Multi-Level Liveness Verification for Face-Voice Biometric Authentication

Author

Chetty, Girija ; Wagner, Michael

Author_Institution

Univ. of Canberra, Canberra

fYear

2006

fDate

Sept. 19 2006-Aug. 21 2006

Firstpage

1

Lastpage

6

Abstract

In this paper we present the details of the multilevel liveness verification (MLLV) framework proposed for realizing a secure face-voice biometric authentication system that can thwart different types of audio and video replay attacks. The proposed MLLV framework based on novel feature extraction and multimodal fusion approaches, uncovers the static and dynamic relationship between voice and face information from speaking faces, and allows multiple levels of security. Experiments with three different speaking corpora VidTIMIT, UCBN and AVOZES shows a significant improvement in system performance in terms of DET curves and equal error rates (EER) for different types of replay and synthesis attacks.

Keywords

authorisation; biometrics (access control); face recognition; feature extraction; message authentication; speech processing; audio replay attacks; equal error rates; face-voice biometric authentication; feature extraction; multilevel liveness verification; multimodal fusion; speaking corpora; speaking faces; video replay attacks; Authentication; Biometrics; Error analysis; Face detection; Feature extraction; Fingerprint recognition; Information security; Pins; Speech synthesis; System performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometric Consortium Conference, 2006 Biometrics Symposium: Special Session on Research at the

Conference_Location

Baltimore, MD

Print_ISBN

978-1-4244-0487-2

Electronic_ISBN

978-1-4244-0487-2

Type

conf

DOI

10.1109/BCC.2006.4341615

Filename

4341615