Three measures for secure palmprint identification

Abstract

Most previous research in the area of personal authentication using the palmprint as a biometric trait has concentrated on enhancing accuracy yet resistance to attacks is also a centrally important feature of any biometric security system. In this paper, we address three relevant security issues: template re-issuances, also called cancellable biometrics, 1 1 In this paper, we use the definition of cancellable biometrics proposed by Ratha and his co-workers, who are the first inventors of cancellable biometrics based on our best knowledge [N.K. Ratha, J.H. Connell, R.M. Bolle, Enhancing security and privacy in biometrics-based authentication systems, IBM Syst. J. 40(3) (2001) 614–634]. replay attacks, and database attacks. We propose to use a random orientation filter bank (ROFB) as a feature extractor to generate noise-like feature codes, called Competitive Codes for templates re-issuances. Secret messages are hidden in templates to prevent replay and database attacks. This technique can be regarded as template watermarking. A series of analyses is provided to evaluate the security levels of the measures.