A Fusion Technique for The Multimodal Biometric System

Authors

  • Wincy JA Parttime Research Scholar, Centre for Information Technology and Engineering, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu
  • Raj YJV Department of Computer Science, Nesamony Memorial Christian College, Marthandam

DOI:

https://doi.org/10.26438/ijcse/v6i9.492495

Keywords:

Feature extraction, score level fusion, SURF, Multimodal system and MeRank

Abstract

Biometric recognition is the challenging area because security and user authentication is necessary for any login purpose. To identify a person, physiological characteristics are most widely used. This paper proposed a new fusion technique for the integration of finger knuckle print, palmprint and face biometrics. The present study concentrated on the multimodal biometric system due to its benefits. Initially the region of interest was obtained for the biometric traits. Then the features are extracted using Speeded Up Robust Features (SURF). Fusion of finger knuckle print, palmprint and face are done at score level using MeRank fusion rule. The MeRank technique uses classification result as well as matching scores of each trait. The performance of the proposed technique is evaluated and experimental results demonstrated that the fusion technique achieved 98.84% of accuracy for the multimodal biometric system.

References

[1] C. Busch, “Finger Knuckle Recognition”, Technical University of Denmark, pp. 1-4, 2011.

[2] D. Gabor, “Theory of Communication”, The Journal of the Institute of Electrical Engineers, Vol.93, Issue.3, pp.429-457, 1946.

[3] A. Ross, A. Jain “Information Fusion in Biometrics”, Pattern Recognition Letters, Vol. 24: pp. 2115‐2125, 2003.

[4] K. Geetha, V. Radhakrishnan, “Multimodal Biometric System: A Feature Level Fusion Approach”, International Journal of Computer Applications, Vol.71, Issue.4, pp. 25-29, 2013.

[5] J. Aravind, S. Valarmathy, “Multi classifier-based score level fusion of multi-modal biometric recognition and its application to remote biometrics authentication”, The Imaging Science Journal, Vol.64, Issue.1, pp.1-15, 2015.

[6] P. P. Archana, D.G. Bhalke, “Fusion of fingerprint, palmprint and iris for person identification”, In the proceedings of the International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT - 2016), pp. 960 – 963, 2016.

[7] M. Kazi, Y. Rode, “Multimodal biometric system using face and signature : a score level fusion approach”, Advances in Computational Research, Vol. 4, Issue. 1, pp.99-103, 2012.

[8] H. Bay, T. Tuytelaars, L. V. Gool, "SURF: Speeded up robust features", In 9th European Conference on Computer Vision 2006, pp. 404– 417, 2006.

[9] The Hong Kong Polytechnic University, PolyU Palmprint Database, Available at: http:// www. Comp. polyu. edu.hk/biometrics.

[10] PolyU Finger Knuckle Print Database, Available at: http://www.comp.polyu.edu.hk/ biometrics/FKP.htm.

[11]PolyU FaceDatabase, Available at:

http://www.comp.polyu.edu.hk/ biometrics/

[12] M. Nageshkumar, P. Mahesh, M. Swamy, “An Efficient Secure Multimodal Biometric Fusion using Palmprint and Face Image”, The International Journal of Computer Science Issue, vol. 1, pp. 49-53, 2009.

[13] M. M. Kazi, Y. S. Rode, S. B. Dabhade, N. N. H. Al-Dawla, A. V. Mane, R. R. Manza, K. V. Kale, “Multimodal biometric system using face and signature: a score level fusion approach”, Advances in Computational Research, vol. 4, no. 1, pp. 99-103, 2012

[14] S. Chaudhary, R. Nath, “A New Multimodal Biometric Recognition System Integrating Iris, Face and Voice” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 5, no. 4, pp.145-150, 2015.

Downloads

Published

2018-09-30
CITATION
DOI: 10.26438/ijcse/v6i9.492495
Published: 2018-09-30

How to Cite

[1]
J. A. Wincy and Y. J. V. Raj, “A Fusion Technique for The Multimodal Biometric System”, Int. J. Comp. Sci. Eng., vol. 6, no. 9, pp. 492–495, Sep. 2018.

Issue

Vol. 6 No. 9 (2018): IJCSE September Editor

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.