A Meta-Analysis of Face Recognition Covariates

Published

November 22, 2010

Author(s)

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

Abstract

This paper presents a meta-analysis for covariates that affect performance of face recognition algorithms. Our review of the literature found six covariates for which multiple studies reported effects on face recognition performance. These are: age of the person, elapsed time between images, gender of the person, the person s expression, the resolution of the face images, and the race of the person. The results presented are drawn from 25 studies conducted over the past 12 years. There is near complete agreement between all of the studies that older people are easier to recognize than younger people, and recognition performance begins to degrade when images are taken more than a year apart. While individual studies find men or women easier to recognize, there is no consistent gender effect. There is universal agreement that changing expression hurts recognition performance. If forced to compare different expressions, there is still insufficient evidence to conclude that any particular expression is better than another. Higher resolution images improve performance for many modern algorithms. Finally, given the studies summarized here, no clear conclusions can be drawn about whether one racial group is harder or easier to recognize than another

Proceedings Title

Biometrics: Theory, Applications and Systems (BTAS 09)

Conference Dates

September 28-30, 2009

Conference Location

Crystal City, VA, US

Pub Type

Conferences

Download Paper

Local Download

Citation

Lui, Y. , Bolme, D. , Draper, B. , Beveridge, J. , Givens, G. and Phillips, P. (2010), A Meta-Analysis of Face Recognition Covariates, Biometrics: Theory, Applications and Systems (BTAS 09), Crystal City, VA, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=903089 (Accessed April 24, 2024)