A Multimodal Approach for Biometric Authentication with Multiple Classifiers

The paper presents a multimodal approach for biometric authentication, based on multiple classifiers. The proposed solution uses a post-classification biometric fusion method in which the biometric data classifiers outputs are combined in order to improve the overall biometric system performance by decreasing the classification error rates. The paper shows also the biometric recognition task improvement by means of a carefully feature selection, as much as not all of the feature vectors components support the accuracy improvement.

• Sorin Soviany
• Cristina Soviany
• Mariana Jurian

• biometric fusion
• multiple classifiers

[1] P.Reid "Biometrics for Network Security", Prentice Hall, 2004
[2] R. Snelick, M. Indovina, "Multimodal biometrics: issues in desgin and
testing", Proceedings of 5th International Conference on Multimodal
Interface, pp.68-72, 2003
[3] S. Soviany, M Jurian "Multimodal biometric securing methods for
informatics systems", 34th International Spring Seminar on Electronics
Technology (ISSE2011), Slovakia, 11-15 May 2011
[4] R Polikar, "Pattern recognition" Wiley Encyclopedia of BioMedical
Engineering, 2006
[5] A.K..Jain ÔÇ×An Introduction to Biometric Recognition, IEEE Transaction
on Circuits and Systems for Video Technology", Special Issue on
Image- and Video-Based Biometrics, vol. 14, no. 1, 2004
[6] A.K.Jain, R.P.W.Duin, J.Mao "Statistical Pattern Recognition: A
Review", in IEEE Transactions on Pattern Analysis and Machine
Intellingence, vol. 22, No.1, January 2000
[7] S.Soviany, M.Jurian, R. Dragomir, S. Puscoci "Securing Medical
Databases Access by Mixed Authentication Methods", Proceeding of the
2nd International Conference on e-Health and Bioengineering, Romania,
2009
[8] S.Soviany, M.Jurian, S.Puscoci "Decision Optimization Criteria in
Multimodal Biometric Systems", Proceeding of ECAI 2011-
International Conference on Electronics, Computers and Artificial
Intellingence, România, July 2011