The pandemic has brought on new challenges for security and forensic experts worldwide. Travelers could just end up breezing through the airports without having to remove their facial masks if facial recognition technology can correctly scan the faces that wear masks.
The US Department of Homeland Security (DHS) is pioneering facial recognition technologies that will see through face masks. The trial has been supported by other science and technology bodies, and it has been on now for about two years. Technology vendors and volunteers have been testing top-notch biometric systems, making sure that they are up to the challenges posed by the use of facial recognition technology in several scenarios.
The rally is now focusing on the ability of AI systems to reliably collect and match images of individuals wearing an array of different face masks, with the promise of deploying the technology in international airports.
60 facial recognition configurations were tested, with about 600 volunteers taking part from 60 countries. It was a mix and match of six different image collection systems, that were also paired with ten different matching algorithms. These were evaluated on their ability to snap a picture when presented with a human face, to the reliability of the identification process.
The volunteers presented themselves both masked and unmasked. The DHS reports that on average, the AI systems correctly identified 93 percent of unmasked individuals. That success rate is lowered to 77 percent for those who wore masks.
Although the success rate is not a perfect one, it still reduces risks for many travelers, as well as for airport workers, who may no longer need to tell travelers to remove facial masks.
Facial recognition makes it possible to verify travelers’ identities with the snap of a picture rather than have them present a travel document. AI compares the picture against a gallery of images that the traveler has previously provided to the government to confirm a traveler’s identity.