F-ratio client dependent normalisation for biometric authentication tasks

The paper investigates a new client-dependent normalisation to improve biometric authentication systems. There exist many client-dependent score normalisation techniques, such as Z-Norm, D-Norm and T-Norm, that are applied to speaker authentication. Such normalisation is intended to adjust the variation across different client models. We propose "F-ratio" normalisation, or F-Norm, applied to face and speaker authentication systems. This normalisation requires only that as few as two client-dependent accesses are available (the more the better). Different from previous normalisation techniques, F-Norm considers the client and impostor distributions simultaneously. We show that F-ratio is a natural choice because it is directly associated to equal error rate. It has the effect of centering the client and impostor distributions such that a global threshold can be easily found. Another difference is that F-Norm actually "interpolates" between client-independent and client-dependent information by introducing a mixture parameter. This parameter can be optimised to maximise the class dispersion (the degree of separability between client and impostor distributions) while the aforementioned normalisation techniques cannot. The results of 13 unimodal experiments carried out on the XM2VTS multimodal database show that such normalisation is advantageous over Z-Norm, client-dependent threshold normalisation or no normalisation.

[1]  Frédéric Bimbot,et al.  A Monte-Carlo method for score normalization in Automatic Speaker Verification using Kullback-Leibler distances , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Samy Bengio,et al.  The expected performance curve: a new assessment measure for person authentication , 2004, Odyssey.

[3]  Javier Hernando,et al.  On the use of score pruning in speaker verification for speaker dependent threshold estimation , 2004, Odyssey.

[4]  Julian Fiérrez,et al.  Exploiting general knowledge in user-dependent fusion strategies for multimodal biometric verification , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[6]  Samy Bengio,et al.  Why do multi-stream, multi-band and multi-modal approaches work on biometric user authentication tasks? , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Hong Yan,et al.  Comparison of face verification results on the XM2VTFS database , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Julian Fiérrez,et al.  Target dependent score normalization techniques and their application to signature verification , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[9]  Ajay Kumar,et al.  Integrating palmprint with face for user authentication , 2003 .

[10]  Roland Auckenthaler,et al.  Score Normalization for Text-Independent Speaker Verification Systems , 2000, Digit. Signal Process..

[11]  Frédéric Bimbot,et al.  Techniques for a priori decision threshold estimation in speaker verification , 1998 .

[12]  Alvin F. Martin,et al.  The DET curve in assessment of detection task performance , 1997, EUROSPEECH.

[13]  Samy Bengio,et al.  A statistical significance test for person authentication , 2004, Odyssey.

[14]  Arun Ross,et al.  Learning user-specific parameters in a multibiometric system , 2002, Proceedings. International Conference on Image Processing.

[15]  Samy Bengio,et al.  Non-Linear Variance Reduction Techniques in Biometric Authentication , 2003 .

[16]  Samy Bengio,et al.  Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication , 2006, Pattern Recognit..

[17]  Samy Bengio,et al.  An Investigation of F-ratio Client-Dependent Normalisation on Biometric Authentication Tasks , 2004 .