Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon openaccess Beyond parametric score normalisation in biometric verification systems

This is an open access article published by the IET under the Creative Commons Attribution License
(http://creativecommons.org/licenses/by/3.0/)
Received 06/10/2013, Accepted 04/03/2014, Revised 20/02/2014, Published 07/04/2014

Similarity scores represent the basis for identity inference in biometric verification systems. However, because of the so-called miss-matched conditions across enrollment and probe samples and identity-dependent factors these scores typically exhibit statistical variations that affect the verification performance of biometric systems. To mitigate these variations, score-normalisation techniques, such as the z-norm, the t-norm or the zt-norm, are commonly adopted. In this study, the authors study the problem of score normalisation in the scope of biometric verification and introduce a new class of non-parametric normalisation techniques, which make no assumptions regarding the shape of the distribution from which the scores are drawn (as the parametric techniques do). Instead, they estimate the shape of the score distribution and use the estimate to map the initial distribution to a common (predefined) distribution. Based on the new class of normalisation techniques they also develop a hybrid normalisation scheme that combines non-parametric and parametric techniques into hybrid two-step procedures. They evaluate the performance of the non-parametric and hybrid techniques in face-verification experiments on the FRGCv2 and SCFace databases and show that the non-parametric techniques outperform their parametric counterparts and that the hybrid procedure is not only feasible, but also retains some desirable characteristics from both the non-parametric and the parametric techniques.

Inspec keywords: image matching; biometrics (access control)

Other keywords: score-normalisation techniques; parametric score normalisation; miss-matched conditions; statistical variations; SCFace database; nonparametric normalisation technique; FRGCv2 database; biometric verification systems

