Guide to Biometric Reference Systems and Performance Evaluation

Biometrics has moved from using fingerprints to using many methods of assessing human physical and behavioral traits. This guide introduces a new performance evaluation framework designed to offer full coverage of performance evaluation of biometric systems.

Our daily interactions are based on recognizing people. As information technology advances, our interactions will be accomplished through newly designed interfaces, with a vital element being the automated process of recognition of a person's real identity: Biometrics. In recent years, biometrics has moved from using fingerprints, to many different methods of assessing human physical and behavioural traits.

This useful guide introduces a new performance evaluation framework designed to provide complete coverage of performance evaluation of major biometric systems. Two key areas are presented: The first gives a unique snapshot of the performance evaluation of various biometrics within a common evaluation framework (databases and protocols). The second presents a state-of-the-art benchmarking evaluation framework for use in future performance evaluations - comprised of open-source reference systems.

Features and benefits:

• Includes a Foreword by renowned biometric expert Prof. Anil K. Jain, Michigan State University, USA

• Introduces the concept of reproducible results and comparative evaluations

• Presents an extensive benchmarking methodology

• Describes reference algorithms in detail, with a link to source code

• Biometrics Reference and Evaluation Toolkit provided via http://share.int-evry.fr/svnview-eph/

• Implements this methodology throughout all chapters

• Offers readers a tool for a better evaluation of their algorithms by giving them the instruments to fully reproduce the benchmarking (reference) experiments (software, database, experimental protocols)

• Provides a global perspective with a common evaluation scheme and methodology

• Examines current research results with this framework

• Consolidates results from publicly available databases, using well defined protocols

This unique text/reference combines state-of-the-artresearch with practical tools for researchers, practitioners and graduates in the field of Biometrics and Pattern Recognition, and with its comprehensive coverage, it will prove an indispensable resource and frequently used tool.

Key topics

BioSecure Benchmarking Methodology

Biometric Performance Evaluation

Iris Recognition

Fingerprint Recognition

Hand Recognition

Online Handwritten Signature Verification

Text-independent Speaker Verification

2D and 3D Face Recognition

Talking Face Verification

Provides a global perspective with a common evaluation scheme and methodology Biometrics Reference and Evaluation Toolkit provided via Web Offers readers a tool for a better evaluation of their algorithms by giving them the instruments to fully reproduce the benchmarking (reference) experiments (software, database, experimental protocols) Examines current research results with this framework Includes supplementary material: sn.pub/extras

Inhalt
IntroductionAbout the Need of an Evaluation Framework in Biometrics.- The BioSecure Benchmarking Methodology for Biometric Performance Evaluation.- Iris Recognition.- Fingerprint Recognition.- Hand Recognition.- Online Handwritten Signature Verification.- Text-independent Speaker Verification.- 2D Face Recognition.- 3D Face Recognition.- Talking-face Verification.- BioSecure Multimodal Evaluation Campaign 2007 (BMEC'2007).