A hybrid system of Iris and Fingerprint recognition for security applications

Abstract

The increase in security level due to the use of biometric recognition systems compared to traditional identification systems is helping in the rapid advancement of such systems. The use of Fingerprint or Iris recognition systems is considered to be reliable and accurate. Both systems do have some drawbacks and errors. In order to minimize the error and increase the accuracy, we propose a hybrid system for identification by using both fingerprint recognition and Iris recognition systems. In this paper, the algorithm used for identification for Iris image was based on Ng et al algorithm using Rapid Haar Wavelet Decomposition while the algorithm used for fingerprint identification presented by Porpanomchai et al is based on the Euclidean distance from the bifurcation point to the core point. Both algorithms were modified and then combined for the hybrid system. The simulation results show the improvement in performance of the proposed method and the added advantages of combining both identifications systems.