Gaussian Random Projection Based Non-invertible Cancelable Biometric Templates

Abstract

Abstract Wide spread use of biometric based authentication implies the need to secure biometric reference data. Various template protection schemes have been introduced to prevent biometric forgery and identity thefts. Cancelable biometrics is a recent approach introduced to address the concerns regarding privacy of biometric data, public confidence, and acceptance of biometric systems. It allows biometric templates to be cancelled and revoked like passwords innumerable times. The work proposes a novel cancelable biometric template generation algorithm using Gaussian random vectors and one way modulus hashing. Instead of using the original templates, the proposed system uses its transformed versions for storing and matching. The approach is tested on face and palmprint biometric modalities. A thorough analysis is performed to analyze the performance, non-invertibility, and distinctiveness of the proposed approach which reveals that the generated templates are non-invertible, easy to revoke, and also deliver good performance.