Cancelable Biometric System Based on the Quaternion Implementation of Double Random Phase Encoding
Paper ID : 1073-ICEEM2023 (R1)
Authors
Mahmoud Nasr *1, Mohamed Essam2, Adam Piorkowski3, Fathi Abd El-Samie4
1Faculty of engineering, Future University in Egypt
2Future University in Egypt
3AGH University of Science and Technology
4Communications and Electronics Department Faculty of Electronic Engineering,Manoufia University
Abstract
The majority of contemporary security solutions rely on biometrics. Unfortunately, these systems have been subjected to hacking attacks for a very long period. The biometrics contained in these databases will be gone permanently if the biometric databases have been breached and stolen. Therefore, the demand for innovative cancelable biometric solutions is great. The fundamental idea behind cancelable biometrics is to utilize a different biometric template constructed using a 1-way transform or an encryption technique to keep the original biometrics secure and out of the system. In this research, we depend on the Double Random Phase Encoding (DRPE) algorithm's basic idea and improve the algorithm by using another auxiliary input biometric and applying the quaternion mathematics to the proposed algorithm. The suggested cancelable biometric technique performs well in simulations even when noise is present, particularly when combined with the proposed cancelable face recognition scheme, where we got a high area under ROC is 0.994 and an EER low of 0.00174.
Keywords
cancelable biometrics, image encryption, DRPE, quaternion mathematics.
Status: Accepted