Finger Knuckle Print Based Verification Using Minimum Average Correlation Energy Filter

Gaurav Verma ； Aloka Sinha

《International Journal of Electronic Commerce Studies》 5卷2期 (2014/12) Pp. 233-246

https://doi.org/10.7903/ijecs.1089

並列摘要

Biometric-based technologies are being widely used for personal authentication and identification in access control and e-commerce applications. Finger knuckle print, a new hand based biometric trait has recently been utilized in verification and identification based systems. A finger knuckle print possesses a unique and highly distinctive pattern. In this paper, the high discrimination capability of correlation filters were employed for a finger knuckle print based recognition system. The correlation filters have important characteristics like shift invariance and distortion tolerance. A minimum average correlation energy correlation filter was designed for finger knuckle print verification. The performance of the designed filter was evaluated by calculating the peak to side lobe ratio, the false acceptance ratio, the false rejection ratio and the equal error rate. The computational experiments were done on a Matlab platform on the Poly U finger knuckle print database.

並列關鍵字

Authentication ； Correlation Filter ； Minimum Average Correlation Energy Filter ； Finger Knuckle Print ； Region of Interest

參考文獻

The Hong Kong Polytechnic university. Retrieved on December 19, 2011, from http://www.comp.polyu.edu.k/_biometrics/FKP.htm

Hester, C.F.,Casasent, D.(1980).Multivariant technique for multiclass pattern recognition.Applied Optics.19(11),1758-1761.

Jain, A.K.,Flynn, P.,Ross, A.(2008).Handbook of biometrics.New York:Springer.

Jain, A.K.,Ross, A.,Prabhakar, S.(2004).An introduction to biometric recognition.IEEE Transaction on Circuits and Systems for Video Technology.14(1),4-20.

Kumar, A.,Ravikanth, C.(2009).Personal authentication using finger knuckle surface.IEEE Transaction Information Forensics and Security.4(1),98-109.