SREDS: A dichromatic separation based measure of skin color

TL;DR

This paper introduces SREDS, a novel skin color measure based on dichromatic reflection, enabling accurate skin tone estimation from a single image without needing consistent background or lighting conditions.

Contribution

The work presents a new data-driven skin color measure using dichromatic reflection model that overcomes limitations of previous methods requiring calibration or labeled datasets.

Findings

Effective skin tone estimation from single images.

No need for controlled lighting or background.

Potential to improve fairness in face recognition systems.

Abstract

Face recognition (FR) systems are fast becoming ubiquitous. However, differential performance among certain demographics was identified in several widely used FR models. The skin tone of the subject is an important factor in addressing the differential performance. Previous work has used modeling methods to propose skin tone measures of subjects across different illuminations or utilized subjective labels of skin color and demographic information. However, such models heavily rely on consistent background and lighting for calibration, or utilize labeled datasets, which are time-consuming to generate or are unavailable. In this work, we have developed a novel and data-driven skin color measure capable of accurately representing subjects' skin tone from a single image, without requiring a consistent background or illumination. Our measure leverages the dichromatic reflection model in RGB space to decompose skin patches into diffuse and specular bases.