Source of Publication
© 2013 IEEE. Recent studies have demonstrated that most commercial facial analysis systems are biased against certain categories of race, ethnicity, culture, age and gender. The bias can be traced in some cases to the algorithms used and in other cases to insufficient training of algorithms, while in still other cases bias can be traced to insufficient databases. To date, no comprehensive literature review exists which systematically investigates bias and discrimination in the currently available facial analysis software. To address the gap, this study conducts a systematic literature review (SLR) in which the context of facial analysis system bias is investigated in detail. The review, involving 24 studies, additionally aims to identify (a) facial analysis databases that were created to alleviate bias, (b) the full range of bias in facial analysis software and (c) algorithms and techniques implemented to mitigate bias in facial analysis.
Institute of Electrical and Electronics Engineers Inc.
Algorithmic discrimination, bias, classification bias, facial analysis, unfairness
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Khalil, Ashraf; Ahmed, Soha Glal; Khattak, Asad Masood; and Al-Qirim, Nabeel, "Investigating Bias in Facial Analysis Systems: A Systematic Review" (2020). All Works. 2125.
Indexed in Scopus
Open Access Type
Gold: This publication is openly available in an open access journal/series