Multi-modal biometric authentication on the SecurePhone PDA

We present an overview of the development of the SecurePhone mobile communication system in which multimodal biometric authentication gives access to the system’s built-in e-signing facilities, enabling users to deal m-contracts using a mobile call in an easy yet secure and dependable way. Authentication uses an original combination of non-intrusive, psychologically neutral biometrics: the user reads a prompt into a camera and microphone, and signs on a touch screen. The state of the art techniques used for each biometric modality were initially developed using the benchmark databases BANCA (audio-visual) and BIOMET (signature). A suitable PDA was then selected and a multimodal database was recorded on the device itself. Several fusion techniques were tested for biometric evidence combination. Best performance achieved for voice, face, signature and fused modalities was 2.3, 17.3, 4.3 and 0.6% EER for BANCA/BIOMET and 3.2, 27.6, 8.0 and 0.8% EER for the PDA database.

[1]  Douglas A. Reynolds,et al.  Speaker identification and verification using Gaussian mixture speaker models , 1995, Speech Commun..

[2]  J.G.A. Dolfing,et al.  Handwriting recognition and verification : a hidden Markov approach , 1998 .

[3]  Ronald A. Cole,et al.  The CSLU speaker recognition corpus , 1998, ICSLP.

[4]  Frédéric Bimbot,et al.  A MAP approach, with synchronous decoding and unit-based normalization for text-dependent speaker verification , 2000, INTERSPEECH.

[5]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[6]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[7]  Samy Bengio,et al.  Torch: a modular machine learning software library , 2002 .

[8]  Frédéric Bimbot,et al.  The BANCA Database and Experimental Protocol for Speaker Verification , 2002 .

[9]  Gérard Chollet,et al.  BIOMET: A Multimodal Person Authentication Database Including Face, Voice, Fingerprint, Hand and Signature Modalities , 2003, AVBPA.

[10]  Josef Kittler,et al.  A Comparative Study of Automatic Face Verification Algorithms on the BANCA Database , 2003, AVBPA.

[11]  U. Uludag,et al.  Multimodal Biometric Authentication Methods : A COTS Approach , 2003 .

[12]  Bernadette Dorizzi,et al.  Fusion of HMM's Likelihood and Viterbi Path for On-line Signature Verification , 2004, ECCV Workshop BioAW.

[13]  Harin Sellahewa,et al.  Wavelet-based face verification for constrained platforms , 2005, SPIE Defense + Commercial Sensing.

[14]  Julian Fiérrez,et al.  Target dependent score normalization techniques and their application to signature verification , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[15]  G. Chollet,et al.  Adapting a high quality audiovisual database to PDA quality , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[16]  Bernadette Dorizzi,et al.  Multimodal biometric score fusion: The Mean Rule vs. support vector classifiers , 2005, 2005 13th European Signal Processing Conference.

[17]  Ian H. Witten,et al.  Detecting Replay Attacks in Audiovisual Identity Verification , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[18]  Sabah Jassim,et al.  The SecurePhone PDA Database, Experimental Protocol and Automatic Test Procedure for Multimodal User , 2006 .

[19]  Sabah Jassim,et al.  Nonintrusive multibiometrics on a mobile device: a comparison of fusion techniques , 2006, SPIE Defense + Commercial Sensing.