Report on the Evaluation of 2D Still-Image Face Recognition Algorithms

Published

June 17, 2010

Author(s)

Patrick J. Grother, George W. Quinn, P J. Phillips

Abstract

The paper evaluates state-of-the-art face identification and verification algorithms, by applying them to corpora of face images the population of which extends into the millions. Performance is stated in terms of core accuracy and speed metrics, and the dependence of these on population size and image properties are reported. One-to-many search algorithms are evaluated in terms of their use in both investigational and identification modes. Investigational performance has implications for workload on an examiner reviewing the results of a search. Identification performance, using a high score threshold, can support fully automated operation and decision making if some quantified level of false match is acceptable. In addition, the paper establishes an initial approach toward calibration of false match accuracy.

Citation

NIST Interagency/Internal Report (NISTIR) - 7709

Report Number

7709

NIST Pub Series

NIST Interagency/Internal Report (NISTIR)

Pub Type

NIST Pubs

Download Paper

https://doi.org/10.6028/NIST.IR.7709

Keywords

Face recognition, biometrics, verification, identification, recognition, identity management, watch-list, pattern recognition, reliability, scalability, calibration, mugshot.

Citation

Grother, P. , Quinn, G. and Phillips, P. (2010), Report on the Evaluation of 2D Still-Image Face Recognition Algorithms, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.7709 (Accessed February 4, 2023)