Worms, Chameleons, Phantoms and Doves: New Additions to the Biometric Menagerie

Goat, sheep, and lamb are labels for problem users of a biometric system. These user types are defined in terms of their verification performance when matched against themselves (goats) or when matched against others (lambs and wolves). Four new members of the biometric menagerie are proposed based on a user's relationship between their genuine and imposter match scores. Experiments using a variety of biometrics, algorithms, and data sets have indicated that this relationship can exist with real-world data (face, voice, and fingerprint). An analysis of the results indicates that the presence of these user types tends to reflect a weakness of the underlying system. A new framework for the evaluation of biometric systems based on user groups from the biometric menagerie (as opposed to collective statistics) is proposed.