Evaluation of Face
Recognition Algorithms

HOME: Evaluation of Face Recognition Algorithms

See News for 2010 for information about our more recent OpenSource releases.

This web site is a resource for researchers developing face recognition algorithms. It provides a standard set of well known algorithms and established experimental protocols. The goal is to provide a firm statistical basis for drawing conclusions about the relative performance of different algorithms and to better explain why algorithms behave as they do. This helps further our understanding of traditional methods such as Eigenfaces as well as providing a basis for testing if and when novel algorithms are better.


On July 23 2010 we released version 5.1 of our Face Identifcation Evaluation System which included minor refinements and fixes. We have also created the 2010* page with more recent information pertinent to anyone interested in the Face Identification Evaluation System.

Version 5.0 of our Face Identifcation Evaluation System was released on May 1, 2003. This release was downloaded over 20,000 times between 2003 and 2010.

The CSU Face Identification Evaluation System.

Four baseline face recognition algorithms have been developed. They are:

  1. A standard PCA, or Eigenfaces, algorithm
  2. A combination PCA and LDA algorithm based upon the University of Maryland algorithm in the FERET tests.
  3. A Bayesian Intrapersonal/Extrapersoanl Image Diffference Classifier based upon the MIT algorithm in the FERET tests.
  4. An Elastic Bunch Graph Matching Algorithm that uses localized landmark features represented by Gabor jets. This algorithm is based upon the USC algorithm in the FERET tests.

To review how these algorithms perform today on the four FERET probe sets used in much of the original FERET evaluation see our summary pages. To understand how these pages are generated, review our system User's Guide and download your own copy of the CSU Face Identification Evaluation System.


This site is not a repository for data. Most of the work presented here is based upon the FERET data. Follow the data link for more information on the FERET data and instructions on how to obtain it. There are a number of other face data repositories, these can be found through the related sites link.

Papers and Experiments

A series of papers have now been written explaining different experiments conducted using the Face Identification Evaluation System. These papers are the most up-to-date summary of the experiments we have run. Abstracts, citation information and full copies in PDF are available through our papers page.


This web site was originally developed under the project "Statistical Inference Methods for Understanding Human Identification Systems" as part of the DARPA Human Identification at a distance Program. The material presented here is being developed in cooperation with both DARPA and NIST. However, the views expressed, quality of algorithms, etc., are the sole responsibility of the research team at Colorado State University. The web site logo was produced by Sue Daigle-Leach.


If you have questions about this site, contact Ross Beveridge or Bruce Draper at Colorado State University.

02:04:08 PM (Colorado)
Monday 24th of October 2016
Contact: Ross Beveridge

Apply to CSU | Contact CSU | Disclaimer | Equal Opportunity
Colorado State University, Fort Collins, CO 80523 USA
© 2010 Colorado State University