Description

This paper has been submitted for publication in the 15th IEEE International Conference on Automatic Face and Gesture Recognition on Automatic Facial and Gesture Recognition (FG2020). This work reveals a bias in scoring sensitivity across different subgroups when verifying the identity of a subject using facial images. In other words, the performance of an FR system on different subgroups (e.g., male vs female, Asian vs Black) typically depends on a global threshold (i.e., decision boundary on scores or distances to determine whether true or false pair). Our work uses fundamental signal detection theory to show that the use of a single, global threshold causes a skew in performance ratings across different subgroups. For this, we demonstrate that subgroup-specific thresholds are optimal in terms of overall performance and balance across subgroups.