Color Invariant Skin Segmentation

TL;DR

This paper introduces a color-invariant skin segmentation method that achieves consistent detection across diverse skin tones by training with augmented datasets, reducing bias and improving generalization in various imaging conditions.

Contribution

The work presents a novel approach that learns color-invariant features for skin detection, using dataset augmentation to enhance robustness across skin tones and lighting conditions.

Findings

Improved precision and recall across multiple skin tones.

More consistent performance across different ethnicities.

Effective on grayscale and unconstrained illumination images.

Abstract

This paper addresses the problem of automatically detecting human skin in images without reliance on color information. A primary motivation of the work has been to achieve results that are consistent across the full range of skin tones, even while using a training dataset that is significantly biased toward lighter skin tones. Previous skin-detection methods have used color cues almost exclusively, and we present a new approach that performs well in the absence of such information. A key aspect of the work is dataset repair through augmentation that is applied strategically during training, with the goal of color invariant feature learning to enhance generalization. We have demonstrated the concept using two architectures, and experimental results show improvements in both precision and recall for most Fitzpatrick skin tones in the benchmark ECU dataset. We further tested the system with the RFW dataset to show that the proposed method performs much more consistently across different ethnicities, thereby reducing the chance of bias based on skin color. To demonstrate the effectiveness of our work, extensive experiments were performed on grayscale images as well as images obtained under unconstrained illumination and with artificial filters. Source code: https://github.com/HanXuMartin/Color-Invariant-Skin-Segmentation