms, Lecture Notes in Statistics, Springer, 1996. 199–206.

DOI: 10.1007/978-1-4612-2404-4_19

[10] I. Guyon, A. Elisseeff, An introduction to variable and feature selection, J. Mach. Learn. Res. 3 (2003) 1157–1182.

[11] B. Guo, M. Nixon, Gait feature subset selection by mutual information, IEEE Trans. Syst. Man Cybern. Syst. Hum. 39 (1) (2009) 36–46.

DOI: 10.1109/tsmca.2008.2007977

[12] J. Doak, An evaluation of feature selection methods and their application to computer security, Tech. Rep., Technical Report CSE-92-18, University of California at Davis, (1992).

[13] R. Caruana, D. Freitag, Greedy attribute selection, International Conference on Machine Learning, (1994).

[14] S. Yu, D. Tan, T. Tan, A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition, Pattern Recognit. (2006) 441–444.

DOI: 10.1109/icpr.2006.67

[15] S. Chen, H. Zhao, M. Kong, B. Luo, 2D-LPP: a two-dimensional extension of locality preserving projections, Neurocomputing 70(2007) 912–921.

DOI: 10.1016/j.neucom.2006.10.032