Mutibiometric System Based on Game Theory
Biometric systems based on a single biometric trait have drawbacks that are alleviated by multibiometric systems, which combine multiple sources of information. The novelty of this research effort is that Coalition Game Theory (CGT) is applied to improve the performance of the iris and face based multibiometric system. The CGT technique selects the most salient patches obtained using the Local Binary Patterns (LBP) and modified LBP (mLBP) feature extraction techniques. The CGT chooses patches that have better individual importance along with a strong interaction with other patches based on the Shapely value. Results show that CGT model maintains impressive recognition accuracy while using smaller image areas for recognition. More specifically, CGT outperforms the LBP and mLBP techniques.
KeywordsMultibiometric system Coalition game theory Modified local binary pattern Patch selection
This research was funded by the National Science Foundation (NSF) and Science & Technology Center: Bio/Computational Evolution in Action Consortium (BEACON).
- 1.Wang, Y., Tan, T., Jain, A.: Combining face and iris biometrics for identity verification. In: Proceedings in International Conference on Audio- and Video-based Biometric Person Authentication, pp. 805–813 (2003)Google Scholar
- 3.Roy, K., Shelton, J., O’Connor, B., Kamel, M.S.: Multibiometric system using fuzzy level set, and genetic and evolutionary feature extraction. IET Biometrics, p. 11 (2015)Google Scholar
- 7.Ahmad, F., Roy, K., Popplewell, K.: Multispectral iris recognition using patch based game theory. In: Campilho, A., Kamel, M. (eds.) ICIAR 2014, Part II. LNCS, vol. 8815, pp. 112–120. Springer, Heidelberg (2014)Google Scholar
- 8.Ahmad, F., Roy, K., O’Connor, B., Shelton, J., Arias, P., Esterline, A., Dozier, G.: Facial recognition utilizing patch based game theory. Intl. J. Mach. Learn. Comput. 5(4), 334–338 (2015)Google Scholar
- 10.CASIA-Iris Version 3 interval dataset. http://www.cbsr.ia.ac.cn/IrisDatabase.htm