Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms

Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accu...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Proceedings of the National Academy of Sciences - PNAS Ročník 115; číslo 24; s. 6171
Hlavní autoři:	Phillips, P Jonathon, Yates, Amy N, Hu, Ying, Hahn, Carina A, Noyes, Eilidh, Jackson, Kelsey, Cavazos, Jacqueline G, Jeckeln, Géraldine, Ranjan, Rajeev, Sankaranarayanan, Swami, Chen, Jun-Cheng, Castillo, Carlos D, Chellappa, Rama, White, David, O'Toole, Alice J
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States 12.06.2018
Témata:	Algorithms Biometric Identification - methods Face - anatomy & histology Forensic Sciences - methods Humans Machine Learning Reproducibility of Results face identification forensic science wisdom-of-crowds face recognition algorithm machine learning technology
ISSN:	1091-6490, 1091-6490
On-line přístup:	Zjistit podrobnosti o přístupu
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible.
AbstractList	Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible. Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible.Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences. Although forensic examiners identify faces in these applications, systematic tests of their accuracy are rare. How can we achieve the most accurate face identification: using people and/or machines working alone or in collaboration? In a comprehensive comparison of face identification by humans and computers, we found that forensic facial examiners, facial reviewers, and superrecognizers were more accurate than fingerprint examiners and students on a challenging face identification test. Individual performance on the test varied widely. On the same test, four deep convolutional neural networks (DCNNs), developed between 2015 and 2017, identified faces within the range of human accuracy. Accuracy of the algorithms increased steadily over time, with the most recent DCNN scoring above the median of the forensic facial examiners. Using crowd-sourcing methods, we fused the judgments of multiple forensic facial examiners by averaging their rating-based identity judgments. Accuracy was substantially better for fused judgments than for individuals working alone. Fusion also served to stabilize performance, boosting the scores of lower-performing individuals and decreasing variability. Single forensic facial examiners fused with the best algorithm were more accurate than the combination of two examiners. Therefore, collaboration among humans and between humans and machines offers tangible benefits to face identification accuracy in important applications. These results offer an evidence-based roadmap for achieving the most accurate face identification possible.
Author	Yates, Amy N O'Toole, Alice J Ranjan, Rajeev Hu, Ying Castillo, Carlos D Phillips, P Jonathon Noyes, Eilidh Cavazos, Jacqueline G Jackson, Kelsey Hahn, Carina A White, David Sankaranarayanan, Swami Chen, Jun-Cheng Jeckeln, Géraldine Chellappa, Rama
Author_xml	– sequence: 1 givenname: P Jonathon orcidid: 0000-0001-6284-5197 surname: Phillips fullname: Phillips, P Jonathon email: jonathon@nist.gov organization: Information Access Division, National Institute of Standards and Technology, Gaithersburg, MD 20899; jonathon@nist.gov – sequence: 2 givenname: Amy N surname: Yates fullname: Yates, Amy N organization: Information Access Division, National Institute of Standards and Technology, Gaithersburg, MD 20899 – sequence: 3 givenname: Ying surname: Hu fullname: Hu, Ying organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 4 givenname: Carina A surname: Hahn fullname: Hahn, Carina A organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 5 givenname: Eilidh surname: Noyes fullname: Noyes, Eilidh organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 6 givenname: Kelsey surname: Jackson fullname: Jackson, Kelsey organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 7 givenname: Jacqueline G surname: Cavazos fullname: Cavazos, Jacqueline G organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 8 givenname: Géraldine surname: Jeckeln fullname: Jeckeln, Géraldine organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080 – sequence: 9 givenname: Rajeev surname: Ranjan fullname: Ranjan, Rajeev organization: Department of Electrical and Computer Engineering, University of Maryland Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20854 – sequence: 10 givenname: Swami surname: Sankaranarayanan fullname: Sankaranarayanan, Swami organization: Department of Electrical and Computer Engineering, University of Maryland Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20854 – sequence: 11 givenname: Jun-Cheng surname: Chen fullname: Chen, Jun-Cheng organization: University of Maryland Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20854 – sequence: 12 givenname: Carlos D surname: Castillo fullname: Castillo, Carlos D organization: University of Maryland Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20854 – sequence: 13 givenname: Rama surname: Chellappa fullname: Chellappa, Rama organization: Department of Electrical and Computer Engineering, University of Maryland Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20854 – sequence: 14 givenname: David surname: White fullname: White, David organization: School of Psychology, The University of New South Wales, Sydney, NSW 2052, Australia – sequence: 15 givenname: Alice J surname: O'Toole fullname: O'Toole, Alice J organization: School of Behavioral and Brain Sciences, The University of Texas at Dallas, Richardson, TX 75080
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/29844174$$D View this record in MEDLINE/PubMed
BookMark	eNplkE1LxDAYhIOsuB969iY9erBrPtvmKIurwoIXPZc36Zu10iZr0oLrr1d0BcHTDMMzc5g5mfjgkZBzRpeMluJ65yEtWcmZUIoxdURmjGqWF1LTyR8_JfOUXimlWlX0hEy5rqRkpZwRswaLWUQbtr4d2uAzsHaMYPdZcJkLEX1qbYbv0LceY7rK0rjDeCh8fCfgm8z9m-m2IbbDS59OybGDLuHZQRfkeX37tLrPN493D6ubTW4VlUOuoHFAwUnrmDbCcWG0Qd5UWDrkxjmBnKM0AFYWugKlZVEoYYtKoAGq-IJc_uzuYngbMQ113yaLXQcew5hqTmXJFddKfKEXB3Q0PTb1LrY9xH39-wv_BG_kacU
CitedBy_id	crossref_primary_10_1016_j_forsciint_2020_110486 crossref_primary_10_1073_pnas_2110013119 crossref_primary_10_1016_j_neubiorev_2024_105943 crossref_primary_10_1038_s41598_024_58605_7 crossref_primary_10_1109_ACCESS_2019_2923626 crossref_primary_10_1007_s11263_024_02078_8 crossref_primary_10_1016_j_cognition_2024_105876 crossref_primary_10_1007_s11704_020_9001_8 crossref_primary_10_1016_j_eswa_2019_04_018 crossref_primary_10_1002_acp_4153 crossref_primary_10_1007_s00426_020_01429_7 crossref_primary_10_1002_arcp_1089 crossref_primary_10_1016_j_apergo_2024_104364 crossref_primary_10_1016_j_tics_2018_06_006 crossref_primary_10_1111_1467_9566_70032 crossref_primary_10_1002_acp_70002 crossref_primary_10_1186_s41235_024_00596_0 crossref_primary_10_1002_acp_70003 crossref_primary_10_7717_peerj_6330 crossref_primary_10_1002_acp_3739 crossref_primary_10_1016_j_forsciint_2023_111576 crossref_primary_10_4018_IJSSCI_2020010103 crossref_primary_10_1145_3403964 crossref_primary_10_1007_s12206_025_0124_6 crossref_primary_10_1016_j_neucom_2025_130614 crossref_primary_10_3758_s13428_021_01609_2 crossref_primary_10_1016_j_cognition_2024_105904 crossref_primary_10_1111_cogs_13031 crossref_primary_10_1016_j_compbiomed_2019_103584 crossref_primary_10_1073_pnas_2304085120 crossref_primary_10_1002_acp_4027 crossref_primary_10_1111_bjop_12794 crossref_primary_10_1016_j_isci_2023_108501 crossref_primary_10_1002_acp_3975 crossref_primary_10_3758_s13423_021_02044_2 crossref_primary_10_1177_1741659020917434 crossref_primary_10_26634_jcom_8_1_17390 crossref_primary_10_3758_s13428_023_02092_7 crossref_primary_10_1016_j_cognition_2021_104955 crossref_primary_10_1098_rsos_201187 crossref_primary_10_1177_17456916231185339 crossref_primary_10_1177_17470218221076817 crossref_primary_10_1186_s41235_021_00317_x crossref_primary_10_1109_ACCESS_2024_3467151 crossref_primary_10_1007_s42113_022_00157_y crossref_primary_10_1109_TCSVT_2023_3344809 crossref_primary_10_1002_acp_3608 crossref_primary_10_1016_j_eswa_2025_126691 crossref_primary_10_35784_iapgos_7156 crossref_primary_10_1057_s41284_021_00321_2 crossref_primary_10_1016_j_jml_2020_104104 crossref_primary_10_1016_j_forsciint_2023_111879 crossref_primary_10_1038_s41598_021_92549_6 crossref_primary_10_3390_s22145270 crossref_primary_10_1016_j_scijus_2024_07_006 crossref_primary_10_1016_j_forsciint_2022_111473 crossref_primary_10_1073_pnas_2220642120 crossref_primary_10_1002_acp_4254 crossref_primary_10_1016_j_entcom_2024_100847 crossref_primary_10_1016_j_jarmac_2018_08_006 crossref_primary_10_1371_journal_pone_0237855 crossref_primary_10_1057_s41264_024_00285_5 crossref_primary_10_1111_1556_4029_15531 crossref_primary_10_1177_0301006620904614 crossref_primary_10_3390_bs15081094 crossref_primary_10_1186_s41235_019_0193_0 crossref_primary_10_1111_bjop_12392 crossref_primary_10_1186_s41235_019_0174_3 crossref_primary_10_1111_bjop_12394 crossref_primary_10_1111_1556_4029_14324 crossref_primary_10_1109_TETC_2019_2958738 crossref_primary_10_1109_ACCESS_2023_3294090 crossref_primary_10_1073_pnas_1902661116 crossref_primary_10_1145_3664634 crossref_primary_10_1002_sam_70021 crossref_primary_10_1186_s41235_024_00564_8 crossref_primary_10_1002_acp_4127 crossref_primary_10_2139_ssrn_5199544 crossref_primary_10_1002_acp_4003 crossref_primary_10_1002_acp_4245 crossref_primary_10_1016_j_cortex_2022_09_012 crossref_primary_10_1016_j_cose_2021_102227 crossref_primary_10_1111_bjop_12657 crossref_primary_10_3758_s13423_023_02304_3 crossref_primary_10_1016_j_neuropsychologia_2022_108279 crossref_primary_10_1088_1361_6501_ad889d crossref_primary_10_1371_journal_pone_0258241 crossref_primary_10_3389_fnins_2024_1441285 crossref_primary_10_1016_j_forsciint_2023_111888 crossref_primary_10_1155_2022_5151105 crossref_primary_10_1016_j_neuropsychologia_2024_109061 crossref_primary_10_1177_21695067231192692 crossref_primary_10_1016_j_cognition_2020_104345 crossref_primary_10_1155_2023_8225630 crossref_primary_10_1145_3365842 crossref_primary_10_1111_bjop_12368 crossref_primary_10_1038_s41598_025_92907_8 crossref_primary_10_1016_j_cognition_2020_104341 crossref_primary_10_1016_j_eswa_2020_113448 crossref_primary_10_1002_acp_70053 crossref_primary_10_1057_s41599_022_01090_y crossref_primary_10_1145_3618113 crossref_primary_10_1177_03010066241295992 crossref_primary_10_1177_2041669519863077 crossref_primary_10_1017_S0140525X23000602 crossref_primary_10_3390_s22031153 crossref_primary_10_1073_pnas_2220580120 crossref_primary_10_1134_S1064230720040073 crossref_primary_10_1145_3625288 crossref_primary_10_1038_s41467_019_12623_6 crossref_primary_10_1089_ast_2022_0017 crossref_primary_10_7202_1076696ar crossref_primary_10_1002_acp_3813 crossref_primary_10_1007_s10548_025_01136_9 crossref_primary_10_1007_s10610_020_09441_8 crossref_primary_10_1371_journal_pone_0283682 crossref_primary_10_3758_s13428_022_02009_w crossref_primary_10_1186_s41235_019_0205_0 crossref_primary_10_1016_j_cotox_2019_03_009 crossref_primary_10_1177_0301006619877821 crossref_primary_10_1007_s42991_022_00253_3 crossref_primary_10_1371_journal_pone_0212935 crossref_primary_10_1002_acp_70037 crossref_primary_10_1038_s44159_022_00041_3 crossref_primary_10_1016_j_neuropsychologia_2021_108119 crossref_primary_10_1016_j_visres_2025_108641 crossref_primary_10_1038_s41598_023_39944_3 crossref_primary_10_1109_ACCESS_2020_3011028 crossref_primary_10_1016_j_cobeha_2020_08_008 crossref_primary_10_1016_j_foodcont_2024_110754 crossref_primary_10_1073_pnas_2111547119 crossref_primary_10_1146_annurev_vision_093019_111701 crossref_primary_10_3389_fdata_2024_1337465 crossref_primary_10_3758_s13428_021_01638_x crossref_primary_10_1007_s12024_024_00839_y crossref_primary_10_1186_s41235_024_00532_2 crossref_primary_10_1016_j_cognition_2022_105333 crossref_primary_10_1080_00401706_2020_1785549 crossref_primary_10_2139_ssrn_4279986 crossref_primary_10_1111_bjop_12629 crossref_primary_10_1371_journal_pone_0277625 crossref_primary_10_3758_s13428_021_01614_5 crossref_primary_10_1002_acp_4053 crossref_primary_10_1016_j_cognition_2021_104966 crossref_primary_10_1109_TNSRE_2022_3173079 crossref_primary_10_1111_bjop_12745 crossref_primary_10_1080_13683500_2023_2295923 crossref_primary_10_1016_j_chbah_2025_100200 crossref_primary_10_1146_annurev_vision_091718_014951 crossref_primary_10_1109_TIFS_2021_3059274 crossref_primary_10_3390_app14093783 crossref_primary_10_3758_s13428_024_02592_0 crossref_primary_10_1016_j_forsciint_2021_110947 crossref_primary_10_1016_j_forsciint_2024_112202 crossref_primary_10_1016_j_neuropsychologia_2021_107810 crossref_primary_10_1016_j_jarmac_2021_07_010 crossref_primary_10_1145_3422988 crossref_primary_10_1016_j_cortex_2023_05_018 crossref_primary_10_1016_j_neunet_2022_07_007 crossref_primary_10_1111_1556_4029_15613 crossref_primary_10_1177_25151274231164927 crossref_primary_10_1016_j_neuropsychologia_2021_107809 crossref_primary_10_1016_j_tics_2020_06_006 crossref_primary_10_3390_laws13030035 crossref_primary_10_1063_1_5129306 crossref_primary_10_1016_j_future_2020_07_014 crossref_primary_10_1098_rsos_200233 crossref_primary_10_1162_jocn_a_02040 crossref_primary_10_1093_jrsssc_qlad089 crossref_primary_10_1098_rsos_201169 crossref_primary_10_1186_s41235_021_00288_z crossref_primary_10_1073_pnas_2319709121 crossref_primary_10_1016_j_forsciint_2019_109910 crossref_primary_10_1016_j_scijus_2024_06_002 crossref_primary_10_1016_j_forsciint_2025_112613 crossref_primary_10_1177_17470218211027695 crossref_primary_10_3758_s13428_025_02809_w crossref_primary_10_1038_s41598_023_28632_x crossref_primary_10_1109_TNNLS_2021_3082304 crossref_primary_10_1145_3609224 crossref_primary_10_1038_s41583_020_00393_w crossref_primary_10_1038_s41598_021_93109_8 crossref_primary_10_3390_s21030728
ContentType	Journal Article
Copyright	Copyright © 2018 the Author(s). Published by PNAS.
Copyright_xml	– notice: Copyright © 2018 the Author(s). Published by PNAS.
