EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Which Skin Tone Measures Are the Most Inclusive? An Investigation of Skin Tone Measures for Artificial Intelligence

Courtney M. Heldreth, Ellis P. Monk, Alan T. Clark, Candice Schumann, Xango Eyee, Susanna Ricco

ACM Journal on Responsible Computing · 31.03.2024 · 1 (1) · 1-21

DOI: 10.1145/3632120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Journal on Responsible Computing, online erschienen am 20.03.2024. Verfasst von Courtney M. Heldreth und 5 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin tone plays a critical role in artificial intelligence (AI). However, many algorithms have exhibited unfair bias against people with darker skin tones. One reason this occurs is a poor understanding of how well the scales we use to measure and account for skin tone in AI actually represent the variation of skin tones in people affected by these systems. To address this, we conducted a survey with 2,214 people in the United States to compare three skin tone scales: The Fitzpatrick 6-point scale, Rihanna's Fenty Beauty 40-point skin tone palette, and a newly developed Monk 10-point scale from the social sciences. We find that the Fitzpatrick scale is perceived to be less inclusive than the Fenty and Monk skin tone scales, and this was especially true for people from historically marginalized communities (i.e., people with darker skin tones, BIPOCs, and women). We also find no statistically meaningful differences in perceived representation across the Monk skin tone scale and the Fenty Beauty palette. We discuss the ways in which our findings can advance the understanding of skin tone in both the social science and machine learning communities.

Zitieren

APA

Heldreth, C. M., Monk, E. P., Clark, A. T., Schumann, C., Eyee, X., & Ricco, S. (2024). Which Skin Tone Measures Are the Most Inclusive? An Investigation of Skin Tone Measures for Artificial Intelligence. ACM Journal on Responsible Computing, 1(1), 1-21. https://doi.org/10.1145/3632120

Vancouver

Heldreth CM, Monk EP, Clark AT, Schumann C, Eyee X, Ricco S. Which Skin Tone Measures Are the Most Inclusive? An Investigation of Skin Tone Measures for Artificial Intelligence. ACM Journal on Responsible Computing. 2024;1(1):1-21. doi:10.1145/3632120

BibTeX
@article{Heldreth2024,
  author = {Heldreth, Courtney M. and Monk, Ellis P. and Clark, Alan T. and Schumann, Candice and Eyee, Xango and Ricco, Susanna},
  title = {Which Skin Tone Measures Are the Most Inclusive? An Investigation of Skin Tone Measures for Artificial Intelligence},
  journal = {ACM Journal on Responsible Computing},
  year = {2024},
  volume = {1},
  number = {1},
  pages = {1--21},
  doi = {10.1145/3632120}
}
Kostenlos starten →