A Cancelable Biometric System Based on Deep Style Transfer and Symmetry Check for Double-Phase User Authentication
Open Access
Abstract
In recent times, there has been a noticeable increase in the application of human biometrics for user authentication in various domains, such as online banking. However, the use of biometric systems poses security risks and the potential for misuse, primarily due to the storage of original templates in databases. To tackle this issue, the concept of cancelable biometrics has emerged as a reliable method utilizing one-way encryption. Several algorithms have been developed to implement cancelable biometrics, incorporating visual representations of single or multiple biometrics. This research proposes a cancelable biometric system that utilizes deep learning techniques to generate two encrypted modalities, namely text and image, using facial and fingerprint biometrics acquired from a smartphone. The system consists of two main stages: a visual encoder and a text encoder. The visual encoder converts the fingerprint style into a facial representation, creating a cancelable template to ensure the potential for cancelation. The resulting visual template is then processed by the text encoder, which employs hashing techniques to generate a corresponding text template. User authentication is automatically verified by utilizing the generated templates through Siamese networks.Keywords
Funding Information
- Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia (PNURSP2023R137)
This publication has 34 references indexed in Scilit:
- Biometric Template Protection: Bridging the performance gap between theory and practiceIEEE Signal Processing Magazine, 2015
- Chaotic watermark for blind forgery detection in imagesMultimedia Tools and Applications, 2015
- Fingerprint Recognition Using Zone Based Linear Binary PatternsProcedia Computer Science, 2015
- Caffe2014
- Standardization of Biometric Template ProtectionIEEE MultiMedia, 2014
- Chaos and NDFT-based spread spectrum concealing of fingerprint-biometric data into audio signalsDigital Signal Processing, 2010
- Cancellable biometrics and annotations on BioHashPattern Recognition, 2008
- Image encryption by using fractional Fourier transform and jigsaw transform in image bit planesOptical Engineering, 2005
- Algorithm 778: L-BFGS-BACM Transactions on Mathematical Software, 1997
- Optical image encryption based on input plane and Fourier plane random encodingOptics Letters, 1995