Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384339921> ?p ?o ?g. }
- W4384339921 abstract "Facial recognition errors can jeopardize national security, criminal justice, public safety and civil rights. Here, we compare the most accurate humans and facial recognition technology in a detailed lab-based evaluation and international proficiency test for forensic scientists involving 27 forensic departments from 14 countries. We find striking cognitive and perceptual diversity between naturally skilled super-recognizers, trained forensic examiners and deep neural networks, despite them achieving equivalent accuracy. Clear differences emerged in super-recognizers' and forensic examiners' perceptual processing, errors, and response patterns: super-recognizers were fast, biased to respond 'same person' and misidentified people with extreme confidence, whereas forensic examiners were slow, unbiased and strategically avoided misidentification errors. Further, these human experts and deep neural networks disagreed on the similarity of faces, pointing to differences in their representations of faces. Our findings therefore reveal multiple types of facial recognition expertise, with each type lending itself to particular facial recognition roles in operational settings. Finally, we show that harnessing the diversity between individual experts provides a robust method of maximizing facial recognition accuracy. This can be achieved either via collaboration between experts in forensic laboratories, or most promisingly, by statistical fusion of match scores provided by different types of expert." @default.
- W4384339921 created "2023-07-15" @default.
- W4384339921 creator A5001164336 @default.
- W4384339921 creator A5019518324 @default.
- W4384339921 creator A5023564321 @default.
- W4384339921 creator A5035715654 @default.
- W4384339921 creator A5044878893 @default.
- W4384339921 creator A5047695648 @default.
- W4384339921 creator A5061422047 @default.
- W4384339921 creator A5073967023 @default.
- W4384339921 date "2023-07-14" @default.
- W4384339921 modified "2023-09-26" @default.
- W4384339921 title "Diverse types of expertise in facial recognition" @default.
- W4384339921 cites W1912022303 @default.
- W4384339921 cites W1977286432 @default.
- W4384339921 cites W1978311498 @default.
- W4384339921 cites W1995341919 @default.
- W4384339921 cites W2009575609 @default.
- W4384339921 cites W2013584371 @default.
- W4384339921 cites W2034604217 @default.
- W4384339921 cites W2035234175 @default.
- W4384339921 cites W2049664898 @default.
- W4384339921 cites W2080008128 @default.
- W4384339921 cites W2098931048 @default.
- W4384339921 cites W2106354515 @default.
- W4384339921 cites W2117268255 @default.
- W4384339921 cites W2121320820 @default.
- W4384339921 cites W2121427122 @default.
- W4384339921 cites W2134401828 @default.
- W4384339921 cites W2140543255 @default.
- W4384339921 cites W2158275940 @default.
- W4384339921 cites W2160649823 @default.
- W4384339921 cites W2163470562 @default.
- W4384339921 cites W2168282726 @default.
- W4384339921 cites W2168385859 @default.
- W4384339921 cites W2168505921 @default.
- W4384339921 cites W2204202707 @default.
- W4384339921 cites W2228007736 @default.
- W4384339921 cites W2320871807 @default.
- W4384339921 cites W2505734102 @default.
- W4384339921 cites W2521423115 @default.
- W4384339921 cites W2559702471 @default.
- W4384339921 cites W2566596821 @default.
- W4384339921 cites W2604387740 @default.
- W4384339921 cites W2620226472 @default.
- W4384339921 cites W2738724892 @default.
- W4384339921 cites W2774657106 @default.
- W4384339921 cites W2787685653 @default.
- W4384339921 cites W2789467142 @default.
- W4384339921 cites W2790500130 @default.
- W4384339921 cites W2797378491 @default.
- W4384339921 cites W2805754451 @default.
- W4384339921 cites W2807768237 @default.
- W4384339921 cites W2841638860 @default.
- W4384339921 cites W2885231902 @default.
- W4384339921 cites W2897222461 @default.
- W4384339921 cites W2912087339 @default.
- W4384339921 cites W2919115771 @default.
- W4384339921 cites W2924010481 @default.
- W4384339921 cites W2969985801 @default.
- W4384339921 cites W2982699117 @default.
- W4384339921 cites W3010134765 @default.
- W4384339921 cites W3037784116 @default.
- W4384339921 cites W3092219074 @default.
- W4384339921 cites W3095556657 @default.
- W4384339921 cites W3099206234 @default.
- W4384339921 cites W3104123947 @default.
- W4384339921 cites W3105252786 @default.
- W4384339921 cites W3106928028 @default.
- W4384339921 cites W3119948327 @default.
- W4384339921 cites W3136870903 @default.
- W4384339921 cites W3137888317 @default.
- W4384339921 cites W3152710495 @default.
- W4384339921 cites W3164816383 @default.
- W4384339921 cites W3211809588 @default.
- W4384339921 cites W4207019402 @default.
- W4384339921 cites W4238768900 @default.
- W4384339921 cites W4246904949 @default.
- W4384339921 cites W4293802197 @default.
- W4384339921 cites W4376595422 @default.
- W4384339921 cites W4377011600 @default.
- W4384339921 doi "https://doi.org/10.1038/s41598-023-28632-x" @default.
- W4384339921 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37452069" @default.
- W4384339921 hasPublicationYear "2023" @default.
- W4384339921 type Work @default.
- W4384339921 citedByCount "0" @default.
- W4384339921 crossrefType "journal-article" @default.
- W4384339921 hasAuthorship W4384339921A5001164336 @default.
- W4384339921 hasAuthorship W4384339921A5019518324 @default.
- W4384339921 hasAuthorship W4384339921A5023564321 @default.
- W4384339921 hasAuthorship W4384339921A5035715654 @default.
- W4384339921 hasAuthorship W4384339921A5044878893 @default.
- W4384339921 hasAuthorship W4384339921A5047695648 @default.
- W4384339921 hasAuthorship W4384339921A5061422047 @default.
- W4384339921 hasAuthorship W4384339921A5073967023 @default.
- W4384339921 hasBestOaLocation W43843399211 @default.
- W4384339921 hasConcept C103278499 @default.
- W4384339921 hasConcept C115961682 @default.
- W4384339921 hasConcept C119857082 @default.
- W4384339921 hasConcept C140505726 @default.