© The Institution of Engineering and Technology
The authors present an algorithm that models the rate of change of biometric performance over time on a subject-dependent basis. It is called ‘homomorphic users grouping algorithm’. Although the model is based on very simplistic assumptions that are inherent in linear regression, it has been applied successfully to estimate the performance of talking face and speech identity verification modalities, as well as their fusion, over a period of more than 600 days. Their experiments carried out on the MOBIO database show that subjects exhibit very different performance trends. Although the performance of some users degrades over time, which is consistent with the literature, they also found that for a similar proportion of users, their performance actually improves with use. The latter finding has never been reported in the literature. Hence, their findings suggest that the problem of biometric performance degradation may be not as serious as previously thought, and so far, the community has ignored the possibility of improved biometric performance over time. The findings also suggest that adaptive biometric systems, that is, systems that attempt to update biometric templates, should be subject-dependent.
References
-
-
1)
-
18. Auckenthaler, R., Carey, M., Lloyd-Thomas, H.: ‘Score normalization for text-independant speaker verification systems’, Digit. Signal Process. (DSP) J., 2000, 10, pp. 42–54 (doi: 10.1006/dspr.1999.0360).
-
2)
-
8. Poh, N., Bengio, S.: ‘F-ratio client-dependent normalisation on biometric authentication tasks’. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, 2005, pp. 721–724.
-
3)
-
2. Wang, H., Flynn, P.J.: ‘Experimental evaluation of eye location accuracies and time-lapse effects on face recognition systems’. Fifth Int. Conf. Audio- and Video-Based Biometric Person Authentication (AVBPA 2005), New York, 2005 (, 3546), pp. 627–636.
-
4)
-
15. Chen, K.: ‘Towards better making a decision in speaker verification’, Pattern Recognit., 2003, 36, (2), pp. 329–346 (doi: 10.1016/S0031-3203(02)00034-1).
-
5)
-
26. Poh, N., Bourlai, T., Kittler, J.: ‘A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms’, Pattern Recognit., 2010, 43, (3), pp. 1094–1105 (doi: 10.1016/j.patcog.2009.09.011).
-
6)
-
10. Hicklin, A., Ulery, B.: ‘The myth of goats: How many people have fingerprints that are hard to match?’. , National Institute of Standards and Technology, 2005.
-
7)
-
1. Flynn, P.J., Bowyer, K.W., Phillips, P.J.: ‘Assessment of time dependency in face recognition: an initial study’. Fourth Int. Conf. Audio- and Video-Based Biometric Person Authentication (AVBPA 2003), Guildford, 2003 (, 2688), pp. 44–51.
-
8)
-
19. Fierrez-Aguilar, J., Ortega-Garcia, J., Gonzalez-Rodriguez, J.: ‘Target dependent score normalisation techniques and their application to signature verification’. Int. Conf. on Biometric Authentication (ICBA), Hong Kong, 2004 (, 3072), pp. 498–504.
-
9)
-
32. Dass, S.C., Zhu, Y., Jain, A.K.: ‘Validating a biometric authentication system: sample size requirements’, IEEE Trans. Pattern Anal. Mach., 2006, 28, (12), pp. 1902–1319 (doi: 10.1109/TPAMI.2006.255).
-
10)
-
9. Daugman, J.: ‘Biometric decision landscapes’. , University of Cambridge Computer Laboratory, 2000.
-
11)
-
11. Wittman, M., Davis, P., Flynn, P.: ‘Empirical studies of the existence of the biometric menagerie in the FRGC 2.0 color image corpus’. Conf. on Computer Vision and Pattern Recognition Workshop, June 2006, p. 33.
-
12)
-
16. 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, 2004, pp. 215–218.
-
13)
-
20. Poh, N., Kittler, J.: ‘On the use of log-likelihood ratio based model-specific score normalisation in biometric authentication’. IEEE/IAPR Proc. Int. Conf. Biometrics (ICB'07), Seoul, 2007 (, 4542), pp. 614–624.
-
14)
-
28. Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: ‘Speaker verification using adapted Gaussian mixture models’, Digit. Signal Process., 2000, 10, (1–3), pp. 19–41 (doi: 10.1006/dspr.1999.0361).
-
15)
-
17. Genoud, D.: ‘Reconnaissance et Transformation de Locuteur’. , Ecole Polythechnique Federale de Lausanne (EPFL), Switzerland, 1998.
-
16)
-
27. Daugman, J.: ‘New methods in iris recognition’, IEEE Trans. Syst. Man Cybern. B, 2007, 37, (5), pp. 1167–1175 (doi: 10.1109/TSMCB.2007.903540).
-
17)
-
30. Box, G.E., Cox, D.R.: ‘An analysis of transformations’. 2007 IEEE Workshop on Automatic Identification Advanced Technologies, 1964, vol. B, no. 26, pp. 211–246.
-
18)
-
37. Poh, N., Bourlai, T., Kittler, J., et al: ‘Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms’, IEEE Trans. Inf. Forensics Sec. (TIFS), 2009, 4, (4), pp. 849–866 (doi: 10.1109/TIFS.2009.2034885).
