Surveying Racial Bias in Facial Recognition: Balancing Datasets and Algorithmic Enhancements

Author:

Sumsion Andrew1ORCID,Torrie Shad1ORCID,Lee Dah-Jye1ORCID,Sun Zheng1ORCID

Affiliation:

1. Electrical and Computer Engineering Department, Brigham Young University, Provo, UT 84602, USA

Abstract

Facial recognition systems frequently exhibit high accuracies when evaluated on standard test datasets. However, their performance tends to degrade significantly when confronted with more challenging tests, particularly involving specific racial categories. To measure this inconsistency, many have created racially aware datasets to evaluate facial recognition algorithms. This paper analyzes facial recognition datasets, categorizing them as racially balanced or unbalanced while limiting racially balanced datasets to have each race be represented within five percentage points of all other represented races. We investigate methods to address concerns about racial bias due to uneven datasets by using generative adversarial networks and latent diffusion models to balance the data, and we also assess the impact of these techniques. In an effort to mitigate accuracy discrepancies across different racial groups, we investigate a range of network enhancements in facial recognition performance across human races. These improvements encompass architectural improvements, loss functions, training methods, data modifications, and incorporating additional data. Additionally, we discuss the interrelation of racial and gender bias. Lastly, we outline avenues for future research in this domain.

Publisher

MDPI AG

Reference146 articles.

1. Coe, J., and Atay, M. (2021). Evaluating impact of race in facial recognition across machine learning and deep learning algorithms. Computers, 10.

2. Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?;Cavazos;IEEE Trans. Biom. Behav. Identity Sci.,2020

3. Issues related to face recognition accuracy varying based on race and skin tone;Krishnapriya;IEEE Trans. Technol. Soc.,2020

4. Pagano, T.P., Loureiro, R.B., Araujo, M.M., Lisboa, F.V.N., Peixoto, R.M., Guimaraes, G.A.d.S., Santos, L.L.d., Cruz, G.O.R., de Oliveira, E.L.S., and Cruz, M. (2022). Bias and unfairness in machine learning models: A systematic literature review. arXiv.

5. Addressing bias in artificial intelligence in health care;Parikh;JAMA,2019

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3