Abstract
In this paper, we present a new combination technique to fuse scores deriving from face and iris biometric matchers. Based on a precise statistical analysis of bootstrapped match scores deriving from similarity matrices, we show the utility of wavelet denoising on normalized scores. Then, we use an adaptive fusion rule based on the maximization of a cost function combining user-specific weights, a separation distance and statistical moments. Experiments are conducted on FERET and CASIA databases and results show that our proposed method outperforms by 70% some of the best current combination approaches in terms of Equal Error Rates (EER), and reaches a Genuine Accept Rate (GAR) equals to 100% at a False Accept Rate (FAR) of 7×10− 4%.
Keywords
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Nandakumar, K.: Integration of multiple cues in biometric systems. PhD thesis (2005)
Ma, Y., Cukic, B., Singh, H.: A classification approach to multi-biometric score fusion. In: AVBPA, pp. 484–493 (2005)
N.I.S.T., U.N.D.: Multiple biometric grand challenge (mbgc) database (2008), http://face.nist.gov/mbgc
Dorizzi, B., Garcia-Salicetti, S., Allano, L.: Multimodality in biosecure: Evaluation on real vs. virtual subjects. In: ICASSP, p. V (2006)
Garcia-Salicetti, S., Anouar, M.M., Allano, L., Dorizzi, B.: A generic protocol for multibiometric systems evaluation on virtual and real subjects. In: AVBPA, pp. 494–502 (2005)
Dugelay, J.L., Junqua, J.C., Rose, K., Turk, M.: Workshop on multimodal user authentication. In: MMUA, Santa Barbara, CA, USA (2003)
Kittler, J., Hatef, M., Duin, R., Matas, J.: On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 226–239 (1998)
Poh, N., Bengio, S.: Using chimeric users to construct fusion classifiers in biometric authentication tasks: An investigation. Technical report (2005)
Scheidat, T., Vielhauer, C.: Analyzing a multimodal biometric system using real and virtual users. In: Security, Steganography, and Watermarking of Multimedia Contents IX. Proceedings of the SPIE 2007, vol. 6505 (2007)
Morizet, N., Amara, A.: Wavelet domain match score level fusion for multimodal biometrics. In: Proceedings of International Conference on COGnitive systems with Interactive Sensors (COGIS). Stanford University, Palo Alto (2007)
Phillips, P.J., Moon, H., Rizvi, S.A., Rauss, P.J.: The feret evaluation methodology for face-recognition algorithms. IEEE TPAMI 22, 1090–1104 (2000)
Bolme, D.S., Beveridge, J.R., Teixeira, M., Draper, B.A.: The csu face identification evaluation system: Its purpose, features, and structure. In: ICVS, pp. 304–313 (2003)
Perlibakas, V.: Face recognition using principal component analysis and log-gabor filters (unpublished manuscript, 2006)
Beveridge, J.R., Bolme, D.S., Teixeira, M., Draper, B.A.: The csu face identification evaluation system user’s guide: Version 5.0. Technical report, Colorado State University (2003)
CASIA: Casia-irisv3 database (2005), http://www.cbsr.ia.ac.cn/IrisDatabase.htm
Rydgren, E., Ea, T., Amiel, F., F., Rossant, A.A., Amara, A.: Iris features extraction using wavelet packets. ICIP 2, 861–864 (2000)
Zoubir, A.M., Iskander, D.R.: Bootstrap methods and applications, a tutorial for the signal processing practitioner. IEEE Signal Processing Magazine 24, 10–19 (2007)
Andrews, D.W.K., Buchinsky, M.: A three-step method for choosing the number of bootstrap repetitions. Econometrica 68, 23–52 (2000)
Edwards, A.L.: 4, The Correlation Coefficient. In: An Introduction to Linear Regression and Correlation, pp. 33–46. W. H. Freeman and Co. Ltd., New York (1976)
Jain, A.K., Nandakumar, K., Ross, A.: Score normalization in multimodal biometric systems. Pattern Recognition 38, 2270–2285 (2005)
Hamilton, J.D.: Time Series Analysis. Princeton University Press, Princeton (1994)
Donoho, D.L., Johnstone, I.M.: Ideal spatial adaptation by wavelet shrinkage. Biometrika 81, 425–455 (1994)
Sachs, L.: Applied Statistics: A Handbook of Techniques, p. 253. Springer, Heidelberg (1984)
Merry, R.J.E.: Wavelet theory and applications - a literature study. Technical report, Eindhoven University of Technology (2005)
Gilles, J.: Décomposition et détection de structures géométriques en imagerie. PhD thesis, École Normale Supérieure de Cachan (2006)
Coifman, R.R., Donoho, D.L.: Translation-invariant de-noising. Technical report, Stanford University (1995)
Ross, A.A., Nandakumar, K., Jain, A.K.: Handbook of Multibiometrics. Springer, New York (2006)
Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.: 14.1, Moments of a Distribution: Mean, Variance, Skewness, and So Forth. In: Numerical Recipes in FORTRAN: The Art of Scientific Computing, 2nd edn., pp. 604–609. Cambridge University Press, Cambridge (1992)
Snelick, R., Indovina, M., Yen, J., Mink, A.: Multimodal biometrics: issues in design and testing. In: ICMI, pp. 68–72 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Morizet, N., Gilles, J. (2008). A New Adaptive Combination Approach to Score Level Fusion for Face and Iris Biometrics Combining Wavelets and Statistical Moments. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5359. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89646-3_65
Download citation
DOI: https://doi.org/10.1007/978-3-540-89646-3_65
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89645-6
Online ISBN: 978-3-540-89646-3
eBook Packages: Computer ScienceComputer Science (R0)