DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation

TL;DR

DiffClean employs a diffusion model to remove makeup from facial images, enhancing age estimation and face verification accuracy against makeup-based deception.

Contribution

It introduces a novel diffusion-based approach for makeup removal that improves biometric verification and age estimation robustness.

Findings

Increases age estimation accuracy by 5.8%

Enhances face verification TMR by 5.1% at FMR=0.01%

Outperforms multiple baselines in biometric and perceptual quality

Abstract

Accurate age verification can protect underage users from unauthorized access to online platforms and e-commerce sites that provide age-restricted services. However, accurate age estimation can be confounded by several factors, including facial makeup that can induce changes to alter perceived identity and age to fool both humans and machines. In this work, we propose DiffClean which erases makeup traces using a text-guided diffusion model to defend against makeup attacks. DiffClean improves age estimation (minor vs. adult accuracy by 5.8%) and face verification (TMR by 5.1% at FMR=0.01%) compared to images with makeup. Our method is robust across digitally simulated and real-world makeup styles, and outperforms multiple baselines in terms of biometric and perceptual quality. Our codes are available at https://github.com/Ektagavas/DiffClean.