Fractional-Order Model for Fingerprint Image Processing in ATM Banking

Thomas Wetere Tulu; Tiande Guo

doi:https://doi.org/10.14445/22315373/IJMTT-V65I4P522

International Journal of Mathematics Trends and Technology

Research Article | Open Access | Download PDF

Volume 65 | Issue 4 | Year 2019 | Article Id. IJMTT-V65I4P522 | DOI : https://doi.org/10.14445/22315373/IJMTT-V65I4P522

Fractional-Order Model for Fingerprint Image Processing in ATM Banking

Thomas Wetere Tulu , Tiande Guo

Citation :

Thomas Wetere Tulu , Tiande Guo, "Fractional-Order Model for Fingerprint Image Processing in ATM Banking," International Journal of Mathematics Trends and Technology (IJMTT), vol. 65, no. 4, pp. 119-124, 2019. Crossref, https://doi.org/10.14445/22315373/IJMTT-V65I4P522

Abstract

Optimization modeling and algorithms of dynamical systems using the classical integer order system of differential equations is becoming an interesting research are now a days. However due to the effective nature of fractional derivatives and integrals, several optimization models and other models in science and engineering have successful being formulated and analyzed. Fractional order derivatives has an important characteristics called memory effect and this special property do not exist in the classical derivatives. These derivatives are non local opposed to the local behavior of integer derivatives. It implies the next state of a fractional system depends not only upon its current state but also upon all of its historical states. In this article we discuss the definition of Caputo derivative and present the fractional-order EUWD model with interventions V and Q in the sense of the Caputo derivative of order α Ε(0,1]. The analysis part then follows accordingly. The main objective of this chapter is therefore to formulate an Optimization model using fractional order derivatives which has an advantage over the classical integer order models discussed in the previous literatures due to its memory effect property. We will consider qualitative stability analysis for the model and finally perform numerical simulations.

Keywords

Fingerprints, ATM, Optimization problem, Caputo derivative

References

[1] RouquetP,etal.Wild animal mortality monitoring and human Ebola outbreaks, Gabon and Repub- lic of Congo,2001-2003,Emerging infectious disease 2005 ;11:283-290.
[2] Selvaraju, N. and Sekar, G., (2010), A Method to Improve the Security Level of ATM Banking Systems Using AES Algorithm, International Journal of Computer Applications (0975 8887) Volume 3 No.6.
[3] Feng, J.,(2008),Combining minutiae descriptors for fingerprint matching, Pattern Recognition 41, 342 352.
[4] Jain, A.K., Prabhakar, S., Hong, L., (1999), A multichannel approach to fingerprint classification, IEEE Trans. Pattern Anal. Mach. Intell. 21 (4),348359.
[5] FVC2002, Second international fingerprint verification competition
[6] Maltoni, D., Maio, D., Jain, A. K., and Prabhakar, S.,(2009), Handbook of Fingerprint Recogni- tion (2nd Edition). Springer.
[7] Jiang, X. and Yau, W. Y.,(2000),Fingerprint Minutiae Matching Based on the Local and Global Structures, In Proc. of ICPR, volume 2, pages 60386041, Barcelona, Spain.
[8] Delac, K. and Grgic, M.,(2004), A Survey of Biometric Recognition Methods, 46th International Symposium Electronics in Marine, ELMAR.
[9] Jain, A.K.; Bolle, R.; Pankanti, S., eds. (1999). Biometrics: Personal Identification in Networked Society, Kluwer Academic Publications, ISBN 978-0-7923-8345-1.
[10] Bansal, R., Sehgal, P. and Bedi, P.,(2011), Minutiae extraction from fingerprint images- a review, IJCSI, Vol. 8, Issue 5.