Measuring Hidden Bias within Face Recognition via Racial Phenotypes [other]

Yucer, Seyma (Durham University, UK); Breckon, Toby (Durham University, UK); Al Moubayed, Noura (Durham University, UK); Tektas, Furkan (BuboAI, Middlesbrough, UK)

Actions

Download Analytics Citations

Export to: EndNote | Zotero | Mendeley

Collections

This file is not currently in any collections.

Measuring Hidden Bias within Face Recognition via Racial Phenotypes [other] Open Access

Recent work reports disparate performance for intersectional racial groups across face recognition tasks: face verification and identification. However, the definition of those racial groups has a significant impact on the underlying findings of such racial bias analysis. Previous studies define these groups based on either demographic information (e.g. African, Asian etc.) or skin tone (e.g. lighter or darker skins). The use of such sensitive or broad group definitions has disadvantages for bias investigation and subsequent counter-bias solutions design. By contrast, this study introduces an alternative racial bias analysis methodology via facial phenotype attributes for face recognition. We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject. We propose categorical test cases to investigate the individual influence of those attributes on bias within face recognition tasks. We compare our phenotype-based grouping methodology with previous grouping strategies and show that phenotype-based groupings uncover hidden bias without reliance upon any potentially protected attributes or ill-defined grouping strategies. Furthermore, we contribute corresponding phenotype attribute category labels for two face recognition tasks: RFW for face verification and VGGFace2 (test set) for face identification.

Descriptions

Resource type: Other
Contributors: Creator: Yucer, Seyma ¹
Contact person: Yucer, Seyma ¹
Editor: Breckon, Toby ¹
Tektas, Furkan ²
Al Moubayed, Noura ¹

¹ Durham University, UK
² BuboAI, Middlesbrough, UK
Funder
Research methods
Other description: Deposit consists of metadata files of two datasets and one machine learning model trained parameters. Code published on GitHub: https://github.com/seymayucer/FacialPhenotypes

Originally published as: Understanding racial bias using facial phenotypes
Keyword: Facial phenotypes
Labels
Pre-trained models
Subject: Face perception--Racial bias
Location: Durham, England, United Kingdom
Language: English
Cited in: arxiv:2110.09839
Identifier: ark:/32150/r2hm50tr746
doi:10.15128/r2hm50tr746
Rights: Creative Commons Attribution 4.0 International (CC BY)
Publisher: Durham University
Date Created

File Details

Depositor: S. Yucer Tektas
Date Uploaded: 20 April 2021, 12:04:16
Date Modified: 5 January 2022, 11:01:47
Audit Status: Audits have not yet been run on this file.
Characterization: File format: zip (ZIP Format)

Mime type: application/zip

File size: 242817654

Last modified: 2021:04:20 13:52:28+01:00

Filename: model_and_labels.zip

Original checksum: 2774ea5e7a10aab0b9db9eb6cdab8450

Activity of users you follow
User Activity	Date
User N. Syrotiuk has updated Understanding racial bias using facial phenotypes [other]	about 3 years ago
User N. Syrotiuk has updated Understanding racial bias using facial phenotypes [other]	about 3 years ago
User N. Syrotiuk has updated Understanding Racial Bias using Facial Phenotypes [other]	about 3 years ago
User N. Syrotiuk has updated Understanding Racial Bias using Facial Phenotypes [other]	about 3 years ago
User N. Syrotiuk has updated Understanding Racial Bias using Facial Phenotypes [dataset]	about 3 years ago