FaceSkin: A Privacy Preserving Facial skin patch Dataset for multi Attributes classification

TL;DR

FaceSkin is a new dataset of facial skin images with diverse ages and races, including synthetic patches, designed to improve attribute classification and related applications like anti-spoofing and age estimation.

Contribution

The paper introduces FaceSkin, a comprehensive facial skin dataset with synthetic patches, addressing data scarcity and enabling multi-attribute classification and downstream tasks.

Findings

Effective in attribute classification tasks

Supports face anti-spoofing applications

Includes diverse synthetic skin patches

Abstract

Human facial skin images contain abundant textural information that can serve as valuable features for attribute classification, such as age, race, and gender. Additionally, facial skin images offer the advantages of easy collection and minimal privacy concerns. However, the availability of well-labeled human skin datasets with a sufficient number of images is limited. To address this issue, we introduce a dataset called FaceSkin, which encompasses a diverse range of ages and races. Furthermore, to broaden the application scenarios, we incorporate synthetic skin-patches obtained from 2D and 3D attack images, including printed paper, replays, and 3D masks. We evaluate the FaceSkin dataset across distinct categories and present experimental results demonstrating its effectiveness in attribute classification, as well as its potential for various downstream tasks, such as Face anti-spoofing and Age estimation.