Gait Recognition by Ranking

  • Raúl Martín-Félez
  • Tao Xiang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7572)


The advantage of gait over other biometrics such as face or fingerprint is that it can operate from a distance and without subject cooperation. However, this also makes gait subject to changes in various covariate conditions including carrying, clothing, surface and view angle. Existing approaches attempt to address these condition changes by feature selection, feature transformation or discriminant subspace learning. However, they suffer from lack of training samples from each subject, can only cope with changes in a subset of conditions with limited success, and are based on the invalid assumption that the covariate conditions are known a priori. They are thus unable to perform gait recognition under a genuine uncooperative setting. We propose a novel approach which casts gait recognition as a bipartite ranking problem and leverages training samples from different classes/people and even from different datasets. This makes our approach suitable for recognition under a genuine uncooperative setting and robust against any covariate types, as demonstrated by our extensive experiments.


Gait recognition Learning to rank Transfer learning 


  1. 1.
    Aghajanian, J., Warrell, J., Prince, S.J., Li, P., Rohn, J., Baum, B.: Patch-based within-object classification. In: ICCV, pp. 1125–1132 (2009)Google Scholar
  2. 2.
    Bashir, K., Xiang, T., Gong, S.: Cross view gait recognition using correlation strength. In: BMVC, pp. 1–11 (2010)Google Scholar
  3. 3.
    Bashir, K., Xiang, T., Gong, S.: Gait recognition without subject cooperation. Pattern Recognition Letters 31(13), 2052–2060 (2010)CrossRefGoogle Scholar
  4. 4.
    Cao, T.S.L., Liu, Z., Huang: Cross-dataset action detection. In: CVPR, pp. 1998–2005 (2010)Google Scholar
  5. 5.
    CASIA: CASIA Gait Database (2005),
  6. 6.
    Chapelle, O., Keerthi, S.: Efficient algorithms for ranking with SVMs. Information Retrieval 13, 201–215 (2010)CrossRefGoogle Scholar
  7. 7.
    Damen, D., Hogg, D.C.: Detecting Carried Objects in Short Video Sequences. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 154–167. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  8. 8.
    Freund, Y., Iyer, R., Schapire, R.E., Singer, Y.: An efficient boosting algorithm for combining preferences. Journal of Machine Learning Research 4, 933–969 (2003)MathSciNetGoogle Scholar
  9. 9.
    Han, J., Bhanu, B.: Individual recognition using Gait Energy Image. PAMI 28(2), 316–322 (2006)CrossRefGoogle Scholar
  10. 10.
    Joachims, T.: Optimizing search engines using clickthrough data. In: ACM SIGKDD, pp. 133–142 (2002)Google Scholar
  11. 11.
    Kusakunniran, W., Wu, Q., Zhang, J., Li, H.: Support Vector Regression for multi-view gait recognition based on local motion feature selection. In: CVPR, pp. 974–981 (2010)Google Scholar
  12. 12.
    Lee, H., Hong, S., Kim, E.: An efficient gait recognition with backpack removal. EURASIP J. Adv. Signal Process 2009, 46:1–46:7 (2009)Google Scholar
  13. 13.
    Makihara, Y., Sagawa, R., Mukaigawa, Y., Echigo, T., Yagi, Y.: Gait Recognition Using a View Transformation Model in the Frequency Domain. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part III. LNCS, vol. 3953, pp. 151–163. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Phillips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The feret evaluation methodology for face-recognition algorithms. PAMI 22(10), 1090–1104 (2000)CrossRefGoogle Scholar
  15. 15.
    Prosser, B., Zheng, W.-S., Gong, S., Xiang, T.: Person re-identification by support vector ranking. In: BMVC, pp. 1–11 (2010)Google Scholar
  16. 16.
    Sarkar, S., Phillips, P.J., Liu, Z., Vega, I.R., Grother, P., Bowyer, K.W.: The HumanID gait challenge problem: data sets, performance, and analysis. PAMI 27(2), 162–177 (2005)CrossRefGoogle Scholar
  17. 17.
    Singh, S., Biswas, K.K.: Biometric Gait Recognition with Carrying and Clothing Variants. In: Chaudhury, S., Mitra, S., Murthy, C.A., Sastry, P.S., Pal, S.K. (eds.) PReMI 2009. LNCS, vol. 5909, pp. 446–451. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  18. 18.
    Tao, S.J.D., Li, X., Wu, X., Maybank: General tensor discriminant analysis and gabor features for gait recognition. PAMI 29(10), 1700–1715 (2007)CrossRefGoogle Scholar
  19. 19.
    Wang, H., Nie, F., Huang, H., Ding, C.: Dyadic transfer learning for cross-domain image classification. In: ICCV, pp. 551–556 (2011)Google Scholar
  20. 20.
    Yang, X., Zhou, Y., Zhang, T., Shu, G., Yang, J.: Gait recognition based on dynamic region analysis. Signal Processing 88(9), 2350–2356 (2008)zbMATHCrossRefGoogle Scholar
  21. 21.
    Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: ICPR, vol. 4, pp. 441–444 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Raúl Martín-Félez
    • 1
  • Tao Xiang
    • 2
  1. 1.Institute of New Imaging TechnologiesUniversitat Jaume ICastellóSpain
  2. 2.School of EECSQueen Mary, University of LondonLondonU.K.

Personalised recommendations