Subjects: Computer vision and image processing techniques; Image recognition

References

    1. 1)
      • 13. Žibert, J., Mihelič, F.: ‘Fusion of acoustic and prosodic features for speaker clustering’. Lecture Notes in Computer Science, Springer, 2013, pp. 210–217.
    2. 2)
      • 35. Gajšek, R., Mihelič, F., Dobrišek, S.: ‘Analysis and assessment of state relevance in hmm-based feature extraction method’. Lecture Notes in Computer Science, Springer, 2012.
    3. 3)
      • 38. Dobrišek, S., Žibert, J., Mihelič, F.: ‘Towards the optimal minimization of a pronunciation dictionary model’. Lecture Notes in Computer Science, Springer, 2013, pp. 267–274.
    4. 4)
      • 38. Dobrišek, S., Žibert, J., Mihelič, F.: ‘Towards the optimal minimization of a pronunciation dictionary model’. Lecture Notes in Computer Science, Springer, 2013, pp. 267–274.
    5. 5)
      • 22. Poh, N., Tistarelli, M.: ‘Customizing biometric authentication systems via discriminative score calibration’. Proc. CVPR, 2012, pp. 2681–2686.
    6. 6)
    7. 7)
    8. 8)
      • 7. Štruc, V., Žganec Gros, J., Pavešić, N.: ‘Non-parametric score normalization for biometric verification systems’. Proc. ICPR, Tsukuba, Japan, 2012, pp. 2395–2399.
    9. 9)
      • 11. Poh, N., Bengio, S.: ‘F-ratio client-dependent normalisation on biometric authentication tasks’. Proc. Int. Conf. on Acoustics, Speech and Signal Processing, 2005, vol. 1, pp. 721–724.
    10. 10)
      • 29. Phillips, P., Flynn, P., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Proc. CVPR, 2005, vol. 1, pp. 947–954.
    11. 11)
      • 27. Iyengar, S.G., Varshney, P.K., Damarla, T.: ‘Biometric authentication: a copula based approach’. In Bhanu, B., Govindaraju, V. (Eds.), ‘Multibiometrics for human identification’ (Cambrdige University Press, 2011) p. 23.
    12. 12)
      • 23. Ahonen, T., Pietikäinen, M.: ‘Pixelwise local binary pattern models of faces using kernel density estimation’. Proc. ICB ‘09, Alghero, Italy, 2009, vol. 1, pp. 52–61.
    13. 13)
      • 40. Poh, N., Merati, A., Kittler, J.: ‘Adaptive client-impostor centric score normalization: a case study in fingerprint verification’. IEEE Conf. on Biometrics: Theory, Applications and Systems (BTAS'09), 2009, pp. 1–7.
    14. 14)
    15. 15)
      • 2. Doddington, G., Liggett, W., Martin, A., Przybocki, M., Reynolds, D.: ‘Sheep, goats, lambs and woves: a statistical analysis of speaker performance in the nist 1998 speaker recognition evaluation’. Proc. Int. Conf. on Spoken Language Processing (ICSLP), Sydney, Australia, 1998, vol. 1.
    16. 16)
    17. 17)
    18. 18)
      • 37. Günther, M., Costa-Pazo, A., Ding, C., et al: ‘The 2013 face recognition evaluation in mobile environment’. Proc. Sixth IAPR Int. Conf. on Biometrics, June2013.
    19. 19)
    20. 20)
    21. 21)
    22. 22)
      • 36. Vesnicer, B., Mihelič, F.: ‘The likelihood ratio decision criterion for nuisance attribute projection in gmm speaker verification’, EURASIP J. Adv. Signal Process., 2008, Article ID 786431, pp. 1–11.
    23. 23)
      • 13. Žibert, J., Mihelič, F.: ‘Fusion of acoustic and prosodic features for speaker clustering’. Lecture Notes in Computer Science, Springer, 2013, pp. 210–217.
    24. 24)
    25. 25)
      • 26. Štruc, V., Žibert, J., Pavešić, N.: ‘Histogram remapping as a preprocessing step for robust face recognition’, WSEAS Trans. ISCA, 2009, 6, (3), pp. 520–529.
    26. 26)
    27. 27)
      • 35. Gajšek, R., Mihelič, F., Dobrišek, S.: ‘Analysis and assessment of state relevance in hmm-based feature extraction method’. Lecture Notes in Computer Science, Springer, 2012.
    28. 28)
      • 39. Sun, Y., Tistarelli, M., Poh, N.: ‘Picture-specific cohort score normalization for face pair matching’. Proc. BTAS, 2013, vol. 1.
    29. 29)
      • 15. Štruc, V., Pavešić, N.: ‘The corrected normalized correlation coefficient: a novel way of matching score calculation for lda-based face verification’. Proc. FSKD 2008, China, 2008, pp. 110–115.
    30. 30)
    31. 31)
    32. 32)
      • 25. Pelecanos, J., Sridharam, S.: ‘Feature warping for robust speaker verification’. Proc. Speaker Recognition Workshop (Odyssey), p. 213.
    33. 33)
    34. 34)
      • 10. Yang, F., Shan, S., Ma, B., Chen, X., Gao, W.: ‘Using score normalization techniques to solve the score variation problem in face authentication’, LNCS, 2005, 3781, pp. 31–38.
    35. 35)
      • 8. Štruc, V., Pavešić, N., Žganec Gros, J.: ‘Composite score normalization for face verification’. Proc. first Int. Workshop on Biometrics and Forensics (IWBF), Lisbon, Portugal, 2013, pp. 1–4.
    36. 36)
    37. 37)
      • 28. Poh, N., Merati, A., Kittler, J.: ‘Adaptive client-impostor centric score normalization: a case study in fingerprint verification’. Proc. BTAS, Washington, USA, 2009, pp. 1–7.
    38. 38)
      • 21. Poh, N., Rattani, A., Tistarelli, M., Kittler, J.: ‘Group-specific score normalization for biometric systems’. IEEE Computer Society Workshop on Biometrics (CVPR), 2010, pp. 38–45.
    39. 39)
    40. 40)
    41. 41)
      • 24. Gonzales, R., Woods, R.: ‘Digital image processing’ (Prentice-Hall, New Jersey, 2008, 3rd edn.).
    42. 42)
      • 20. Saeta, J., Hernando, J.: ‘On the use of score pruning in speaker verification for speaker dependent threshold estimation’. The Speaker and Language Recognition Workshop (Odyssey), Toledo, Spain, 2004, pp. 215–218.
    43. 43)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0076
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0076
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address