The Gender Gap in Face Recognition Accuracy Is a Hairy Problem
Aman Bhatta, Vítor Albiero, Kevin W. Bowyer, Michael C. King
Abstract
It is broadly accepted that there is a “gender gap” in face recognition accuracy, with females having lower accuracy. However, relatively little is known about the cause(s) of this gender gap. We first demonstrate that female and male hairstyles have important differences that impact face recognition accuracy. In particular, variation in male facial hair contributes to a greater average difference in appearance between different male faces. We then demonstrate that when the data used to evaluate recognition accuracy is gender-balanced for how hairstyles occlude the face, the initially observed gender gap in accuracy largely disappears. We show this result for two different matchers, and for a Caucasian image dataset and an African-American dataset. Our results suggest that research on demographic variation in accuracy should include a check for balanced quality of the test data as part of the problem formulation. This new understanding of the causes of the gender gap in recognition accuracy will hopefully promote rational consideration of what might be done about it. To promote reproducible research, the matchers, attribute classifiers, and datasets used in this work are available to other researchers.