Improving Fusion with Margin-Derived Confidence in Biometric Authentication Tasks

  • Norman Poh
  • Samy Bengio
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3546)


This study investigates a new confidence criterion to improve fusion via a linear combination of scores of several biometric authentication systems. This confidence is based on the margin of making a decision, which answers the question, “after observing the score of a given system, what is the confidence (or risk) associated to that given access?”. In the context of multimodal and intramodal fusion, such information proves valuable because the margin information can determine which of the systems should be given higher weights. Finally, we propose a linear discriminative framework to fuse the margin information with an existing global fusion function. The results of 32 fusion experiments carried out on the XM2VTS multimodal database show that fusion using margin (product of margin and expert opinion) is superior over fusion without the margin information (i.e., the original expert opinion). Furthermore, combining both sources of information increases fusion performance further.


Quality Information Equal Error Rate Biometric System False Acceptance Rate Biometric Authentication 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Toh, K.-A., Yau, W.-Y., Lim, E., Chen, L., Ng, C.-H.: Fusion of Auxiliary Information for Multimodal Biometric Authentication. In: Zhang, D., Jain, A.K. (eds.) ICBA 2004. LNCS, vol. 3072, pp. 678–685. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  2. 2.
    Bigun, J., Fierrez-Aguilar, J., Ortega-Garcia, J., Gonzalez-Rodriguez, J.: Multimodal Biometric Authentication using Quality Signals in Mobile Communnications. In: 12th Int’l Conf. on Image Analysis and Processing, Mantova, pp. 2–11 (2003)Google Scholar
  3. 3.
    Fierrez-Aguilar, J., Ortega-Garcia, J., Gonzalez-Rodriguez, J., Bigun, J.: Kernel-Based Multimodal Biometric Verification Using Quality Signals. In: Defense and Security Symposium, Workshop on Biometric Technology for Human Identification, Proc. of SPIE, vol. 5404, pp. 544–554 (2004)Google Scholar
  4. 4.
    Garcia-Romero, D., Fierrez-Aguilar, J., Gonzalez-Rodriguez, J., Ortega-Garcia, J.: On the Use of Quality Measures for Text Independent Speaker Recognition. In: The Speaker and Language Recognition Workshop (Odyssey), Toledo, pp. 105–110 (2004)Google Scholar
  5. 5.
    Freund, Y., Schapire, R.: A Short Introduction to Boosting. J. Japan. Soc. for Artificial Intelligence 14(5), 771–780 (1999)Google Scholar
  6. 6.
    Vapnik, V.N.: Statistical Learning Theory. Springer, Heidelberg (1998)zbMATHGoogle Scholar
  7. 7.
    Cristianini, N., Shawe-Taylor, J.: Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge University Press, Cambridge (2000)Google Scholar
  8. 8.
    Toh, K.-A., Yau, W.-Y., Jiang, X.: A Reduced Multivariate Polynomial Model For Multimodal Biometrics And Classifiers Fusion. IEEE Trans. Circuits and Systems for Video Technology (Special Issue on Image- and Video-Based Biometrics) 14(2), 224–233 (2004)Google Scholar
  9. 9.
    Verlinde, P., Chollet, G., Acheroy, M.: Multimodal Identity Verification Using Expert Fusion. Information Fusion 1(1), 17–33 (2000)CrossRefGoogle Scholar
  10. 10.
    Wark, T., Sridharan, S., Chandran, V.: Robust Speaker Verification via Asynchronous Fusion of Speech and Lip Information. In: 2nd Int’l Conf. Audio- and Video-Based Biometric Person Authentication (AVBPA 1999),Washington, D.C, pp. 37–42 (1999)Google Scholar
  11. 11.
    Sanderson, C., Paliwal, K.K.: Noise Compensation in a Person Verification System Using Face and Multiple Speech Features. Pattern Recognition 36(2) (2003)Google Scholar
  12. 12.
    Poh, N., Bengio, S.: How Do Correlation and Variance of Base Classifiers Affect Fusion in Biometric Authentication Tasks? Research Report 04-18, IDIAP, Martigny, Switzerland (2004), accepted for publication in IEEE Trans. Signal Processing (2005)Google Scholar
  13. 13.
    Matas, J., Hamouz, M., Jonsson, K., Kittler, J., Li, Y., Kotropoulos, C., Tefas, A., Pitas, I., Tan, T., Yan, H., Smeraldi, F., Begun, J., Capdevielle, N., Gerstner, W., Ben-Yacoub, S., Abdeljaoued, Y., Mayoraz, E.: Comparison of Face Verification Results on the XM2VTS Database. In: Proc. 15th Int’l Conf. Pattern Recognition, Barcelona, vol. 4, pp. 858–863 (2000)Google Scholar
  14. 14.
    Poh, N., Bengio, S.: Non-Linear Variance Reduction Techniques in Biometric Authentication. In: Workshop on Multimodal User Authentication (MMUA 2003), Santa Barbara, pp. 123–130 (2003)Google Scholar
  15. 15.
    Poh, N., Bengio, S.: Database, Protocol and Tools for Evaluating Score-Level Fusion Algorithms in Biometric Authentication. Research Report 04-44, IDIAP, Martigny, Switzerland (2004); Accepted for publication in AVBPA 2005Google Scholar
  16. 16.
    Martin, A., Doddington, G., Kamm, T., Ordowsk, M., Przybocki, M.: The DET Curve in Assessment of Detection Task Performance. In: Proc. Eurospeech 1997, Rhodes, pp. 1895–1898 (1997)Google Scholar
  17. 17.
    Bengio, S., Mariéthoz, J.: The Expected Performance Curve: a New Assessment Measure for Person Authentication. In: The Speaker and Language Recognition Workshop (Odyssey), Toledo, pp. 279–284 (2004)Google Scholar
  18. 18.
    Bengio, S., Mariéthoz, J.: A Statistical Significance Test for Person Authentication. In: The Speaker and Language Recognition Workshop (Odyssey), Toledo, pp. 237–244 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Norman Poh
    • 1
  • Samy Bengio
    • 1
  1. 1.IDIAP Research InstituteMartignySwitzerland

Personalised recommendations