Multi-nonlinear multi-view locality preserving projections for gait recognition

被引：0

作者：

Chen X.-Y. ^{[1
]}

Kang Y.-Y. ^{[1
]}

Ye X.-B. ^{[2
]}

机构：

[1] College of Mathematics and Computer Science, Fuzhou University, Fuzhou, 350116, Fujian

[2] School of Economics and Management, Fuzhou University, Fuzhou, 350116, Fujian

来源：

Kongzhi Lilun Yu Yingyong/Control Theory and Applications | 2019年 / 36卷 / 05期

基金：

中国国家自然科学基金;

关键词：

Gait recognition; Locality preserving projections; Multiple views; Nonlinear functions;

D O I：

10.7641/CTA.2018.80079

中图分类号：

学科分类号：

摘要：

View variation between register samples and unknown samples is the main factor affecting gait recognition accuracy. The subspace methods can effectively avoid the influence by projecting samples into a common subspace. However, most of them project samples linearly via projection matrices, which cannot maintain the original nonlinear structure of multi-view gait data. To tackle this problem, multi-nonlinear multi-view locality preserving projections is proposed in this paper. The nonlinear projection is realized by the nonlinear functions family, and then samples are projected into common subspace based on the principle of locality preserving projections. Finally, the unknown samples are identified by nearest neighbor classification in the common subspace. Experiments on the CASIA(B) gait database show that the proposed method is superior to other projection methods under multiple combinations of views. © 2019, Editorial Department of Control Theory & Applications South China University of Technology. All right reserved.

引用

页码：783 / 794

页数：11

共 22 条

[1] Liu W., Zhang C., Ma H., Et al., Learning efficient spatial-temporal gait features with deep learning for human identification, Neuroinformatics, 4, pp. 1-15, (2018)
[2] Kwolek B., Krzeszowski T., Michalczuk A., Et al., 3D gait recognition using spatio-temporal motion descriptors, Proceedings of IEEE International Symposium on Intelligent Control, pp. 595-604, (2014)
[3] Jean F., Bergevin R., Albu A.B., Computing and evaluating viewnormalized body part trajectories, Image & Vision Computing, 27, 9, pp. 1272-1284, (2009)
[4] Li F., Sang N., Wang H.Z., Et al., Real-time and robust hand tracking using multiple features, Journal of Control Theory and Applications, 34, 6, pp. 797-802, (2017)
[5] Basfir K., Xiang T., Gong S., Cross view gait recognition using correlation strength, Proceedings of the British Machine Vision Conference: BMVA, pp. 109.1-109.11, (2010)
[6] Ben X.Y., Meng W.X., Yan R., Et al., An improved biometrics technique based on metric learning approach, Neurocomputing, 97, 1, pp. 44-51, (2012)
[7] Ben X.Y., Meng W.X., Yan R., Et al., Kernel coupled distance metric learning for gait recognition and face recognition, Neurocomputing, 120, 10, pp. 577-589, (2013)
[8] Xu W.J., Luo C., Ji A., Et al., Coupled locality preserving projections for cross-view gait recognition, Neurocomputing, 224, C, pp. 37-44, (2016)
[9] Cunningham J.P., Ghahramanih Z., Linear dimensionality reduction: survey, insights, and generalizations, Journal of Machine Learning Research, 16, Dec., pp. 2859-2900, (2015)
[10] Hardoon D.R., Szedmark S., Shawe-Taylor J., Canonical correlation analysis: an overview with application to learning methods, Neural Computation, 16, 12, pp. 2639-2664, (2004)

← 1 2 3 →