Robust Sclera Segmentation for Skin-tone Agnostic Face Image Quality Assessment
This work addresses demographic fairness in face recognition systems, particularly for enrollment and border control scenarios, by making FIQA algorithms agnostic to skin-tone, age, and ethnicity, though it appears incremental as it builds on existing segmentation and feature analysis techniques.
The paper tackles the problem of demographic bias in face image quality assessment (FIQA) by proposing a robust sclera segmentation method that leverages the consistent whitish color of the eye sclera across all humans, regardless of skin-tone, age, and ethnicity, to produce invariant features for FIQA algorithms.
Face image quality assessment (FIQA) is crucial for obtaining good face recognition performance. FIQA algorithms should be robust and insensitive to demographic factors. The eye sclera has a consistent whitish color in all humans regardless of their age, ethnicity and skin-tone. This work proposes a robust sclera segmentation method that is suitable for face images in the enrolment and the border control face recognition scenarios. It shows how the statistical analysis of the sclera pixels produces features that are invariant to skin-tone, age and ethnicity and thus can be incorporated into FIQA algorithms to make them agnostic to demographic factors.