access icon free Fast neighbourhood component analysis with spatially smooth regulariser for robust noisy face recognition

For the robust recognition of noisy face images, in this study, the authors improved the fast neighbourhood component analysis (FNCA) model by introducing a novel spatially smooth regulariser (SSR), resulting in the FNCA-SSR model. The SSR can enforce local spatial smoothness by penalising large differences between adjacent pixels, and makes FNCA-SSR model robust against noise in face image. Moreover, the gradient of SSR can be efficiently computed in image space, and thus the optimisation problem of FNCA-SSR can be conveniently solved by using the gradient descent algorithm. Experimental results on several face data sets show that, for the recognition of noisy face images, FNCA-SSR is robust against Gaussian noise and salt and pepper noise, and can achieve much higher recognition accuracy than FNCA and other competing methods.

Inspec keywords: face recognition; gradient methods; statistical analysis

Other keywords: adjacent pixels; robust noisy face recognition; gradient descent algorithm; local spatial smoothness; face data sets; spatially smooth regulariser; optimisation problem; Gaussian noise; FNCA-SSR model; salt and pepper noise; fast neighbourhood component analysis

Subjects: Optimisation techniques; Optimisation techniques; Computer vision and image processing techniques; Other topics in statistics; Image recognition; Other topics in statistics

References

    1. 1)
    2. 2)
    3. 3)
      • 29. Chambolle, A.: ‘An algorithm for total variation minimization and applications’, J. Math. Imaging Vis., 2004, 20, (1–2), pp. 8997.
    4. 4)
    5. 5)
      • 20. Nguyen, H.V., Bai, L.: ‘Cosine similarity metric learning for face verification’. Proc. 10th Asian Conf. Comp. Vis., Queenstown, New Zealand, November 2010, pp. 709720.
    6. 6)
    7. 7)
      • 13. Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: ‘Neighbourhood components analysis’. Proc. Adv. Neural Information Processing Systems, Vancover, Canada, December 2004, pp. 513520.
    8. 8)
    9. 9)
    10. 10)
      • 14. Torresani, L., Lee, K.-C.: ‘Large margin component analysis’. Proc. Adv. Neural Information Processing Systems, 2007, vol. 19, pp. 13851392.
    11. 11)
      • 18. Guillaumin, M., Verbeek, J., Schmid, C.: ‘Is that you? metric learning approaches for face identification’. Proc. IEEE 12th Int. Conf. Comp. Vis., Kyoto, September 2009, pp. 498505.
    12. 12)
    13. 13)
    14. 14)
      • 19. Guillaumin, M., Verbeek, J., Schmid, C.: ‘Multiple instance metric learning from automatically labeled bags of faces’. Proc. 11th Eur. Conf. Comp. Vis., Heraklion, Crete, Greece, September 2010, pp. 634647.
    15. 15)
    16. 16)
    17. 17)
      • 30. Hirsch, M., Schuler, C.J., Harmeling, S., Scholkopf, B.: ‘Fast removal of non-uniform camera shake’. Proc. IEEE 13th Int. Conf. Comp. Vis., Barcelona, November 2011, pp. 463470.
    18. 18)
      • 15. Nie, F., Xiang, S., Zhang, C.: ‘Neighborhood MinMax projections’. Proc. 20th Int. Joint Conf. on Artificial Intell. (IJCAI 2007), 2007, pp. 993998.
    19. 19)
      • 21. Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: ‘Large scale metric learning from equivalence constraints’. Proc. IEEE Int. Conf. Comp. Vis. Patt. Recogn., Providence, RI, 2012, pp. 22882295.
    20. 20)
    21. 21)
      • 7. He, X., Niyogi, P.: ‘Locality preserving projections’. Proc. Adv. Neural Information Processing Systems, 2003, vol. 16, pp. 234241.
    22. 22)
    23. 23)
      • 10. Fu, Y., Huang, T.: ‘Locally linear embedded eigenspace analysis’ (IFP-TR, Univ. of Illinois at Urbana-Champaign, 2005).
    24. 24)
    25. 25)
    26. 26)
    27. 27)
    28. 28)
    29. 29)
    30. 30)
      • 26. Cai, D., He, X., Hu, Y., Han, J., Huang, T.: ‘Learning a spatially smooth subspace for face recognition’. Proc. IEEE Int. Conf. Comp. Vis. Patt. Recogn., Minneapolis, MN, June 2007, pp. 650656.
    31. 31)
    32. 32)
      • 16. Weinberger, K.Q., Blitzer, J., Saul, L.K.: ‘Distance metric learning for large margin nearest neighbor classification’, J. Mach. Learn. Res., 2009, 10, pp. 207244.
    33. 33)
    34. 34)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0087
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0087
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading