skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Laptop Computer - Based Facial Recognition System Assessment

Abstract

The objective of this project was to assess the performance of the leading commercial-off-the-shelf (COTS) facial recognition software package when used as a laptop application. We performed the assessment to determine the system's usefulness for enrolling facial images in a database from remote locations and conducting real-time searches against a database of previously enrolled images. The assessment involved creating a database of 40 images and conducting 2 series of tests to determine the product's ability to recognize and match subject faces under varying conditions. This report describes the test results and includes a description of the factors affecting the results. After an extensive market survey, we selected Visionics' FaceIt{reg_sign} software package for evaluation and a review of the Facial Recognition Vendor Test 2000 (FRVT 2000). This test was co-sponsored by the US Department of Defense (DOD) Counterdrug Technology Development Program Office, the National Institute of Justice, and the Defense Advanced Research Projects Agency (DARPA). Administered in May-June 2000, the FRVT 2000 assessed the capabilities of facial recognition systems that were currently available for purchase on the US market. Our selection of this Visionics product does not indicate that it is the ''best'' facial recognition software package for all uses. Itmore » was the most appropriate package based on the specific applications and requirements for this specific application. In this assessment, the system configuration was evaluated for effectiveness in identifying individuals by searching for facial images captured from video displays against those stored in a facial image database. An additional criterion was that the system be capable of operating discretely. For this application, an operational facial recognition system would consist of one central computer hosting the master image database with multiple standalone systems configured with duplicates of the master operating in remote locations. Remote users could perform real-time searches where network connectivity is not available. As images are enrolled at the remote locations, periodic database synchronization is necessary.« less

Authors:
;
Publication Date:
Research Org.:
Oak Ridge Y-12 Plant, TN (US)
Sponsoring Org.:
USDOE Office of Defense Programs (DP) (US)
OSTI Identifier:
780800
Report Number(s):
Y/NSP-553
TRN: AH200121%%54
DOE Contract Number:  
AC05-00OR22800
Resource Type:
Technical Report
Resource Relation:
Other Information: PBD: 1 Mar 2001
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; PERSONAL COMPUTERS; EVALUATION; PERFORMANCE; PATTERN RECOGNITION; FACE; V CODES; COMPUTER NETWORKS; SECURITY

Citation Formats

Cain, R A, and Singleton, G B. Laptop Computer - Based Facial Recognition System Assessment. United States: N. p., 2001. Web. doi:10.2172/780800.
Cain, R A, & Singleton, G B. Laptop Computer - Based Facial Recognition System Assessment. United States. https://doi.org/10.2172/780800
Cain, R A, and Singleton, G B. Thu . "Laptop Computer - Based Facial Recognition System Assessment". United States. https://doi.org/10.2172/780800. https://www.osti.gov/servlets/purl/780800.
@article{osti_780800,
title = {Laptop Computer - Based Facial Recognition System Assessment},
author = {Cain, R A and Singleton, G B},
abstractNote = {The objective of this project was to assess the performance of the leading commercial-off-the-shelf (COTS) facial recognition software package when used as a laptop application. We performed the assessment to determine the system's usefulness for enrolling facial images in a database from remote locations and conducting real-time searches against a database of previously enrolled images. The assessment involved creating a database of 40 images and conducting 2 series of tests to determine the product's ability to recognize and match subject faces under varying conditions. This report describes the test results and includes a description of the factors affecting the results. After an extensive market survey, we selected Visionics' FaceIt{reg_sign} software package for evaluation and a review of the Facial Recognition Vendor Test 2000 (FRVT 2000). This test was co-sponsored by the US Department of Defense (DOD) Counterdrug Technology Development Program Office, the National Institute of Justice, and the Defense Advanced Research Projects Agency (DARPA). Administered in May-June 2000, the FRVT 2000 assessed the capabilities of facial recognition systems that were currently available for purchase on the US market. Our selection of this Visionics product does not indicate that it is the ''best'' facial recognition software package for all uses. It was the most appropriate package based on the specific applications and requirements for this specific application. In this assessment, the system configuration was evaluated for effectiveness in identifying individuals by searching for facial images captured from video displays against those stored in a facial image database. An additional criterion was that the system be capable of operating discretely. For this application, an operational facial recognition system would consist of one central computer hosting the master image database with multiple standalone systems configured with duplicates of the master operating in remote locations. Remote users could perform real-time searches where network connectivity is not available. As images are enrolled at the remote locations, periodic database synchronization is necessary.},
doi = {10.2172/780800},
url = {https://www.osti.gov/biblio/780800}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2001},
month = {3}
}