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

The deployment of face recognition systems has gained popularity in various application scenarios, such as border control initiatives like the European Entry-Exit System (EES) [Eu19]. In particular, the EES will be used as a central system for collecting and querying traveller data to the Schengen area at all border crossing points to facilitate the cooperation of visa and law enforcement authorities. The biometric performance of a system deployed in such sensitive environments must comply with high standards, such as those defined in the best practices for automated border control of the European Border and Coast Guard Agency (Frontex) [Fr15]. At the same time, the European General Data Protection Law complicates the processing of biometric data to avoid privacy leakages. Without an appropriate performance testing strategy, the risk of security lapses increases significantly and allows for the discriminatory treatment of travellers due to algorithmic or dataset bias. One solution to the lack of available test data includes the generation of synthetic data samples. However, in order to conduct reliable biometric performance tests, the synthetic samples must be as similar as possible to data collected in operational environments.