Spectroscopically Enhanced Method and System for Multi-Factor Biometric Authentication

Davar PISHVA  

IEICE TRANSACTIONS on Information and Systems   Vol.E91-D   No.5   pp.1369-1379
Publication Date: 2008/05/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e91-d.5.1369
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Information and Communication System Security)
Category: Biometrics
aliveness detection,  security,  authentication,  multi-factor authentication,  biometrics,  spectral biometrics,  

Full Text: PDF>>
Buy this Article

This paper proposes a spectroscopic method and system for preventing spoofing of biometric authentication. One of its focus is to enhance biometrics authentication with a spectroscopic method in a multi-factor manner such that a person's unique 'spectral signatures' or 'spectral factors' are recorded and compared in addition to a non-spectroscopic biometric signature to reduce the likelihood of imposter getting authenticated. By using the 'spectral factors' extracted from reflectance spectra of real fingers and employing cluster analysis, it shows how the authentic fingerprint image presented by a real finger can be distinguished from an authentic fingerprint image embossed on an artificial finger, or molded on a fingertip cover worn by an imposter. This paper also shows how to augment two widely used biometrics systems (fingerprint and iris recognition devices) with spectral biometrics capabilities in a practical manner and without creating much overhead or inconveniencing their users.