Gait Recognition Using Principal Curves and Neural Networks

  • Han Su
  • Fenggang Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)


This paper presents a new method for human model-free gait recognition using principal curves analysis and neural networks. Principal curves are non-parametric, nonlinear generalizations of principal component analysis, and give a breakthrough to nonlinear principal component analysis. Different from the traditional statistical analysis methods, principal curve analysis seeks lower-dimensional manifolds for every class respectively, and forms the nonlinear summarization of the sample features and directions for each class. Neural network with the virtue of its universal approximation property is an outstanding method to model the nonlinear function of principal curve. Firstly, a background subtraction is used to separate objects from background. Secondly, we extract the contour of silhouettes and represent the spatio-temporal features. Finally, we use principal curves and neural networks to analyze the features to train and test gait sequences. Recognition results demonstrate that our method has encouraging recognition performance.


Principal Curve Gait Feature Gait Recognition Projection Index Nonlinear Principal Component Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Nixon, M.S., Carter, J.N.: Advances in Automatic Gait Recognition. In: Proc. of IEEE Face and Gesture Analysis, Seoul, Korea, pp. 11–16 (2004)Google Scholar
  2. Wang, L., Tan, T.N., Ning, H.Z., Hu, W.M.: Silhouette Analysis-Based Gait Recognition for Human Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(12), 1505–1528 (2003)CrossRefGoogle Scholar
  3. Lee, L., Grimson, W.: Gait Analysis for Recognition and Classification. In: Proc. of Intl. Conf. on Automatic Face and Gesture Recognition, pp. 155–162 (2002)Google Scholar
  4. Abdelkader, C.B., Cutler, R., Nanda, H., Davis, L.: EigenGait: Motion-Based Recognition Using Image Self- Similarity. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 284–294. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  5. Phillips, P.J., Sakar, S., Robledo, I., Grother, P., Bowyer, K.: The Gait Identification Challenge Problem: Data Sets and Baseline Algorithm. In: Proc. of Intl. Conf. on Pattern Recognition, Québec, Canada, pp. 385–388 (2002)Google Scholar
  6. Hastie, T.: Principal Curves and Surfaces. USA, Stanford Univ. (1984)Google Scholar
  7. Chang, K.Y.: Nonlinear Dimensionality Reduction Using Probabilistic Principal Surfaces. USA, Texas Univ. (2000)Google Scholar
  8. Dong, D., McAvoy, T.J.: Nonlinear Principal Component Analysis Based on Principal Curves and Neural Networks. Computers Chemistry Engineering 20(1), 65–78 (1995)CrossRefGoogle Scholar
  9. Su, H., Huang, F.G.: A New Method for Human Gait Recognition Using Temporal Analysis. In: Hao, Y., Liu, J., Wang, Y.-P., Cheung, Y.-m., Yin, H., Jiao, L., Ma, J., Jiao, Y.-C. (eds.) CIS 2005. LNCS (LNAI), vol. 3801, pp. 1039–1044. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Han Su
    • 1
    • 2
  • Fenggang Huang
    • 1
  1. 1.School of Computer Science and TechnologyHarbin Engineering UniversityChina
  2. 2.School of Computer ScienceSichuan Normal UniversityChengduChina

Personalised recommendations