TY - EJOU AU - Ayoup, Ahmed M. AU - Khalaf, Ashraf A. M. AU - Alraddady, Fahad AU - El-Samie, Fathi E. Abd AU - El-Shafai, Walid AU - Eldin, Salwa M. Serag TI - Cancelable Multi-biometric Template Generation Based on Dual-Tree Complex Wavelet Transform T2 - Intelligent Automation \& Soft Computing PY - 2022 VL - 33 IS - 2 SN - 2326-005X AB - 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 CM × 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. KW - Viola-Jones face detection; machine learning; AES; ACM; DT-CWT; statistical security analysis DO - 10.32604/iasc.2022.024381