Investigation of New Gait Representations for Improving Gait Recognition

Authors: Chirawat Wattanapanich, Hong Wei

Abstract:

This study presents new gait representations for improving gait recognition accuracy on cross gait appearances, such as normal walking, wearing a coat and carrying a bag. Based on the Gait Energy Image (GEI), two ideas are implemented to generate new gait representations. One is to append lower knee regions to the original GEI, and the other is to apply convolutional operations to the GEI and its variants. A set of new gait representations are created and used for training multi-class Support Vector Machines (SVMs). Tests are conducted on the CASIA dataset B. Various combinations of the gait representations with different convolutional kernel size and different numbers of kernels used in the convolutional processes are examined. Both the entire images as features and reduced dimensional features by Principal Component Analysis (PCA) are tested in gait recognition. Interestingly, both new techniques, appending the lower knee regions to the original GEI and convolutional GEI, can significantly contribute to the performance improvement in the gait recognition. The experimental results have shown that the average recognition rate can be improved from 75.65% to 87.50%.

Keywords: Convolutional image, lower knee, gait.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1314588

References:

[1] J. Han and B. Bhanu, "Individual recognition using gait energy image," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 28, pp. 316-322, 2006.
[2] Z. Liu and S. Sarkar, "Simplest representation yet for gait recognition: averaged silhouette," in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, 2004, pp. 211-214 Vol.4.
[3] K. Bashir, X. Tao, and G. Shaogang, "Gait recognition using Gait Entropy Image," in Crime Detection and Prevention (ICDP 2009), 3rd International Conference on, 2009, pp. 1-6.
[4] P. Arora and S. Srivastava, "Gait recognition using gait Gaussian image," in Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on, 2015, pp. 791-794.
[5] Y. Yang, D. Tu, and G. Li, "Gait Recognition Using Flow Histogram Energy Image," in Pattern Recognition (ICPR), 2014 22nd International Conference on, 2014, pp. 444-449.
[6] P. Arora, S. Srivastava, K. Arora, and S. Bareja, "Improved Gait Recognition Using Gradient Histogram Gaussian Image," Procedia Computer Science, vol. 58, pp. 408-413, // 2015.
[7] P. Arora, M. Hanmandlu, and S. Srivastava, "Gait based authentication using gait information image features," Pattern Recognition Letters, vol. 68, Part 2, pp. 336-342, 12/15/ 2015.
[8] S. Zheng, J. G. Zhang, K. Q. Huang, R. He, and T. N. Tan, "Robust View Transformation Model for Gait Recognition," 2011 18th IEEE International Conference on Image Processing (Icip), 2011.
[9] G. Chetty, P. Yarlagadda, V. Madasu, and A. Mishra, "Multiview gait biometrics for human identity recognition," in Computing for Sustainable Global Development (INDIACom), 2014 International Conference on, 2014, pp. 358-363.
[10] H. Xue and Z. Hao, "Gait recognition based on gait energy image and linear discriminant analysis," in Signal Processing, Communications and Computing (ICSPCC), 2015 IEEE International Conference on, 2015, pp. 1-4.
[11] L. Zhihui, X. Yong, J. Zhong, and D. Zhang, "Human Gait Recognition via Sparse Discriminant Projection Learning," Circuits and Systems for Video Technology, IEEE Transactions on, vol. 24, pp. 1651-1662, 2014.
[12] M. Alotaibi and A. Mahmood, "Improved Gait recognition based on specialized deep convolutional neural networks," in 2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), 2015, pp. 1-7.
[13] K. Shiraga, Y. Makihara, D. Muramatsu, T. Echigo, and Y. Yagi, "GEINet: View-invariant gait recognition using a convolutional neural network," in 2016 International Conference on Biometrics (ICB), 2016, pp. 1-8.
[14] T. Wolf, M. Babaee, and G. Rigoll, "Multi-view gait recognition using 3D convolutional neural networks," in 2016 IEEE International Conference on Image Processing (ICIP), 2016, pp. 4165-4169.
[15] C. Luo, W. Xu, and C. Zhu, "Robust gait recognition based on partitioning and canonical correlation analysis," in Imaging Systems and Techniques (IST), 2015 IEEE International Conference on, 2015, pp. 1-5.
[16] J. B. Flora, D. F. Lochtefeld, D. A. Bruening, and K. M. Iftekharuddin, "Improved Gender Classification Using Nonpathological Gait Kinematics in Full-Motion Video," Human-Machine Systems, IEEE Transactions on, vol. 45, pp. 304-314, 2015.
[17] D. Das, "Human gait classification using combined HMM & SVM hybrid classifier," in Electronic Design, Computer Networks & Automated Verification (EDCAV), 2015 International Conference on, 2015, pp. 169-174.
[18] Z. Wu, Y. Huang, L. Wang, X. Wang, and T. Tan, "A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 209-226, 2017.
[19] S. Yu, D. Tan, and T. Tan, "A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition," in Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, 2006, pp. 441-444.
[20] D. Matovski, "Extending quality and covariate analyses for gait biometrics," Doctoral, Faculty of Physical & Applied Science, University of Southampton, 2013.
[21] I. Rida, X. Jiang, and G. L. Marcialis, "Human Body Part Selection by Group Lasso of Motion for Model-Free Gait Recognition," IEEE Signal Processing Letters, vol. 23, pp. 154-158, 2016.
[22] Z. Luo, T. Yang, and Y. Liu, "Gait optical flow image decomposition for human recognition," in 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference, 2016, pp. 581-586.
[23] Y. D. Guan, R. F. Zhu, J. Y. Feng, K. Du, and X. R. Zhang, "Research on Algorithm of Human Gait Recognition Based on Sparse Representation," in 2016 Sixth International Conference on Instrumentation & Measurement, Computer, Communication and Control (IMCCC), 2016, pp. 405-410.
[24] J. Lamar-Leon, R. Alonso-Baryolo, E. Garcia-Reyes, and R. Gonzalez-Diaz, "Persistent homology-based gait recognition robust to upper body variations," in 2016 23rd International Conference on Pattern Recognition (ICPR), 2016, pp. 1083-1088.
[25] A. O. Lishani, L. Boubchir, E. Khalifa, and A. Bouridane, "Gabor filter bank-based GEI features for human Gait recognition," in 2016 39th International Conference on Telecommunications and Signal Processing (TSP), 2016, pp. 648-651.
[26] I. Rida, L. Boubchir, N. Al-Maadeed, S. Al-Maadeed, and A. Bouridane, "Robust model-free gait recognition by statistical dependency feature selection and Globality-Locality Preserving Projections," in 2016 39th International Conference on Telecommunications and Signal Processing (TSP), 2016, pp. 652-655.
[27] M. Alotaibi and A. Mahmood, "Reduction of Gait Covariate Factors Using Feature Selection and Sparse Dictionary Learning," in 2016 IEEE International Symposium on Multimedia (ISM), 2016, pp. 337-340.