For Entry-Exit technologies, such as US VISIT and Smart Borders (e-borders), a watchlist normally contains highquality biometric traits and is checked only against visitors. The situation can change drastically if low-quality images are added into the watchlist. Motivated by this fact, we introduce a systematic approach to assessing the risk of travellers using a biometric-enabled watchlist where some latency of the biometric traits is allowed. The main results presented herein include: (1) a taxonomical view of the watchlist technology, and (2) a novel risk assessment technique. For modelling the watchlist landscape, we propose a risk categorisation using the Doddington metric. We evaluate via experimental study on large-scale facial and fingerprint databases, the risks of impersonation and mis-identification in various screening scenarios. Other contributions include a study of approaches to designing a biometric-enabled watchlist for e-borders: a) risk control and b) improving performance of the e-border via integrating the interview supporting machines.

No abstract

Biometric‐enabled systems have become highly desirable to authenticate and identify people due to the proliferation of mobile technologies. Their application in general settings, such as automated border gates using ePassports or at entrances to buildings or rooms, has become popular as well. Regrettably, where current biometry scanning technologies are reliably suitable for single‐user devices, when hundreds or thousands of people need to be processed, shortcomings emerge. The requirement of physically coming to a halt during scanning poses a limitation to the throughput of the people processed. Additionally, since most of these systems require physical contact, hygienic concerns need to be considered, especially with contagious pandemics such as COVID‐19. In this article, we present a solution to the issue of limited throughput and hygienic concerns by developing a biometric system that allows identification on the fly. Using the experimental setup of our design, we demonstrate that hand‐related biometrics can be acquired on the fly. Furthermore, using a random decision forest classifier and our house‐collected database containing over 560 unique images, we inaugurated that the system is a viable solution for biometric identification on the fly.

No abstract

No abstract