Open Access

ARTICLE

Cancelable Multi-biometric Template Generation Based on Dual-Tree Complex Wavelet Transform

Ahmed M. Ayoup^1,*, Ashraf A. M. Khalaf¹, Fahad Alraddady², Fathi E. Abd El-Samie³, Walid El-Shafai^3,5, Salwa M. Serag Eldin^2,4

1 Electrical Communications Engineering Department, Faculty of Engineering, Minia University, Minia, 61111, Egypt
2 Department of Computer Engineering, College of Computers and Information Technology, Taif University, P. O. Box 11099, Taif 21944, Saudi Arabia
3 Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University, Menoufia, 32952, Egypt
4 Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Egypt
5 Security Engineering Laboratory, Department of Computer Science, Prince Sultan University, Riyadh, 11586, Saudi Arabia

* Corresponding Author: Ahmed M. Ayoup. Email:

(This article belongs to this Special Issue: Soft Computing Methods for Intelligent Automation Systems)

Intelligent Automation & Soft Computing 2022, 33(2), 1289-1304. https://doi.org/10.32604/iasc.2022.024381

Received 15 October 2021; Accepted 06 December 2021; Issue published 08 February 2022

Abstract

In this article, we introduce a new cancelable biometric template generation layout depending on selective encryption technology and Dual-Tree Complex Wavelet Transform (DT-CWT) fusion. The input face biometric is entered into the automatic face-segmentation (Viola-Jones) algorithm to detect the object in a short time. Viola-Jones algorithm can detect the left eye, right eye, nose, and mouth of the input biometric image. The encoder can choose the left or right eye to generate a cancelable biometric template. The selected eye image of size M × N is XORed with the created pseudo-random number (PRN) matrix C_{M × N} to provide an initial primary image. Arnold Cat Map (ACM) is used to scramble the PRN matri pixel by pixel for primary image encryption keeping the pixel values themselves unchanged. Finally, the ACM scrambled eye images are encrypted using Advanced Encryption Standard (AES) algorithm for database storage. Moreover, the PRN and Initial Key (IK) of the AES algorithm for the same person are used for the biometric model authentication process for database storage. The IK is generated from the right finger and right eye fusion using DT-CWT technique. To avoid injury of a single eye, both right-eye and left-eye models are developed.

---

Keywords

---