当前位置: X-MOL 学术Proc. Natl. Acad. Sci. U.S.A. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Face recognition accuracy of forensic examiners, superrecognizers, and face recognition algorithms [Psychological and Cognitive Sciences]
Proceedings of the National Academy of Sciences of the United States of America ( IF 9.4 ) Pub Date : 2018-06-12 , DOI: 10.1073/pnas.1721355115
P. Jonathon Phillips 1 , Amy N. Yates 1 , Ying Hu 2 , Carina A. Hahn 2 , Eilidh Noyes 2 , Kelsey Jackson 2 , Jacqueline G. Cavazos 2 , Géraldine Jeckeln 2 , Rajeev Ranjan 3 , Swami Sankaranarayanan 3 , Jun-Cheng Chen 4 , Carlos D. Castillo 4 , Rama Chellappa 3 , David White 5 , Alice J. O’Toole 2
Affiliation  

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.



中文翻译:

法医,超级识别器和面部识别算法的面部识别准确性[心理与认知科学]

在取证应用中达到人脸识别准确度的上限可以最大程度地减少具有严重社会和个人后果的错误。尽管法医检查人员可以识别这些应用程序中的人脸,但很少对其准确性进行系统的测试。我们如何获得最准确的面部识别:使用单独工作或协同工作的人员和/或机器?通过人与计算机对人脸识别的全面比较,我们发现在具有挑战性的人脸识别测试中,法医人脸检查员,人脸审查员和超级识别器比指纹检查员和学生更准确。测试中的个人表现差异很大。在同一测试中,2015年至2017年间开发的四个深度卷积神经网络(DCNN)识别出了人类准确度范围内的面孔。随着时间的流逝,算法的准确性稳步提高,最新的DCNN得分高于法医面部检查员的中位数。使用众包方法,我们通过平均基于评级的身份判断来融合多个法医面部检查员的判断。融合判断的准确性比单独工作的个体要好得多。融合还起到稳定性能的作用,提高了表现较差的个人的得分,并降低了变异性。融合了最佳算法的单个法医面部检查员比两个检查员的组合更准确。因此,人与人之间以及人与机器之间的协作为重要应用中的识别精度提供了切实的好处。

更新日期:2018-06-13
down
wechat
bug