Is Facial Recognition Biased at Near-Infrared Spectrum As Well?

TL;DR

This study investigates whether facial recognition systems exhibit bias at the near-infrared spectrum, finding that performance is more equitable across gender and race compared to visible spectrum-based systems.

Contribution

First to analyze bias in facial recognition at the NIR spectrum using diverse datasets, showing more equitable performance across demographics.

Findings

Bias across gender and race is reduced at NIR spectrum.

NIR-based recognition shows consistent performance across African and Caucasian subjects.

Results suggest NIR spectrum may mitigate demographic biases present in visible spectrum recognition.

Abstract

Published academic research and media articles suggest face recognition is biased across demographics. Specifically, unequal performance is obtained for women, dark-skinned people, and older adults. However, these published studies have examined the bias of facial recognition in the visible spectrum (VIS). Factors such as facial makeup, facial hair, skin color, and illumination variation have been attributed to the bias of this technology at the VIS. The near-infrared (NIR) spectrum offers an advantage over the VIS in terms of robustness to factors such as illumination changes, facial makeup, and skin color. Therefore, it is worthwhile to investigate the bias of facial recognition at the near-infrared spectrum (NIR). This first study investigates the bias of the face recognition systems at the NIR spectrum. To this aim, two popular NIR facial image datasets namely, CASIA-Face-Africa and Notre-Dame-NIVL consisting of African and Caucasian subjects, respectively, are used to investigate the bias of facial recognition technology across gender and race. Interestingly, experimental results suggest equitable face recognition performance across gender and race at the NIR spectrum.