access icon free View-invariant gait recognition system using a gait energy image decomposition method

Gait recognition systems can capture biometrical information from a distance and without the user's active cooperation, making them suitable for surveillance environments. However, there are two challenges for gait recognition that need to be solved, namely when: (i) the walking direction is unknown and/or (ii) the subject's appearance changes significantly due to different clothes being worn or items being carried. This study discusses the problem of gait recognition in unconstrained environments and proposes a new system to tackle recognition when facing the two listed challenges. The system automatically identifies the walking direction using a perceptual hash (PHash) computed over the leg region of the gait energy image (GEI) and then compares it against the PHash values of different walking directions stored in the database. Robustness against appearance changes are obtained by decomposing the GEI into sections and selecting those sections unaltered by appearance changes for comparison against a database containing GEI sections for the identified walking direction. The proposed recognition method then recognises the user using a majority decision voting. The proposed view-invariant gait recognition system is computationally inexpensive and outperforms the state-of-the-art in terms of recognition performance.

Inspec keywords: visual databases; gait analysis; biometrics (access control); image recognition

Other keywords: PHash; unconstrained environments; leg region; gait energy image decomposition method; perceptual hash; unknown walking direction; appearance changes; view-invariant gait recognition system; biometrical information; GEI; majority decision voting

Subjects: Computer vision and image processing techniques; Spatial and pictorial databases; Image recognition

