access icon free Noise modelling for denoising and three-dimensional face recognition algorithms performance evaluation

This study proposes an algorithm is proposed to quantitatively evaluate the performance of three-dimensional (3D) holistic face recognition algorithms when various denoising methods are used. First, a method is proposed to model the noise on the 3D face datasets. The model not only identifies those regions on the face which are sensitive to the noise but can also be used to simulate noise for any given 3D face. Then, by incorporating the noise model in a novel 3D face recognition pipeline, seven different classification and matching methods and six denoising techniques are used to quantify the face recognition algorithms performance for different powers of the noise. The outcome: (i) shows the most reliable parameters for the denoising methods to be used in a 3D face recognition pipeline; (ii) shows which parts of the face are more vulnerable to noise and require further post-processing after data acquisition; and (iii) compares the performance of three different categories of recognition algorithms: training-free matching-based, subspace projection-based and training-based (without projection) classifiers. The results show the high performance of the bootstrap aggregating tree classifiers and median filtering for very high intensity noise. Moreover, when different noisy/denoised samples are used as probes or in the gallery, the matching algorithms significantly outperform the training-based (including the subspace projection) methods.

Inspec keywords: median filters; image sampling; image classification; data acquisition; image denoising; trees (mathematics); image matching; face recognition; image filtering; statistical analysis; bootstrapping

Other keywords: training-based classifier; median filtering; subspace projection-based classifier; denoising; three-dimensional face recognition algorithms performance evaluation; 3D holistic face recognition pipiline; bootstrap aggregating tree classifier; noise model; data acquisition; training-free matching-based classifier

Subjects: Image recognition; Other topics in statistics; Other topics in statistics; Filtering methods in signal processing; Computer vision and image processing techniques; Combinatorial mathematics; Combinatorial mathematics

References

    1. 1)
      • 29. Dietterich, T.: ‘Ensemble methods in machine learning’. Multiple Classifier Systems, Berlin Heidelberg, 2000 (LNCS, 1857), pp. 115.
    2. 2)
    3. 3)
      • 30. Ng, A.Y., Jordan, M.I.: ‘On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes’. Advances in Neural Information Processing Systems 14, 2002, pp. 841848.
    4. 4)
    5. 5)
    6. 6)
      • 21. Llonch, R., Kokiopoulou, E., Tosic, I., Frossard, P.: ‘3D face recognition using sparse spherical representations’. 19th IEEE Int. Conf. on Pattern Recognition, 2008, pp. 14.
    7. 7)
    8. 8)
    9. 9)
      • 17. Emambakhsh, M., Evans, A.: ‘Self-dependent 3D face rotational alignment using the nose region’. Proc. of the Fourth IET Int. Conf. on Imaging for Crime Detection and Prevention (ICDP), 2011, pp. 16.
    10. 10)
    11. 11)
    12. 12)
    13. 13)
      • 15. Emambakhsh, M., Evans, A., Smith, M.: ‘Using nasal curves matching for expression robust 3D nose recognition’. Proc. of the Sixth IEEE Int. Conf. on Biometrics: Theory, Applications and Systems (BTAS), 2013, pp. 16.
    14. 14)
    15. 15)
    16. 16)
      • 23. Lim, J.S.: ‘Two-dimensional signal and image processing’ (Prentice-Hall, Inc., Upper Saddle River, NJ, USA, 1990), p. 548.
    17. 17)
    18. 18)
    19. 19)
      • 39. Ng, A.Y.: ‘Feature selection, L1 vs. L2 regularization, and rotational invariance’. Proc. of the 21st Int. Conf. on Machine Learning (ICML), 2004, pp. 7886.
    20. 20)
      • 3. Emambakhsh, M., Gao, J., Evans, A.: ‘An evaluation of denoising algorithms for 3D face recognition’. Proc. of the Fifth IET Int. Conf. on Imaging for Crime Detection and Prevention (ICDP 2013), 2013, pp. 16.
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
    26. 26)
      • 34. Struc, V.: ‘The PhD face recognition toolbox’, February2012. Available at http://www.mathworks.co.uk/matlabcentral/fileexchange/35106-the-phd-face-recognition-toolbox, accessed time: 13 November 2014.
    27. 27)
      • 18. Moorhouse, A., Evans, A., Atkinson, G., Sun, J., Smith, M.: ‘The nose on your face may not be so plain: using the nose as a biometric’. Third IET Int. Conf. on Crime Detection and Prevention (ICDP), 2009, pp. 16.
    28. 28)
    29. 29)
      • 38. Ke, Q., Kanade, T.: ‘Robust L1-norm factorization in the presence of outliers and missing data’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2005, p. 592599.
    30. 30)
      • 33. Savran, A., Alyüz, N., Dibekliğlu, H., et al: ‘Bosphorus database for 3D face analysis’. Biometrics and Identity Management, Berlin/Heidelberg, 2008, vol. 5372, pp. 4756.
    31. 31)
    32. 32)
    33. 33)
    34. 34)
      • 10. Chang, K.I., Bowyer, K., Flynn, P.: ‘Adaptive rigid multi-region selection for handling expression variation in 3D face recognition’. IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), 2005, p. 157.
    35. 35)
    36. 36)
      • 32. Colombo, A., Cusano, C., Schettini, R.: ‘UMB-DB: a database of partially occluded 3D faces’. IEEE Int. Conf. on Computer Vision (ICCV), 2011, pp. 21132119.
    37. 37)
    38. 38)
      • 35. D'Almeida, F.: ‘Nonlinear diffusion toolbox’, July2003. Available at http://www.mathworks.co.uk/matlabcentral/fileexchange/3710-nonlinear-diffusion-toolbox, accessed time: 19 October 2014.
    39. 39)
      • 42. Zafeiriou, S., Hansen, M., Atkinson, G., et al: ‘The Photoface database’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), 2011, pp. 132139.
    40. 40)
    41. 41)
      • 31. Blei, D.M., Ng, A.Y., Jordan, M.I.: ‘Latent Dirichlet allocation’, J. Mach. Learn. Res., 2003, 3, pp. 9931022.
    42. 42)
      • 26. Sun, X., Rosin, P., Martin, R., Langbein, F.: ‘Noise in 3D laser range scanner data’. IEEE Int. Conf. on Shape Modeling and Applications, 2008, pp. 3745.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0379
Loading

Related content

content/journals/10.1049/iet-cvi.2014.0379
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading