The Biometric Menagerie

It is commonly accepted that users of a biometric system may have differing degrees of accuracy within the system. Some people may have trouble authenticating, while others may be particularly vulnerable to impersonation. Goats, wolves, and lambs are labels commonly applied to these problem users. These user types are defined in terms of verification performance when users are matched against themselves (goats) or when matched against others (lambs and wolves). The relationship between a user's genuine and impostor match results suggests four new user groups: worms, doves, chameleons, and phantoms. We establish formal definitions for these animals and a statistical test for their existence. A thorough investigation is conducted using a broad range of biometric modalities, including 2D and 3D faces, fingerprints, iris, speech, and keystroke dynamics. Patterns that emerge from the results expose novel, important, and encouraging insights into the nature of biometric match results. A new framework for the evaluation of biometric systems based on the biometric menagerie, as opposed to collective statistics, is proposed.

[1]  N. Jaspen.  Applied Nonparametric Statistics , 1979 .

[2]  Douglas A. Reynolds,et al.  SHEEP, GOATS, LAMBS and WOLVES A Statistical Analysis of Speaker Performance in the NIST 1998 Speaker Recognition Evaluation , 1998 .

[3]  Anil K. Jain,et al.  FVC2002: Second Fingerprint Verification Competition , 2002, Object recognition supported by user interaction for service robots.

[4]  Ke Chen,et al.  Towards better making a decision in speaker verification , 2003, Pattern Recognit..

[5]  Anil K. Jain,et al.  Handbook of Fingerprint Recognition , 2005, Springer Professional Computing.

[6]  Michael E. Schuckers,et al.  Approximate Confidence Intervals for Estimation of Matching Error Rates of Biometric Identification Devices , 2004, ECCV Workshop BioAW.

[7]  James L. Wayman,et al.  Multifinger Penetration Rate and ROC Variability for Automatic Fingerprint Identification Systems , 2004 .

[8]  Sharath Pankanti,et al.  Guide to Biometrics , 2003, Springer Professional Computing.

[9]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Craig I. Watson,et al.  The myth of goats :: how many people have fingerprints that are hard to match? , 2005 .

[11]  Anil K. Jain,et al.  Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Claudia Picardi,et al.  Keystroke analysis of free text , 2005, TSEC.

[13]  Vinod Chandran,et al.  3D Face Recognition using Log-Gabor Templates , 2006, BMVC.

[14]  Adnan Amin,et al.  Fingerprint alignment using a two stage optimization , 2006, Pattern Recognit. Lett..

[15]  Patrick J. Flynn,et al.  Empirical Studies of the Existence of the Biometric Menagerie in the FRGC 2.0 Color Image Corpus , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[16]  Samy Bengio,et al.  Database, protocols and tools for evaluating score-level fusion algorithms in biometric authentication , 2006, Pattern Recognit..

[17]  Julian Fiérrez,et al.  Speaker verification using speaker- and test-dependent fast score normalization , 2007, Pattern Recognit. Lett..

[18]  Neil Yager,et al.  Worms, Chameleons, Phantoms and Doves: New Additions to the Biometric Menagerie , 2007, 2007 IEEE Workshop on Automatic Identification Advanced Technologies.

[19]  Josef Kittler,et al.  Incorporating Model-Specific Score Distribution in Speaker Verification Systems , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[20]  W. R. Howard.  Biometric System and Data Analysis: Design, Evaluation, and Data Mining , 2009 .