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

By P. Jonathon Phillips, Amy N. Yates, Ying Hu, Carina A. Hahn, E. Noyes, Kelsey Jackson, J. G. Cavazos, Géraldine Jeckeln, Rajeev Ranjan, S. Sankaranarayanan and 5 more. Proceedings of the National Academy of Sciences of the United States of America, 2018

361 citations recorded by the source corpus.

Significance This study measures face identification accuracy for an international group of professional forensic facial examiners working under circumstances that apply in real world casework. Examiners and other human face “specialists,” including forensically trained facial reviewers and untrained superrecognizers, were more accurate than the control groups on a challenging test of face identification. Therefore, specialists are the best available human solution to the problem of face identification. We present data comparing state-of-the-art face recognition technology with the best human face identifiers. The best machine performed in the range of the best humans: professional facial examiners. However, optimal face identification was achieved only when humans and machines worked in collaboration. 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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/8d9e4f3927dc32c685a01fe050707e4793b66e07

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Weihong Deng
2. Mei Wang
3. Yuanjun Xiong
4. Jiani Hu
5. Luc Van Gool
6. Xiaogang Wang
7. Lei Zhang
8. Yu Qiao

In Signal Processing

1. Mei Wang
2. Weihong Deng
3. Jiani Hu
4. Yaobin Zhang
5. Dongchao Wen
6. Dongyue Zhao
7. Xian Li
8. Pietro Perona

Citations in the corpus

• Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition (2020, background): “Since the performance of deep face recognition has surpassed human significantly [39], it is possible to achieve better cleansing results than manual labeling.”
• Towards causal benchmarking of bias in face analysis algorithms (2020, background): “Benchmarking in computer vision has a long history [6, 9, 22] including face recognition [47, 60, 61, 62, 27, 28] and face analysis [12].”
• Ongoing face recognition vendor test (FRVT) part 2: (2018, background): “Human review is error prone [4, 13, 19] and is sensitive to image acquisition and quality.”
• Deep Face Recognition: A Survey (2018, background): “mplates are essential for addressing public concern on privacy. 24 Understanding deep face recognition. Deep face recognition systems are now believed to surpass human performance in most scenarios [300]. There are also some interesting attempts to apply deep models to assist human operators for fa”
• Face Recognition Vendor Test (FRVT) part 2 :: identification (2019, background): “Human reviewers make recognition errors [5, 19, 27] and are sensitive to image acquisition and quality.”