Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Face Recognition Vendor Test (FRVT) Part 2: Identification

Published

Author(s)

Patrick J. Grother, Mei L. Ngan, Kayee K. Hanaoka

Abstract

This report updates and extends NIST Interagency Report 8238, documenting performance of new face recognition algorithms submitted for evaluation to NIST in November 2018. The algorithms implement one-to-many identification of faces appearing in two- dimensional images. Three datasets were used - the primary dataset is comprised of 26.6 mil- lion reasonably well-controlled live portrait photos of 12.3 million individuals. Three smaller datasets containing more unconstrained photos are also used: 200 thousand side-view images; 3.2 million webcam images; 2.5 million photojournalism and amateur photographer photos. The report will be useful for comparison of face recognition algorithms and assessment of absolute capability. There is an additional appendix to this NISTIR, which contains individual reporting for each algorithm submitted to FRVT 1:N. These "report cards" are available at: https://nfiles.nist.gov/w/dEmFbwW2
Citation
NIST Interagency/Internal Report (NISTIR) - 8271
Report Number
8271

Citation

Grother, P. , Ngan, M. and Hanaoka, K. (2019), Face Recognition Vendor Test (FRVT) Part 2: Identification, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.IR.8271 (Accessed September 16, 2021)
Created September 13, 2019