Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at Schiphol Airport

Abstract

Automatic border control at airports using automated facial recognition for checking the passport is becoming more and more common. A problem is that it is not clear how reliable these automatic gates are. Very few independent studies exist that assess the reliability of automated facial recognition for border control. In this evaluation study the reliability of automated facial recognition for automatic border passage was investigated. To investigate the quality of the images and face recognition, during 2 weeks data of real passengers were acquired at Schiphol Airport using 2 different automatic gates of about 950 passengers for both gates. This data alone already makes the evaluation study of great value. The evaluation experiment consisted of comparing live images of every passenger to the digital photographs stored on their passports. Every live image is compared to every digital passport photograph. In this way we can estimate both the False Accept Rate as well as the Verification Rate. In spite of the critical analysis in this study, the prospects for automatic border passage using face recognition are very good. We expect that, provided that the quality of the live images acquired by the gates is improved and if possible the quality of the digital photographs stored on the passport, excellent recognition results can be obtained with Verification Rates (VR) of above 99% at a False Accept Rate (FAR) of 0.1% or even lower.