Preliminary Studies on the Good, the Bad, and the Ugly Face Recognition Challenge Problem

Published

November 26, 2012

Author(s)

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

Abstract

Face recognition has made significant advances over the last twenty years. State-of-the-art algorithms push the performanceenvelope to near perfect recognition rates on many face databases. Recently, the Good, the Bad, and the Ugly (GBU) face challenge problem has been introduced to focus on hard aspects of face recognition from still frontal images. In this paper, we introduce the CohortLDA base- line algorithm, which is an Linear Discriminant Analysis (LDA) algorithm with color spaces and cohort normalization. CohortLDA greatly outperforms some well known face recognition algorithms on the GBU challenge problem. The GBU protocol includes rules for creating training sets. We investigate the effect on performance of violating the rules for creating training sets. This analysis shows that violating the GBU protocol can substantially over estimate performance on the GBU challenge problem.

Conference Dates

June 18, 2012

Conference Location

Providence, RI

Conference Title

IEEE Computer Society Workshop on Biometrics

Pub Type

Conferences

Download Paper

Local Download

Keywords

face recognition, biometrics, algorithms

Citation

Phillips, P. , Beveridge, J. , Bolme, D. , Draper, B. and Lui, Y. (2012), Preliminary Studies on the Good, the Bad, and the Ugly Face Recognition Challenge Problem, IEEE Computer Society Workshop on Biometrics, Providence, RI, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=911435 (Accessed September 20, 2024)