DBID	CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1073/pnas.1721355115
DatabaseName	Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	no_fulltext_linktorsrc
Discipline	Sciences (General)
EISSN	1091-6490
ExternalDocumentID	29844174
Genre	Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- -DZ -~X .55 0R~ 123 29P 2AX 2FS 2WC 4.4 53G 5RE 5VS 85S AACGO AAFWJ AANCE ABBHK ABOCM ABPLY ABPPZ ABTLG ABXSQ ABZEH ACGOD ACHIC ACIWK ACNCT ACPRK ADULT AENEX AEUPB AEXZC AFFNX AFOSN AFRAH ALMA_UNASSIGNED_HOLDINGS AQVQM BKOMP CGR CS3 CUY CVF D0L DCCCD DIK DOOOF DU5 E3Z EBS ECM EIF EJD F5P FRP GX1 H13 HH5 HYE IPSME JAAYA JBMMH JENOY JHFFW JKQEH JLS JLXEF JPM JSG JSODD JST KQ8 L7B LU7 N9A NPM N~3 O9- OK1 PNE PQQKQ R.V RHF RHI RNA RNS RPM RXW SA0 SJN TAE TN5 UKR VQA W8F WH7 WOQ WOW X7M XSW Y6R YBH YIF YIN YKV YSK ZCA ~02 ~KM 7X8 ADQXQ
ID	FETCH-LOGICAL-c504t-5adfa0af4cf19b3f23b9be2d8e7fe2bff3e22e4baac4698a5946653c683eba052
IEDL.DBID	7X8
ISICitedReferencesCount	238
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000434933400041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1091-6490
IngestDate	Fri Sep 05 14:31:43 EDT 2025 Wed Feb 19 02:33:46 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	24
Keywords	face identification forensic science wisdom-of-crowds face recognition algorithm machine learning technology
Language	English
License	Copyright © 2018 the Author(s). Published by PNAS.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c504t-5adfa0af4cf19b3f23b9be2d8e7fe2bff3e22e4baac4698a5946653c683eba052
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0001-6284-5197
OpenAccessLink	https://www.pnas.org/doi/10.1073/pnas.1721355115
PMID	29844174
PQID	2047252953
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_2047252953 pubmed_primary_29844174
PublicationCentury	2000
PublicationDate	2018-06-12
PublicationDateYYYYMMDD	2018-06-12
PublicationDate_xml	– month: 06 year: 2018 text: 2018-06-12 day: 12
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Proceedings of the National Academy of Sciences - PNAS
PublicationTitleAlternate	Proc Natl Acad Sci U S A
PublicationYear	2018
References	31097803 - Nat Hum Behav. 2018 Jul;2(7):444
References_xml	– reference: 31097803 - Nat Hum Behav. 2018 Jul;2(7):444
SSID	ssj0009580
Score	2.6680768
Snippet	Achieving the upper limits of face identification accuracy in forensic applications can minimize errors that have profound social and personal consequences....
SourceID	proquest pubmed
SourceType	Aggregation Database Index Database
StartPage	6171
SubjectTerms	Algorithms Biometric Identification - methods Face - anatomy & histology Forensic Sciences - methods Humans Machine Learning Reproducibility of Results
Title	Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms
URI	https://www.ncbi.nlm.nih.gov/pubmed/29844174 https://www.proquest.com/docview/2047252953
Volume	115
WOSCitedRecordID	wos000434933400041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings	1
isFullTextHit
isPrint
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEA7qevDi-7G-iOBBwWqbpG1yEhEXLy57UNjbMkkTFdy2bnZF_fUmbVcFEQQvhRZSQmaSfJOZfB9Ch25P5UlmIMhUZgKWOFtA6F4Joy7CVtKFAKYSm0i7Xd7vi15z4Gabssrpmlgt1Fmh_Bm5C9JZSnxWip6Xz4FXjfLZ1UZCYxa1qIMyvqQr7fNvpLu8ZiMQUZAwEU6pfVJ6VuZgT3344_bbKIp_x5fVPtNZ-m8Pl9FigzDxRe0SK2hG56topZnDFh81RNPHa0h2QGn8WUJU5BiUmoxAveHCYIdmfXG7wvoVhv6KoD3BdlLqUdPgvfoCeYbNj9883buOjR-Gdh3dda5uL6-DRnMhUHHIxkEMznAhGKZMJCQ1hEohNcm4To0m0hiqCdFMAiivPQmx56ePqUo41RLCmGygubzI9RbCofLwKRUyVJyJLHNYjgugxviQCShvo4PpOA6cT_tEBeS6mNjB10i20WZtjEFZk28MiOBeNY1t_6H1Dlpw-IYHldTQLmoZN6P1HppXL-NHO9qvnMU9u72bDx0Xy8E
linkProvider	ProQuest
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Face+recognition+accuracy+of+forensic+examiners%2C+superrecognizers%2C+and+face+recognition+algorithms&rft.jtitle=Proceedings+of+the+National+Academy+of+Sciences+-+PNAS&rft.au=Phillips%2C+P+Jonathon&rft.au=Yates%2C+Amy+N&rft.au=Hu%2C+Ying&rft.au=Hahn%2C+Carina+A&rft.date=2018-06-12&rft.eissn=1091-6490&rft.volume=115&rft.issue=24&rft.spage=6171&rft_id=info:doi/10.1073%2Fpnas.1721355115&rft_id=info%3Apmid%2F29844174&rft_id=info%3Apmid%2F29844174&rft.externalDocID=29844174
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1091-6490&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1091-6490&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1091-6490&client=summon