Randomized Radon Signature for face biometric verification

Dabbah, M. A., Dlay, Satnam and Woo, Wai Lok (2008) Randomized Radon Signature for face biometric verification. In: ICIP 2008 - IEEE International Conference on Image Processing, 12th - 15th October 2008, San Diego, CA.

Full text not available from this repository.

Abstract

Conventional biometric systems use the original biometrics for authentication, which exposes the users' identities to a risk of being compromised. The Randomized Radon Signature (RRS) is a cancellable biometric technique that protects face biometrics during authentication by using Radon transform and random projection. The extracted Radon signatures are generated from the parametric domain of the face and then projected into a random multi-space of a uniform distribution. The generated RRS templates are non-reversible, suitable for image-based statistical face classifiers and reissueable. In this paper the fisherface algorithm is used to conduct a comparison between the original face images and the RRS templates. Results have shown a dramatic 53.37% enhancement in the genuine and impostor distributions separation that leads to a 31.34% reduction in the equal error rate.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	cancellable biometric, face recognition, Radon transform, random projection
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Paul Burns
Date Deposited:	28 May 2019 12:38
Last Modified:	10 Oct 2019 18:46
URI:	http://nrl.northumbria.ac.uk/id/eprint/39412

Downloads