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.
This report is an extension of the Two Finger Matching with Vendor SDK Matches [1] which evaluated the accuracy of matching two plain fingers (right index and left index) with vendor proprietary fingerprint templates. This study is based on NISTs
Mary F. Theofanos, Brian C. Stanton, Yee-Yin Choong, Haiying Guan
Compared with traditional password and other identification methods, biometrics like face, iris, and fingerprint for automatic personal identification/verification have many advantages, and are increasingly gaining popularity in all kinds of applications
Elham Tabassi, Patrick J. Grother, Wayne J. Salamon
Iris is rapidly gaining acceptance and support as a viable biometric. Several large scale identity management applications are either using or considering iris as their secondary or primary biometric for verification. While there are several academic
Christofer J. McGinnis, Dylan J. Yaga, Fernando L. Podio
The current version of the ANSI/NIST-ITL standard "Data Format for the Interchange of Fingerprint, Facial & Other Biometric Information" is specified in two parts. Part 1, ANSI/NIST-ITL 1-2007, specifies the traditional format, and Part 2, ANSI/NIST-ITL 2
This paper addresses the importance of standards when implementing or using biometric systems. Standards have been developed to ensure that biometric systems can effectively and accurately meet users needs such as protecting data integrity, privacy, and
Emile L. Morse, Celeste L. Paul, Aiping L. Zhang, Yee-Yin Choong, Mary F. Theofanos
A field study of 24 participants over 10 weeks explored user behavior and perception in a smartcard authentication system. Ethnographic methods used to collect data included diaries, surveys, interviews, and field observations. We observed a number of
The term "lights-out" for AFIS ten-print fingerprint operations has been around for many years and is generally understood to mean "no human intervention is involved." But is this term appropriate for AFIS latent print operations? This IR examines seven
Andrew P. Founds, Nick Orlans, Whiddon Genevieve, Craig I. Watson
This document and associated dataset is an update to the Multiple Encounter Dataset I (MEDS-I), originally published by the National Institute of Standards and Technology (NIST) in May 2010. The MEDS is a test corpus organized from an extract of submission
Fernando L. Podio, Dylan J. Yaga, Christofer J. McGinnis
The Computer Security Division of NIST/ITL supports the development of biometric conformance testing methodology standards and other conformity assessment efforts through active technical participation in the development of these standards and the
Shahram Orandi, John M. Libert, John Grantham, Kenneth Ko, Stephen S. Wood, Jin Chu Wu
This paper presents the findings of a study conducted to measure the impact of JPEG 2000 compression on fingerprint imagery at various levels of compression. The impact of compression is measured in terms of impact to both Galton and non-Galton based
Yooyoung Lee, Ross J. Micheals, James J. Filliben, P J. Phillips
Due to its distinctiveness, the human iris is a popular biometric feature used to identity a person with high accuracy. The Grand Challenge in iris recognition is to have an effective algorithm for subject verification or identification under a broad
Michael D. Indovina, R. A. Hicklin, G I. Kiebuzinski
ELFT-EFS Evaluation 1 is an evaluation of the accuracy of latent matching using features marked by experienced human latent fingerprint examiners. The purpose of this test is to evaluate the current state of the art in latent feature-based matching, by
Patrick J. Grother, Wayne J. Salamon, Craig I. Watson, Michael D. Indovina, Patricia A. Flanagan
The MINEX II trials have been conducted to evaluate the accuracy and speed of MATCH-ON-CARD verification algorithms. These run on ISO/IEC 7816 smartcards. They compare reference and verification data conformant to the ISO/IEC 19794-2 COMPACT CARD
P J. Phillips, Patrick J. Flynn, Kevin W. Bowyer, Richard W. Vorder Bruegge, Patrick J. Grother, George W. Quinn, Matthew Pruitt
The paper measures the ability of face recognition algorithms to distinguish between identical twin siblings. The experimental dataset consists of images taken of 126 pairs of identical twins (252 people) collected on the same day and 24 pairs of identical
P J. Phillips, J. R. Beveridge, Bruce A. Draper, Geof H. Givens, Alice J. O'Toole, David Bolme, Joseph Dunlop, Yui M. Lui, Hassan A. Sahibzada, Samuel Weimer
The Good, the Bad, & the Ugly Face Challenge Problem was created to encourage the development of algorithms that are robust to recognition across changes that occur in still frontal faces. The Good, the Bad, & the Ugly consists of three partitions. The
J. R. Beveridge, P. Jonathon Phillips, Geof H. Givens, Bruce A. Draper, Mohammad N. Teli, David Bolme
In face recognition, quality is typically thought of as a property of individual images, not image pairs. The implicit assumption is that high-quality images should be easy to match to each other, while low quality images should be hard to match. This
Alice J. O'Toole, P. Jonathon Phillips, Xiaobo An, Joseph Dunlop
The intended applications of automatic face recognition systems include venues that vary widely in demographic diversity. Formal evaluations of algorithms do not commonly consider the effects of population diversity on performance. We document the effects
P J. Phillips, J. R. Beveridge, Bruce A. Draper, Geof H. Givens, Alice J. O'Toole, David Bolme, Joseph Dunlop, Yui M. Lui, Hassan A. Sahibzada, Samuel Weimer
The Good, the Bad, & the Ugly Face Challenge Problem was created to encourage the development of algorithms that are robust to recognition across changes in illumination that occur in still frontal faces. The Good, the Bad, & the Ugly consists of three
Alice J. O'Toole, P. Jonathon Phillips, Xiaobo An, Joseph Dunlop
The intended applications of automatic face recognition systems include venues that vary widely in demographic diversity. Formal evaluations of algorithms do not commonly consider the effects of population diversity on performance. We document the effects
Sarah E. Baker, Patrick J. Flynn, Kevin W. Bowyer, P. Jonathon Phillips
We present results of the first systematic study to investigate the degree to which template aging occurs for iris biometrics. Our experiments use an image data set with approximately four years of elapsed time between the earliest and most recent images
US-government sponsored evaluations and challenge problems have helped spur over two-orders-of-magnitude improvement in face recognition system performance.
J. R. Beveridge, P. Jonathon Phillips, Geof H. Givens, Bruce A. Draper, Mohammad N. Teli, David Bolme
In face recognition, quality is typically thought of as a property of individual images, not image pairs. The implicit assumption is that high-quality images should be easy to match to each other, while low quality images should be hard to match. This
The success of biometric applications is particularly dependent on the interoperability of biometric systems. Deploying these systems requires a comprehensive portfolio of biometric standards developed in support of interoperability and data interchange. A
One of the critical issues related to secured Information Technology (IT) systems and applications is the verification of the users identity. Biometrics provides for secure transactions, positive identification and augmentation to human judgment. For
In operational ROC (receiver operating characteristic) analysis of fingerprint-image matching algorithms on large datasets, the measures and their accuracies are investigated in the three scenarios: 1) the true accept rate (TAR) of genuine scores at a