FRVT 2006: Quo Vidas Face Quality

Published

May 10, 2010

Author(s)

P J. Phillips, J. R. Beveridge, Geof H. Givens, Bruce A. Draper, David Bolme, Yui M. Lui

Abstract

This paper summarizes a study of how three state-of-the-art algorithms from the Face Recognition Vendor Test 2006 (FRVT 2006) are effected by factors related to face images and the people being recognized. The recognition scenario compares highly controlled images to images taken of people as they stand before a camera in settings such as hallways and outdoors in front of buildings. A Generalized Linear Mixed Model (GLMM) is used to estimate the probability an algorithm successfully verifies a person conditioned upon the factors included in the study. The factors associated with people are: gender, race, age and whether they wear glasses. The factors associated with images are: the size of the face, edge density and region density. The setting, indoors versus outdoors, is also a factor. Edge density can change the estimated probability of verification dramatically, for example from about 0.15 to 0.85. However, this effect is not consistent across algorithm or setting. This finding shows that simple measurable factors are capable of characterizing face quality; however, these factors typically interact with both algorithm and setting.

Citation

Image and Vision Computing

Volume

28

Issue

5

Pub Type

Journals

Download Paper

Local Download

Keywords

face recognition, generalized linear mixed models, image covariates, biometric quality

Citation

Phillips, P. , Beveridge, J. , Givens, G. , Draper, B. , Bolme, D. and Lui, Y. (2010), FRVT 2006: Quo Vidas Face Quality, Image and Vision Computing, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903087 (Accessed April 25, 2024)