-
19)
-
34. McCool, C., Marcel, S., Hadid, A., et al: ‘Bi-modal person recognition on a mobile phone: using mobile phone data’. IEEE ICME Workshop on Hot Topics in Mobile Multimedia, July 2012.
-
20)
-
35. Le, Q., Bengio, S.: ‘Client dependent GMM-SVM models for speaker verification’. ICANN, 2003, pp. 443–451.
-
21)
-
3. Poh, N., Kittler, J.: ‘A method for estimating authentication performance over time, with applications to face biometrics’. 12th IAPR Iberoamerican Congress on Pattern Recognition (CIARP), Via del Mar-Valparaiso, Chile, 2007, pp. 360–369.
-
22)
-
23. Rattani, A., Marcialis, G.-L., Roli, F.: ‘An experimental analysis of the relationship between biometric template update and the Doddington's zoo: a case study in face verification’. ICIAP ‘09: Proc. of the 15th Int. Conf. on Image Analysis and Processing, Berlin, Heidelberg, 2009, pp. 434–442.
-
23)
-
13. Furui, S.: ‘Cepstral analysis for automatic speaker verification’, IEEE Trans. Acoust. Speech Audio Process./IEEE Trans. Signal Process., 1981, 29, (2), pp. 254–272 (doi: 10.1109/TASSP.1981.1163530).
-
24)
-
22. Grother, P., Tabassi, E.: ‘Performance of biometric quality measures’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (4), pp. 531–543 (doi: 10.1109/TPAMI.2007.1019).
-
25)
-
21. Poh, N., Kittler, J.: ‘Incorporating variation of model-specific score distribution in speaker verification systems’, IEEE Trans. Audio Speech Lang. Process., 2008, 16, (3), pp. 594–606 (doi: 10.1109/TASL.2008.916525).
-
26)
-
31. Poh, N., Kittler, J.: ‘On using error bounds to optimize cost-sensitive multimodal biometric authentication’. Proc. 19th Int. Conf. Pattern Recognition (ICPR), 2008, pp. 1–4.
-
27)
-
7. Bishop, C.: ‘Neural networks for pattern recognition’ (Oxford University Press, New York, NY, 1999).
-
28)
-
36. Hastie, T., Tibshirani, R., Friedman, J.: ‘The elements of statistical learning’ (Springer-Verlag, New York, NY, 2001).
-
29)
-
6. Poh, N., Kittler, J.: ‘A methodology for separating sheep from goats for controlled enrollment and multimodal fusion’. Proc. of the Sixth Biometrics Symp., Tampa, 2008, pp. 17–22.
-
30)
-
24. Teli, M.N., Beveridge, J.R., Phillips, P.J., Givens, G.H., Bolme, D.S., Draper, B.A.: ‘Biometric zoos: theory and experimental evidence’. IEEE Third Int. Conf. on Biometrics: Theory, Applications, and Systems, 2009. BTAS ‘09, 2011, pp. 1–8.
-
31)
-
12. Une, M., Otsuka, A., Imai, H.: ‘Wolf attack probability: a theoretical security measure in biometric authentication systems’, IEICE Trans. Inf. Syst., 2008, E91-D, (5), pp. 1380–1389 (doi: 10.1093/ietisy/e91-d.5.1380).
-
32)
-
25. Poh, N., Bengio, S.: ‘Database, protocol and tools for evaluating score-level fusion algorithms in biometric authentication’, Pattern Recognit., 2005, 39, (2), pp. 223–233 (doi: 10.1016/j.patcog.2005.06.011).
-
33)
-
14. Pierrot, J.-B.: ‘Elaboration et Validation d'Approaches en Verification du Locuteur’. , ENST, Paris, September1998.
-
34)
-
4. Doddington, G., Liggett, W., Martin, A., Przybocki, M., Reynolds, D.: ‘Sheep, goats, lambs and wolves: a statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation’. Int. Conf. Spoken Language Processing (ICSLP), Sydney, 1998.
-
35)
-
5. Yager, N., Dunstone, T.: ‘Worms, chameleons, phantoms and doves: new additions to the biometric menagerie’. 2007 IEEE Workshop on Automatic Identification Advanced Technologies, June 2007, pp. 1–6.
-
36)
-
29. Cardinaux, F., Sanderson, C., Marcel, S.: ‘Comparison of MLP and GMM classifiers for face verification on XM2VTS’. Fourth Int. Conf. Audio- and Video-Based Biometric Person Authentication (AVBPA 2003), Guildford, 2003 (, 2688), pp. 911–920.
-
37)
-
33. Poh, N., Bengio, S.: ‘Why do multi-stream, multi-band and multi-modal approaches work on biometric user authentication tasks?’. IEEE Int. Conf. Acoustics, Speech, and Signal Processing (ICASSP), Montreal, 2004, vol. V, pp. 893–896.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2014.0107
Related content
content/journals/10.1049/iet-bmt.2014.0107
pub_keyword,iet_inspecKeyword,pub_concept
6
6