A Subblock Matrix Approach to Data-Reduction in Gait Recognition

Abstract:

We propose a novel method for data reduction in gait recognition, called Subblock Complete Two Dimensional Principal Component Analysis (SbC2DPCA). GEIs were divided into smaller sub-images and redundant subblocks were adaptively removed. Complete Two Dimensional Principal Component Analysis (C2DPCA) was then applied to every sub-image directly, to acquire a set of projection sub-vectors for both row and column directions and these were synthesized into whole features for subsequent classification using nearest neighbor classifier. We evaluate the proposed gait recognition method on the CASIA gait database. The experimental results and analysis show the recognition accuracy of SbC2DPCA to be superior to C2DPCA, with C2DPCA being a special case of SbC2DPCA. The novelty of the proposed method lies in the adaptive removal of redundant data while extracting local features. This translates to data reduction with very minimal loss of information, as demonstrated by the remarkable recognition accuracy when subjects change clothing or have a backpack.

• Periodical: Advanced Materials Research (Volumes 181-182)
• Pages: 902-907
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.181-182.902
• Online since: January 2011
• Authors: Xian Ye Ben, Shi An, Jian Wang, Hai Yang Liu
• Keywords: Complete Two Dimensional Principal Component Analysis (C2DPCA), Gait Energy Image (GEI), Gait Recognition, Subblock Complete Two Dimensional Principal Component Analysis (SbC2DPCA)

References

[1] WANG Kejun; HOU Benbo: A Survey of Gait Recognition. Journal of Image and Graphics, Vol. 12, 7 (2007), pp.1152-1160.

[2] Xuelong Li, S. Lin, Shuicheng Yan, et al: Discriminant Locally Linear Embedding With High-Order Tensor Data. IEEE Transactions on Systems, Man, and Cybernetics, Part B, Vol. 38, 2(2008), pp.342-352.

DOI: 10.1109/tsmcb.2007.911536

[3] Chiraz BenAbdelkader1, Ross Cutlerz, Larry Davis1: View-invariant Estimation of Height and Stride for Gait Recognition. Biometric Authentication, (2002), pp.155-167.

DOI: 10.1007/3-540-47917-1_16

[4] J. HAN, B. BHANU: Individual Recognition using Gait Energy Image. Proceedings of the IEEE Conference on Block Analysis and Machine Intelligence, Vol. 28, 2(2006), pp.316-322.

DOI: 10.1109/tpami.2006.38

[5] K. Bashir, Tao Xiang, Shaogang Gong: Feature selection on Gait Energy Image for human identification. IEEE International Conference on Acoustics, Speech and Signal Processing(2008), pp.985-988.

DOI: 10.1109/icassp.2008.4517777

[6] D. Xu, S. Yan, D. Tao, et al: Human Gait Recognition with Matrix Representation. IEEE Trans. on Circuits Systems for Video Technology (T-CSVT), Vol. 16, 7(2006), pp.896-903.

DOI: 10.1109/tcsvt.2006.877418

[7] Yang Jian, Zhang David, F. Alejandro, et al: Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition. IEEE transactions on Pattern Analysis and Machine Intelligence, Vol. 26, 1(2004), pp.131-137.

DOI: 10.1109/tpami.2004.1261097

[8] XU Anbang, JIN Xin, JIANG Yugang, et al: Complete Two-Dimensional PCA for Face Recognition. 18th International Conference on Pattern Recognition, Vol. 3(2006), pp.481-484.

DOI: 10.1109/icpr.2006.395

[9] Tan Keren, Chen Songcan: Adaptively weighted subblock PCA for face recognition. Neurocomputing, Vol. 64(2005), pp.505-511.

DOI: 10.1016/j.neucom.2004.10.113