The DOI matches its Crossref record.
Face Recognition Vendor Test (FRVT)
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Benchmarking tests of automatic face recognition systems do not account for the errors of human operators, causing a mismatch between evaluation tests and operational accuracy.
“However, benchmarking tests designed to evaluate these systems do not account for the errors of human operators, who are often an integral part of face recognition solutions in forensic and security settings. This causes a mismatch between evaluation tests and operational accuracy.”
From Error Rates in Users of Automatic Face Recognition Software (2015) · cites this paper as [1]
Section 5.7 assumes reviewers always find a mate when present and never incorrectly select a nonmate; the report therefore does not incorporate human adjudication errors into that model. The 'Accuracy by age group' passage also says reviewer adjudication accuracy remains poorly quantified. These passages support the concern about omitted human errors, but the report does not establish the asserted mismatch between benchmark results and operational accuracy. (LLM, conf=0.84)
Experimental — accuracy not yet measuredLeading commercial off-the-shelf algorithms in one-to-many identification returned matching images of the target identity in the top ten ranked matches for between 80% and 97% of targets in a challenging FRVT test.
“Leading algorithms performed with a high level of accuracy, returning matching images of the target identity in the top ten ranked matches for between 80% and 97% of targets, depending on the algorithm.”
From Error Rates in Users of Automatic Face Recognition Software (2015) · cites this paper as [1]
Estimates of operational FR system accuracy, in the conditions tested here, can be computed by halving scores attained on recent benchmark tests.
“Thus, estimates of operational FR system accuracy, in the conditions we have tested here, can be computed by halving scores attained on recent benchmark tests [1].”
From Error Rates in Users of Automatic Face Recognition Software (2015) · cites this paper as [1]
Section 4.6 reports accuracy measurements from operational datasets, and the 'Magnitude of accuracy gains' section describes a possible twofold reduction in miss rate when candidate rank increases from 1 to 50. Neither passage says that operational accuracy can be estimated by halving benchmark-test scores. Searches for 'benchmark,' 'half,' and comparisons between operational and benchmark accuracy did not find that conversion in our copy; page numbers were not supplied. (LLM, conf=0.72)
Experimental — accuracy not yet measuredIn the most recent international benchmarking test, the Cognitec DBScan 4.1.0 B3 algorithm correctly returned a matching image in the top eight ranked matches in approximately 90% of cases when searching a database of 1.6 million police mugshot images of adults.
“In the most recent international benchmarking test of leading commercial face identification systems, this algorithm correctly returned a matching image in the top eight ranked matches in approximately 90% of cases, when searching a database of 1.6 million police mugshot images of adults [1].”
From Error Rates in Users of Automatic Face Recognition Software (2015) · cites this paper as [1]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 17
- Blumstein, Cohen, Roth, and Visher, editors. Random parameter stochastic models of criminal careers. National Academy of Sciences Press, 1986.
- M. Brauckmann and C. Busch. Large scale database search. In Anil K. Jain and Stan Z. Li, editors, Handbook of Face Recognition, pages 639-654. Springer-Verlag New York, Inc., Secaucus, NJ, USA, 2011.
- Working Group 3. Ed. D. D'Amato. ISO/IEC 19794-5 Amendment 1 -Biometric data interchange formats -Part 5: Face image data - Conditions for taking photographs for face image data. JTC1 :: SC37, 1 edition, 12 2007. http://webstore.ansi.org.
- G. Doddington, W. Liggett, A. Martin, M. Przybocki, and D. Reynolds. Sheep, goats, lambs and wolves: A statistical analysis of speaker performance in the nist 1998 speaker recognition evaluation. In Proceedings of 5th International Conference of Spoken Language Processing, ICSLP 98, Sydney, Australia, 1998. Paper 608 on CD-ROM.
- J. Egan. Signal Detection Theory and Analysis, pages 46-48. Academic Press, 1975.
- Matteo Ferrara, Annalisa Franco, Dario Maio, and Davide Maltoni. Face image conformance to iso/icao standards in machine readable travel documents. IEEE Transactions on Information Forensics and Security, 7(4):1204-1213, 2012.
- Working Group 3. Ed. P. Griffin. ISO/IEC 19794-5 Information Technology -Biometric Data Interchange Formats -Part 5: Face image data. JTC1 :: SC37, 1 edition, 2005. http://webstore.ansi.org.
- P. J. Grother and P. J. Phillips. Models of large population recognition performance. In IEEE Proceedings of the Computer Vision and Pattern Recognition (CVPR), June 2004. Main conference.
- J.P. Hube. Using biometric verification to estimate identification performance. In Biometric Consortium Conference, 2006 Biometrics Symposium: Special Session on Research at the, pages 1-6, 9 2006.
- Herve Jarosz and Jean-Christophe Fondeur. Large scale identification system design. In Wayman, editor, Biometric Systems, chap- ter 9. Springer, 2005.
- J. Klontz and A. Jain. A case study of automated face recognition: The boston marathon bombings suspects. IEEE Computer Magazine, 11 2013. http://openbiometrics.org/publications/KlontzJain IEEEComputerNov2013.pdf.
- Scott Klum, Hu Han, Anil K. Jain, and Brendan Klare. Sketch based face recognition: Forensic vs. composite sketches. In Proc. 6th IAPR International Conference on Biometrics (ICB), June 2013. Madrid, Spain.
- Deepayan Sarkar. Lattice: Multivariate Data Visualization with R. Springer, New York, 2008. ISBN 978-0-387-75968-5.
- Jamie Sherrah. False alarm rate: a critical performance measure for face recognition. In FGR, pages 189-194. IEEE Computer Society, 2004.
- X. Wang and X. Tang. Face photo-sketch synthesis and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 31(11):1955-1967, 2009.
- Working Group 3. Ed. M. Werner. ISO/IEC 19794-5 Information Technology -Biometric Data Interchange Formats -Part 5: Face image data. JTC1 :: SC37, 2 edition, 2011. http://webstore.ansi.org.
- W. Zhang, X. Wang, and X. Tang. Coupled information-theoretic encoding for face photo-sketch recognition. In Proceedings of IEEE
Cited by
Sorted by citations
Racial faces in the wild: Reducing racial bias by information maximization adaptation network
Wang, M., Deng, W., Hu, J., Tao, X., & Huang, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00078 · Cited by 353
Error Rates in Users of Automatic Face Recognition Software
White, D., Dunn, J. D., Schmid, A. C., & Kemp, R. I. (2015) · PLOS ONE · doi:10.1371/journal.pone.0139827 · Cited by 141
Schultebraucks, K., Yadav, V., Shalev, A. Y., Bonanno, G. A., & Galatzer-Levy, I. R. (2022) · Psychological Medicine · doi:10.1017/s0033291720002718 · Cited by 108
Longitudinal Study of Child Face Recognition
Deb, D., Nain, N., & Jain, A. K. (2018) · 2018 International Conference on Biometrics (ICB) · doi:10.1109/icb2018.2018.00042 · Cited by 73
Metadata
- Authors
- Grother, P., & Ngan, M.
- Published
- 2014
- Cited by
- 50
- References
- 0
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
