Adaptive Score Normalization: A Novel Approach for Multimodal Biometric Systems

Authors: Anouar Ben Khalifa, Sami Gazzah, Najoua Essoukri BenAmara

Abstract:

Multimodal biometric systems integrate the data presented by multiple biometric sources, hence offering a better performance than the systems based on a single biometric modality. Although the coupling of biometric systems can be done at different levels, the fusion at the scores level is the most common since it has been proven effective than the rest of the fusion levels. However, the scores from different modalities are generally heterogeneous. A step of normalizing the scores is needed to transform these scores into a common domain before combining them. In this paper, we study the performance of several normalization techniques with various fusion methods in a context relating to the merger of three unimodal systems based on the face, the palmprint and the fingerprint. We also propose a new adaptive normalization method that takes into account the distribution of client scores and impostor scores. Experiments conducted on a database of 100 people show that the performances of a multimodal system depend on the choice of the normalization method and the fusion technique. The proposed normalization method has given the best results.

Keywords: Multibiometrics, Fusion, Score level, Score normalization, Adaptive normalization.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1088462

References:

[1] A. BenKhalifa, N. Essoukri BenAmara, “Contribution to the Fusion of Biometric Modalities by the Choquet Integral,” International Journal of Image, Graphics and Signal Processing, vol. 4, No. 10, 2012, pp. 1 - 7.
[2] A. BenKhalifa, N. Essoukri BenAmara, “Exploration of the Choquet integral for the fusion of biometric modalities,” IEEE International Multi-Conference on Systems, Signals & Devices, 2012, pp. 1 - 6.
[3] A. BenKhalifa, N. Essoukri BenAmara, “Bimodal biometric verification with different fusion levels,” IEEE International Multi-Conference on Systems, Signals & Devices, 2009, pp. 1 - 6.
[4] A.K Jain, K. Nandakumar, A. Ross, “Score normalization in multimodal biometric systems,” Pattern Recognition, Vol. 38, No. 12, 2005, pp. 2270 - 2285.
[5] A.K. Jain, A. Ross, S. Prabhakar, “An introduction to biometric recognition,” IEEE Transactions on Circuits and Systems for Video Technology, 2004, pp. 4 - 20.
[6] A. K. Jain, A. Ross, “Handbook of Multimodalbiometrics,” Springers, 2007.
[7] C. Wang, Y. Li, H. Zhang, L. Wang, “Classifier Discriminant Analysis for Face Verification based on FAR-score normalization,” IEEE Symposium on Foundations of Computational Intelligence, 2007 , pp. 476 - 480.
[8] C. Shu, X. Ding, “Multi-Biometrics Fusion for Identity Verification,” International Conference on Pattern Recognition, 2006, pp. 493 - 496.
[9] D. Zhang, W.K. Kong, J. You, M. Wong, “On-line palmprint identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, pp. 1041 - 1050.
[10] D. Hond, L. Spacek “Distinctive Descriptions for Face Processing,” Proceedings of the 8th British Machine Vision Conference, 1997, pp. 320 - 329.
[11] F. Liu, Q. Zhao, L. Zhang, D. Zhang, “Fingerprint Pore Matching based on Sparse Representation,” International Conference on Pattern Recognition, 2010, pp. 1630 - 1633.
[12] F. Perronnin, J.L. Dugelay, “Introduction à la biométrie Authentification des individus par traitement Audio Vidéo,” Revue traitement du signal, Vol. 19, No. 4, 2002, pp. 253 - 256.
[13] L. Rzouga, A. BenKhalifa, N. Essoukri BenAmara, “Authentification multimodale d’un individu par le visage, l’empreinte digitale et la paume de la main,” Le Colloque de Recherche Appliquée et de Transfert de Technologie, 2012, pp. 1 - 6.
[14] L. Latha, S. Thangasamy, “Efficient approach to Normalization of Multimodal Biometric Scores,” International Journal of Computer Applications, Vol. 32, No. 10, 2011, pp. 57 - 64.
[15] L. Xiuyan, M. Changyun, L. Tiegen, Y. Chenhu, “Research on Personal Identity Verification Based on Hand Vein Iris and Fingerprint,” International Symposium on Computer Science and Society, 2011, pp. 16 - 19.
[16] M. Imran, A. Rao, G.H. Kumar, “Multibiometric systems: A comparative study of multi-algorithmic and multimodal approaches,” Procedia Computer Science, Vol. 2, 2010, pp. 207 - 212.
[17] R. Snelick, M. Indovina, J. Yen, A. Mink, “Multimodal biometrics: issues in design and testing,” International Conference on Multimodal Interfaces, 2003, pp. 68 - 72.
[18] R. Cappelli, D. Maio, D. Maltoni, “Combining fingerprint classifiers,” International Workshop on Multiple Classifier Systems, 2000, pp. 351 - 361.
[19] R. Giot, C. Rosenberger, “Genetic programming for multibiometrics,” Expert Systems with Applications, Vol. 39, No. 2, 2012, pp. 1837 - 1847.
[20] P. Ejarque, J. Hernando, “Score bi-Gaussian equalisation for multimodal person verification,” IET Signal Processing, Vol.3, No. 4, 2009, pp. 322 - 332.
[21] S.J. Horng, Y.H. Chen, R.S. Run, R.J. Chen, J.L Lai, K.O. Sentosal, “An Improved Score Level Fusion in Multimodal Biometric Systems,” International Conference on Parallel and Distributed Computing, Applications and Technologies, 2009, pp. 239 - 246.
[22] S. Ribaric, I. Fratric, “Experimental Evaluation of Matching-Score Normalization Techniques on Different Multimodal Biometric Systems,” IEEE Mediterranean Electrotechnical Conference, 2006, pp. 498 - 501.
[23] T. Savič, N. Pavešić, “Personal recognition based on an image of the palmar surface of the hand,” Pattern Recognition, Vol. 40, No 11, 2007, pp. 3152 - 3163.
[24] K. Niinuma, P. Unsang, A.K. Jain, “Soft Biometric Traits for Continuous User Authentication,” IEEE Transactions on Information Forensics and Security, Vol. 5, No. 4, 2010, pp.771–780.