An Other-Race Effect for Face Recognition Algorithms

Published

August 19, 2009

Author(s)

P J. Phillips, Alice J. O'Toole, Fang Jiang, Abhijit Narvekar, Julianne Ayadd

Abstract

Psychological research indicates that humans recognize faces of their own race more accurately than faces of other races. This "other-race effect" occurs for algorithms tested in a recent international competition for state-of-the-art face recognition algorithms. We report results for a Western algorithm made by fusing eight algorithms from Western countries and an East Asian algorithm made by fusing five algorithms from East Asian countries. At the low false accept rates required for most security applications, the Western algorithm recognized Caucasian faces more accurately than East Asian faces and the East Asian algorithm recognized East Asian faces more accurately than Caucasian faces. Next, using a test that spanned all false alarm rates, we compared the algorithms with humans of Caucasian and East Asian descent matching face identity in an iden- tical stimulus set. In this case, both algorithms performed better on the Caucasian faces-the "majority" race in the database. The Caucasian face advantage, however, was far larger for the Western algorithm than for the East Asian algorithm. Humans showed the standard other-race effect for these faces, but showed more stable performance than the algorithms over changes in the race of the test faces. State-of-the-art face recognition algorithms, like humans, struggle with "other-race face" recognition.

Citation

ACM Transactions on Applied Perception

Pub Type

Journals

Download Paper

Local Download

Citation

Phillips, P. , O'Toole, A. , Jiang, F. , Narvekar, A. and Ayadd, J. (2009), An Other-Race Effect for Face Recognition Algorithms, ACM Transactions on Applied Perception, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=906254 (Accessed October 9, 2025)