Empirical Studies of the Existence of the Biometric Menagerie in the FRGC 2.0 Color Image Corpus

Authors:
M. Wittman;P. Davis;P. J. Flynn
Affiliations:
University of Notre Dame, USA;University of Notre Dame, USA;University of Notre Dame, USA
Venue:
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Year:
2006

Citing 0
Cited 3

A Biometric Menagerie Index for Characterising Template/Model-Specific Variation

ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Intersubject differences in false nonmatch rates for a fingerprint-based authentication system

EURASIP Journal on Advances in Signal Processing - Special issue on recent advances in biometric systems: a signal processing perspective
Evaluation of a template protection approach to integrate fingerprint biometrics in a PIN-based payment infrastructure

Electronic Commerce Research and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The issue of recognizability of subjects in biometric identification is of particular interest to the designers of these systems. We have applied the concept of Doddington's biometric menagerie to the area of facial recognition. We performed a series of tests for the presence of goats, lambs, and wolves on FRGC 2.0 color image data. The data for the subjects that appeared at the extreme end of these tests was then visually examined. Even a cursory comparison of images showed that for this set of data, some images fell into the defined menagerie categories. Our tests show the statistical existence of these animal classifications within the constraints of this set of FRGC 2.0 data using the baseline matching algorithm. Ultimately, these tests were limited by the image data set and matching algorithm used. For further confirmation of the existence of the menagerie, the analysis must be expanded to include different image sets and matching algorithms..