Title :
The Biometric Menagerie
Author :
Yager, Neil ; Dunstone, Ted
Author_Institution :
Nat. Innovation Centre, Biometix Pty Ltd., Eveleigh, NSW, Australia
Abstract :
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.
Keywords :
authorisation; face recognition; fingerprint identification; iris recognition; message authentication; speech recognition; statistical testing; 2D face; 3D face; authentication; biometric match; biometric menagerie; biometric modality; biometric system; fingerprint; impersonation; iris; keystroke dynamics; speech; statistical test; verification performance; Artificial Intelligence; Biometrics; Image Processing and Computer Vision; Pattern Recognition; authentication; face; fingerprint; identification; iris; keystroke dynamics.; performance evaluation; recognition; speech; Algorithms; Biometric Identification; Dermatoglyphics; Face; Humans; Iris; Pattern Recognition, Automated; Speech; Statistics, Nonparametric;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2008.291