A Meta-Analysis of the Impact of Skin Tone and Gender on Non-Contact Photoplethysmography Measurements

Ewa M. Nowara, Daniel McDuff, Ashok Veeraraghavan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 284-285

It is well established that many datasets used for computer vision tasks are not representative and may be biased towards some demographic groups. The result of this is that performance evaluation may not reflect that in the real-world and might expose some groups (often minorities) to greater risks than others. Imaging photoplethysmography is a set of techniques that enables non-contact measurement of vital signs using imaging devices. While these methods hold great promise for low-cost and scalable physiological monitoring, it is important that performance is characterized accurately over diverse populations. We perform a meta-analysis across three datasets, including 73 people and over 400 videos featuring a broad range of skin types. While heart rate measurement can be performed on all skin types under certain conditions, we find that average performance drops significantly for the darkest skin type. We compare supervised and unsupervised learning algorithms and find that skin type does not impact all methods equally. The imaging photoplethysmography community should devote greater efforts to addressing these disparities and collecting representative datasets.