The Biometric Menagerie - A Fuzzy and Inconsistent Concept

TL;DR

This paper demonstrates that the concepts of the Biometric Menagerie in iris recognition are inherently fuzzy, unstable, and dependent on system parameters, challenging their traditional crisp definitions.

Contribution

It provides a detailed analysis showing the fuzzy and non-stationary nature of the Menagerie categories in iris recognition, supported by extensive experimental validation.

Findings

Categories are fuzzy and depend on system parameters.

Membership is better expressed as fuzzy degrees rather than crisp labels.

Experimental tests confirm the instability and fuzziness of the concepts.

Abstract

This paper proves that in iris recognition, the concepts of sheep, goats, lambs and wolves - as proposed by Doddington and Yager in the so-called Biometric Menagerie, are at most fuzzy and at least not quite well defined. They depend not only on the users or on their biometric templates, but also on the parameters that calibrate the iris recognition system. This paper shows that, in the case of iris recognition, the extensions of these concepts have very unsharp and unstable (non-stationary) boundaries. The membership of a user to these categories is more often expressed as a degree (as a fuzzy value) rather than as a crisp value. Moreover, they are defined by fuzzy Sugeno rules instead of classical (crisp) definitions. For these reasons, we said that the Biometric Menagerie proposed by Doddington and Yager could be at most a fuzzy concept of biometry, but even this status is conditioned by improving its definition. All of these facts are confirmed experimentally in a series of 12 exhaustive iris recognition tests undertaken for University of Bath Iris Image Database while using three different iris code dimensions (256x16, 128x8 and 64x4), two different iris texture encoders (Log-Gabor and Haar-Hilbert) and two different types of safety models.