Demographic Variability in Face Image Quality Measures

TL;DR

This paper evaluates demographic biases in face image quality assessment algorithms, finding minimal bias across most measures but notable variations for skin tone in two measures, informing fairness in biometric systems.

Contribution

It systematically assesses demographic variability in ISO-standardized face image quality measures across age, gender, and skin tone, highlighting areas needing bias mitigation.

Findings

Most measures show no significant demographic bias.

Two measures vary notably with skin tone.

Results support fairer biometric quality assessments.

Abstract

Face image quality assessment (FIQA) algorithms are being integrated into online identity management applications. These applications allow users to upload a face image as part of their document issuance process, where the image is then run through a quality assessment process to make sure it meets the quality and compliance requirements. Concerns about demographic bias have been raised about biometric systems, given the societal implications this may cause. It is therefore important that demographic variability in FIQA algorithms is assessed such that mitigation measures can be created. In this work, we study the demographic variability of all face image quality measures included in the ISO/IEC 29794-5 international standard across three demographic variables: age, gender, and skin tone. The results are rather promising and show no clear bias toward any specific demographic group for most measures. Only two quality measures are found to have considerable variations in their outcomes for different groups on the skin tone variable.