Authors: Yednek Asfaw; Guy Scott; Paul Pelletier; Andy Adler
Addresses: Systems and Computer Engineering, Carleton University, Ottawa K1S 5B6, Ontario, Canada ' Citizenship and Immigration Canada, Ottawa K1A 1L1, Ontario, Canada ' Seacom Technologies Inc. Ottawa, Ontario, Canada ' Systems and Computer Engineering, Carleton University, Ottawa K1S 5B6, Ontario, Canada
Abstract: A key concern in Automatic Face Recognition (AFR) is the decrease of recognition performance as the quality of images decreases. This paper introduces a method to evaluate the impact of face pose variability on face recognition accuracy. Experiments were conducted using three leading commercial face recognition algorithms on data with poses from 0 to ±20 deg in each of the roll, pitch, and yaw directions per subject. Results indicate that roll variations has small effect on performance, while pitch and yaw variations produce a significant increase in error rates. More recent algorithms show better results at low pose variability.
Keywords: AFR; automatic face recognition; receiver operator curve; biometric sample quality; biometric performance analysis; biometrics; pose variability; image quality; image deterioration.
International Journal of Biometrics, 2012 Vol.4 No.4, pp.373 - 387
Received: 08 Dec 2010
Accepted: 11 Oct 2011
Published online: 29 Nov 2014 *