Accuracy Comparison across Face Recognition Algorithms: Where Are We on Measuring Race Bias?

被引：88
作者：
Cavazos J.G. [1 ]
Phillips P.J. [2 ]
Castillo C.D. [3 ]
O'Toole A.J. [1 ]
机构：
[1] School of Behavioral and Brain Sciences, University of Texas at Dallas, Richardson, 75080, TX
[2] Information Access Division, National Institute of Standards and Technology, Gaithersburg, 20899, MD
[3] Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, 21218, MD
来源：
IEEE Transactions on Biometrics, Behavior, and Identity Science | 2021年 / 3卷 / 01期
关键词：
deep convolutional neural networks; Face recognition algorithm; race bias; the other-race effect;
D O I：
10.1109/TBIOM.2020.3027269
中图分类号：
学科分类号：
摘要：
Previous generations of face recognition algorithms differ in accuracy for images of different races (race bias). Here, we present the possible underlying factors (data-driven and scenario modeling) and methodological considerations for assessing race bias in algorithms. We discuss data-driven factors (e.g., image quality, image population statistics, and algorithm architecture), and scenario modeling factors that consider the role of the 'user' of the algorithm (e.g., threshold decisions and demographic constraints). To illustrate how these issues apply, we present data from four face recognition algorithms (a previous-generation algorithm and three deep convolutional neural networks, DCNNs) for East Asian and Caucasian faces. First, dataset difficulty affected both overall recognition accuracy and race bias, such that race bias increased with item difficulty. Second, for all four algorithms, the degree of bias varied depending on the identification decision threshold. To achieve equal false accept rates (FARs), East Asian faces required higher identification thresholds than Caucasian faces, for all algorithms. Third, demographic constraints on the formulation of the distributions used in the test, impacted estimates of algorithm accuracy. We conclude that race bias needs to be measured for individual applications and we provide a checklist for measuring this bias in face recognition algorithms. © 2019 IEEE.
引用
收藏
页码：101 / 111
页数：10
相关论文
共 47 条
  • [1] Malpass R.S., Kravitz J., Recognition for faces of own and other race, J. Pers. Soc. Psychol, 13, 4, pp. 330-334, (1969)
  • [2] O'Toole A.J., Deffenbacher K., Abdi H., Bartlett J.C., Simulating the 'other-race effect' as a problem in perceptual learning, Connection Sci, 3, 2, pp. 163-178, (1991)
  • [3] Meissner C.A., Brigham J.C., Thirty years of investigating the own-race bias in memory for faces: A meta-analytic review, Psychol. Public Policy Law, 7, 1, pp. 3-35, (2001)
  • [4] Brigham J.C., Malpass R.S., The role of experience and contact in the recognition of faces of own- And other-race persons, J. Soc. Issues, 41, 3, pp. 139-155, (1985)
  • [5] Bukach C.M., Cottle J., Ubiwa J., Miller J., Individuation experience predicts other-race effects in holistic processing for both Caucasian and black participants, Cognition, 123, 2, pp. 319-324, (2012)
  • [6] Kelly D.J., Et al., Three-month-olds, but not newborns, prefer own-race faces, Develop. Sci, 8, 6, pp. F31-F36, (2005)
  • [7] Kelly D.J., Quinn P.C., Slater A.M., Lee K., Ge L., Pascalis O., The other-race effect develops during infancy: Evidence of perceptual narrowing, Psychol. Sci, 18, 12, pp. 1084-1089, (2007)
  • [8] Pezdek K., Blandon-Gitlin I., Moore C., Children's face recognition memory: More evidence for the cross-race effect, J. Appl. Psychol, 88, 4, pp. 760-763, (2003)
  • [9] Sangrigoli S., Pallier C., Argenti A.-M., Ventureyra V., Schonen S.D., Reversibility of the other-race effect in face recognition during childhood, Psychol. Sci, 16, 6, pp. 440-444, (2005)
  • [10] Yi L., Et al., Children with autism spectrum disorder scan own-race faces differently from other-race faces, J. Exp. Child Psychol, 141, pp. 177-186, (2016)
12345