Face recognition has become essential in our daily lives as a convenient and\ncontactless method of accurate identity verification. Process such as identity\nverification at automatic border control gates or the secure login to\nelectronic devices are increasingly dependant on such technologies. The recent\nCOVID-19 pandemic have increased the value of hygienic and contactless identity\nverification. However, the pandemic led to the wide use of face masks,\nessential to keep the pandemic under control. The effect of wearing a mask on\nface recognition in a collaborative environment is currently sensitive yet\nunderstudied issue. We address that by presenting a specifically collected\ndatabase containing three session, each with three different capture\ninstructions, to simulate realistic use cases. We further study the effect of\nmasked face probes on the behaviour of three top-performing face recognition\nsystems, two academic solutions and one commercial off-the-shelf (COTS) system.\n
Paper
References (19)
Scroll for more · 7 remaining