On the Applicability of Synthetic Data for Face Recognition

TL;DR

This paper evaluates the use of synthetic face images generated by StyleGAN models for face recognition testing, finding minimal differences compared to real images and discussing implications for privacy and performance assessment.

Contribution

It investigates the suitability of synthetic face images generated by StyleGAN and StyleGAN2 for face recognition testing, addressing data scarcity and privacy concerns.

Findings

Negligible differences between StyleGAN and StyleGAN2 images.

Minor discrepancies between synthetic and real face images.

Synthetic images are viable for performance evaluation.

Abstract

Face verification has come into increasing focus in various applications including the European Entry/Exit System, which integrates face recognition mechanisms. At the same time, the rapid advancement of biometric authentication requires extensive performance tests in order to inhibit the discriminatory treatment of travellers due to their demographic background. However, the use of face images collected as part of border controls is restricted by the European General Data Protection Law to be processed for no other reason than its original purpose. Therefore, this paper investigates the suitability of synthetic face images generated with StyleGAN and StyleGAN2 to compensate for the urgent lack of publicly available large-scale test data. Specifically, two deep learning-based (SER-FIQ, FaceQnet v1) and one standard-based (ISO/IEC TR 29794-5) face image quality assessment algorithm is utilized to compare the applicability of synthetic face images compared to real face images extracted from the FRGC dataset. Finally, based on the analysis of impostor score distributions and utility score distributions, our experiments reveal negligible differences between StyleGAN vs. StyleGAN2, and further also minor discrepancies compared to real face images.