Zobrazeno 1 - 10
of 140
pro vyhledávání: '"Michael C. King"'
Publikováno v:
IEEE Transactions on Information Forensics and Security. 17:127-137
Media reports have accused face recognition of being ''biased'', ''sexist'' and ''racist''. There is consensus in the research literature that face recognition accuracy is lower for females, who often have both a higher false match rate and a higher
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e6bcf0877b2fe979d00c25ba097b390
https://doi.org/10.1109/tifs.2021.3135750
https://doi.org/10.1109/tifs.2021.3135750
Autor:
Afi Edem Edi Gbekevi, Paloma Vela Achu, Gabriella Pangelinan, Michael C. King, Kevin W. Bowyer
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bde46f9f58d1bc872e2d3b41bb4169d3
https://doi.org/10.1109/wacvw58289.2023.00037
https://doi.org/10.1109/wacvw58289.2023.00037
Publikováno v:
2022 IEEE International Joint Conference on Biometrics (IJCB).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c73469328950fd76ce099c4e01fd70f
https://doi.org/10.1109/ijcb54206.2022.10007941
https://doi.org/10.1109/ijcb54206.2022.10007941
It is broadly accepted that there is a "gender gap" in face recognition accuracy, with females having higher false match and false non-match rates. However, relatively little is known about the cause(s) of this gender gap. Even the recent NIST report
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::84ecef6d729d0c38a5c095ea23f56c3b
http://arxiv.org/abs/2206.04867
http://arxiv.org/abs/2206.04867
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IEEE Transactions on Technology and Society. 1:8-20
Face recognition technology has recently become controversial over concerns about possible bias due to accuracy varying based on race or skin tone. We explore three important aspects of face recognition technology related to this controversy. Using t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4221bb2d9fc3747627bb03bc9d46ffde
https://doi.org/10.1109/tts.2020.2974996
https://doi.org/10.1109/tts.2020.2974996
Publikováno v:
2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::730c7811e2b5c027804fa0027b8cbd9b
https://doi.org/10.1109/wacvw54805.2022.00049
https://doi.org/10.1109/wacvw54805.2022.00049
Publikováno v:
IJCB
This paper is the first to explore the question of whether images that are classified incorrectly by a face analytics algorithm (e.g., gender classification) are any more or less likely to participate in an image pair that results in a face recogniti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b682c0240194c8c02a7a2057a26b53c
https://doi.org/10.1109/ijcb52358.2021.9484346
https://doi.org/10.1109/ijcb52358.2021.9484346
Autor:
Kevin W. Bowyer, Michael C. King
Publikováno v:
Biometric Technology Today. 2019:8-11
The varying accuracy of face recognition across race and gender has attracted a good deal of media attention. Publications ranging from the New York Times to Wired have carried headlines like ‘Facial Recognition Is Accurate, if You're a White Guy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::988eba9718238008507dd49d8b0a5e8e
https://doi.org/10.1016/s0969-4765(19)30114-6
https://doi.org/10.1016/s0969-4765(19)30114-6
Publikováno v:
SSCI
In this paper, we propose two new attacks: the Adversarial Universal False Positive (UFP) Attack and the Adversarial Universal False Negative (UFN) Attack. The objective of this research is to introduce a new class of attack using only feature vector
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::72b0cd1728c1c829ac6cc7627c3a973b
https://doi.org/10.1109/ssci47803.2020.9308298
https://doi.org/10.1109/ssci47803.2020.9308298