References

    1. 1)
      • 5. Tardi, T., Sruti, C.D.: ‘Silhouette-based gait recognition using procrustes shape analysis and elliptic fourier descriptors’, Pattern Recognit., 2012, 45, (9), pp. 34143426.
    2. 2)
      • 9. Zhao, G., Liu, G., Li, H., et al: ‘3D gait recognition using multiple cameras’. Proc. 7th Int. Conf. on Automatic Face and Gesture Recognition, Southampton, 2006.
    3. 3)
      • 23. Pratheepan, Y., Condell, J., Prasad, G.: ‘P Rw GEI: poisson random walk based gait recognition’. Proc. IEEE 7th Int. Symp. on Image and Signal Processing and Analysis (ISPA), 2011.
    4. 4)
      • 6. Poo, L., Tan, A., Tan, S.: ‘Gait probability image: an information-theoretic model of gait representation’, J. Vis. Commun. Image Represent., 2014, 25, (6), pp. 14891492.
    5. 5)
      • 7. Iwashita, Y., Kurazume, R., Baba, R., et al: ‘Method for gait-based biometric identification robust to changes in observation angle’. Proc. 26th Int. Conf. of Image and Vision Computing, Auckland, New Zealand, 2011.
    6. 6)
      • 15. Chaubey, H., Hanmandlu, M., Vasikarla, S.: ‘Enhanced view invariant gait recognition using feature level fusion’. Proc. Applied Imagery Pattern Recognition Workshop (AIPR), Washington DC, 2014.
    7. 7)
      • 19. Choudhury, D.S., Tardi, T.: ‘Robust view invariant multiscale gait recognition’, Pattern Recognit., 2015, 48, (3), pp. 798811.
    8. 8)
      • 20. Guan, Y., Li, C., Hu, Y.: ‘An adaptive system for gait recognition in multi-view environments’. Proc. 14th ACM Multimedia and Security Workshop, Coventry, UK, 2012.
    9. 9)
      • 8. Muramatsu, D., Shiraishi, A., Makihara, Y., et al: ‘Arbitrary view transformation model for gait person authentication’. Proc. 5th Int. Conf. on Theory, Applications and Systems (BTAS), 2012.
    10. 10)
      • 2. Gafurov, D.: ‘A survey of biometric gait recognition: approaches, security and challenges’. Proc. Annual Norwegian Computer Science Conf., 2007.
    11. 11)
      • 12. Goffredo, M., Bouchrika, I., Carter, J., et al: ‘Self-calibrating view-invariant gait biometrics’, IEEE Trans. Syst. Man Cybern., 2010, 40, (4), pp. 9971008.
    12. 12)
      • 27. Iwashita, Y., Uchino, K., Kurazume, R.: ‘Gait-based person identification robust to changes in appearance’, Sens. - Open Access J., 2013, 13, (6), pp. 78847901.
    13. 13)
      • 21. Khalid, B., Tao, X., Shaogang, G.: ‘Cross view gait recognition using correlation strength’. Proc. British Machine Vision Conf., London, 2010.
    14. 14)
      • 11. Bouchrika, I., Carter, J., Nixon, M.: ‘Towards automated visual surveillance using gait for identity recognition and tracking across multiple non-intersecting cameras’, Multimedia Tools Appl., 2016, 75, (2), pp. 12011221.
    15. 15)
      • 28. Liang, Y., Li, C., Guan, Y., et al: ‘Gait recognition based on the golden ratio’, EURASIP J. Image Video Process., 2016, (1), p. 22.
    16. 16)
      • 4. Fazenda, J., Santos, D., Correia, P.: ‘Using gait to recognize people’. Proc. Int. Conf. on Computer as a Tool, EUROCON, Belgrade, 2005.
    17. 17)
      • 13. Jeana, F., Albub, A., Bergevina, R.: ‘Towards view-invariant gait modeling: computing view-normalized body’, Pattern Recognit., 2009, 42, (11), pp. 29362949.
    18. 18)
      • 25. Jeevan, M., Jain, N., Hanmandlu, M., et al: ‘Gait recognition based on Gait Pal and Pal Entropy Image’. Proc. 20th IEEE Int. Conf. on Image Processing (ICIP), 2013.
    19. 19)
      • 17. Liu, N., Tan, Y.: ‘View invariant gait recognition’. Proc. IEEE Int. Conf. on Acoustics Speech and Signal Processing (ICASSP), Dallas, TX, 2010.
    20. 20)
      • 18. Kusakunniran, W., Wu, Q., Zhang, J., et al: ‘A new view-invariant feature for cross-view gait recognition’, IEEE Trans. Inf. Forensics Sec., 2013, 8, (10), pp. 16421653.
    21. 21)
      • 3. Ju, M., Bhanu, B.: ‘Individual recognition using gait energy image’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (2), pp. 316322.
    22. 22)
      • 24. Bashir, K., Tao, X., Shaogang, G.: ‘Gait recognition using gait entropy image’. Proc. 3rd Int. Conf. on Crime Detection and Prevention (ICDP), 2009.
    23. 23)
      • 29. Verlekar, T., Correia, P.: ‘Walking Direction Identification using Perceptual Hashing’. Proc. Int. Workshop on Biometrics and Forensics – IWBF, Limassol, Cyprus, 2016.
    24. 24)
      • 30. ‘CASIA Gait Database’, http://www.sinobiometrics.com.
    25. 25)
      • 31. Iwama, H., Okumura, M., Makihara, Y., et al: ‘The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (5), pp. 15111521.
    26. 26)
      • 14. Kusakunniran, W., Wu, Q., Li, H., et al: ‘Multiple views gait recognition using view transformation model based on optimized gait energy image’. Proc. IEEE 12th Int. Conf. on Computer Vision Workshops (ICCV Workshops), Kyoto, 2009.
    27. 27)
      • 26. Bashir, K., Tao, X., Shaogang, G.: ‘Gait recognition without subject cooperation’, Pattern Recognit. Lett., 2010, 31, (13), pp. 20522060.
    28. 28)
      • 22. Verlekar, T., Correia, P., Soares, L.: ‘View-invariant gait recognition exploiting spatio-temporal information and a dissimilarity metric’. Proc. Int. Conf. of IEEE in Biometrics Special Interest Group (BIOSIG), 2016.
    29. 29)
      • 16. Shiraga, K., Makihara, Y., Muramatsu, D., et al: ‘GEINet: view-invariant gait recognition using a convolutional neural network’. Proc. IEEE Int. Conf. on Biometrics (ICB), 2016.
    30. 30)
      • 10. Kale, A., Chowdhury, A., Chellappa, R.: ‘Towards a view invariant gait recognition algorithm’. Proc. Int. Conf. on Advanced Video and Signal Based Surveillance, 2005.
    31. 31)
      • 1. Makihara, Y., Matovski, D., Nixon, M., et al: ‘Gait recognition: databases, representations, and applications’ (Wiley Encyclopedia of Electrical and Electronics Engineering, 2015).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2016.0118
Loading

Related content

content/journals/10.1049/iet-bmt.2016.0118
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading