Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data

TL;DR

This paper investigates how face ageing affects biometric recognition performance using synthetic data generated by recent face age modification algorithms, highlighting minor effects for short-term and significant challenges for long-term ageing.

Contribution

It introduces the use of synthetic face ageing data to study recognition performance and compares it with real data, revealing insights into the impact of short-term and long-term ageing.

Findings

Short-term ageing (1-5 years) has minor impact on recognition.

Long-term ageing (>20 years) significantly challenges verification.

Synthetic data effectively models face ageing effects for biometric analysis.

Abstract

The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real dataset is used to evaluate the effects of short-term ageing, comparing the biometric performance to the synthetic domain. The main findings indicate that short-term ageing in the range of 1-5 years has only minor effects on the general recognition performance. However, the correct verification of mated faces with long-term age differences beyond 20 years poses still a significant challenge and requires further investigation.