We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Cancelable features using log-Gabor filters for biometric authentication.
- Authors
Kaur, Harkeerat; Khanna, Pritee
- Abstract
Wide spread use of biometric based authentication requires security of biometric data against identity thefts. Cancelable biometrics is a recent approach to address the concerns regarding privacy of biometric data, public confidence, and acceptance of biometric systems. This work proposes a template protection approach which generates revocable binary features from phase and magnitude patterns of log-Gabor filters. Multi-level transformations are applied at signal and feature level to distort the biometric data using user specific tokenized variables which are observed to provide better performance and security against information leakage under correlation attacks. A thorough analysis is performed to study the performance, non-invertibility, and changeability of the proposed approach under stolen token scenario on multiple biometric modalities. It is revealed that generated templates are non-invertible, easy to revoke, and also deliver good performance.
- Subjects
BIOMETRIC identification; IDENTITY theft; REVOCABLE trusts; INFORMATION technology security; RANDOM projection method
- Publication
Multimedia Tools & Applications, 2017, Vol 76, Issue 4, p4673
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-016-3652-3