15th European Signal Processing Conference EUSIPCO 2007

Tutorials



Tutorial title: Biometric Identity Verification - Signal Processing Challenges

Lecturer: Andrzej Drygajlo, Ecole Polytechnique Fédérale de Lausanne, Switzerland

Tutorial outline:
Biometrics is a relatively new area of technology that uses unique and measurable biological and behavioral traits of individuals to automatically establish or verify their identity. The tutorial provides a valuable insight into the state-of-the-art in biometric identity verification technology, both under the signal processing and pattern recognition point of view. It addresses the issues of the global breakthrough by biometrics in identity verification technology that is imminent in terms of its use in identity documents and corresponding applications. With an increase in identity fraud and the emphasis on security, there is a growing and urgent need to efficiently identify humans both locally and remotely on a routine basis. The appearance of electronic identity documents such as passports, visas, national identity cards, drivers' licenses and health insurance cards, have triggered a real need for reliable, user-friendly and widely acceptable automated methods for checking the identity of an individual. Biometric systems are more secure than traditional identification systems. But they only represent a secure identification process in as much as they provide a strong link between a physical person and this person identity.

The attendees will have the opportunity to:

The tutorial will cover the following topics:

Fundamentals of Biometrics
Identity and Biometrics, Individuality of Biometric Data, Recognition,
Verification, Identification and Authentication

Challenges in Analysis, Modeling and Interpretation of Biometric Signals
Mathematical Tools, Sensing and Storage, Representation and Feature
Extraction, Enrollment and Template Creation, Statistical Models, Biometric System Errors,
Evaluation of Biometric Systems

Leading Biometric Technology
Biological Characteristics (fingerprints, face (2D and 3D), hand geometry and veins, palmprint, iris), Behavioral Characteristics (dynamic signature, voice, gait), Technologies under Development, Synthetic Biometric Data Generation

Multimodal Biometrics

Robustness and Reliability in Biometrics

Integration of Biometrics with other Existing Technologies (identity documents, smartcards, mobile phones, e-technologies, transmission of biometric data)

Biometric Applications

Privacy and Legal Issues


Information about the lecturer:

[Andrzej Drygajlo - photo]

Andrzej Drygajlo, head of the Speech Processing and Biometrics Group at the Swiss Federal Institute of Technology at Lausanne (EPFL), conducts research on technological, methodological and legal aspects of biometrics for security and forensic applications.
In 1993 he created the EPFL Speech Processing Group (GTP) and then the EPFL Speech Processing and Biometrics Group (GTPB) and Biometrics Centre Lausanne. His research interests include biometrics, speech processing and man-machine communication applications. He conducts research and teaches at the School of Engineering in EPFL and at the School of Criminal Sciences in the University of Lausanne.
He participates in and coordinates numerous national and international projects and is member of various scientific committees. Among ongoing European research projects the most relevant are the Network of Excellence "BioSecure" and COST 2101 Action "Biometrics for Identity Documents and Smart Cards". Recently, he has been elected chairman of the COST 2101 Action. The main objective of this European Action is to investigate novel technologies for unsupervised multimodal biometric authentication systems using a new generation of biometrics-enabled identity documents and smart cards.