NOTICE: Due to a lapse in annual appropriations, most of this website is not being updated. Learn more.
Form submissions will still be accepted but will not receive responses at this time. Sections of this site for programs using non-appropriated funds (such as NVLAP) or those that are excepted from the shutdown (such as CHIPS and NVD) will continue to be updated.
An official website of the United States government
Here’s how you know
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.
Transformation, Ranking, and Clustering for Face Recognition Algorithm Performance
Published
Author(s)
Stefan D. Leigh, Nathanael A. Heckert, Andrew L. Rukhin, P J. Phillips, Patrick J. Grother, E M. Newton, M Moody, K Kniskern, S Heath
Abstract
The performance of face recognition algorithms is recently of increased interest, although to date empirical analyses of algorithms have been limited to rank-based scores such a cumulative match score and receiver operating characteristic. This paper demonstrates that algorithms that report ratio scale similarities between unknown and gallery images can be enormalized so that a large body of classical statistical methods can be applied to measure recognition performance.
Leigh, S.
, Heckert, N.
, Rukhin, A.
, Phillips, P.
, Grother, P.
, Newton, E.
, Moody, M.
, Kniskern, K.
and Heath, S.
(2002),
Transformation, Ranking, and Clustering for Face Recognition Algorithm Performance, Automatic Identification Advanced Technologies Workshop
(Accessed October 1, 2025)