The outbreak of COVID-19 has led to people wearing protective masks as a precautionary measure. This has further led to smartphone users experiencing high failure rates in unlocking their devices using facial recognition techniques like Face ID. A solution to this issue may now be on the horizon.
Leading Artificial Intelligence (AI) and facial recognition companies in China are said to have fixed the issue. Companies like SenseTime and Qingfei Technologies have reached a solution to the facial recognition problem by locating 14 key points on the face, Abacus News reported. This updated technology can not only recognise people wearing masks over their mouths, but also those wearing scarves or fake beards.
But before we go any further, let's see how face recognition works.
Face recognition identifies a person by locating several key points on the face and connecting them together to form a unique person-specific signature. The previous set of key points to successfully recognise a person wearing a mask included those around the eyes, nose and lips.
The facial recognition system developed by Amarjot Singh, a postdoctoral fellow at Stanford University, and his team now only requires the eyes and nose as key points. “Although it would be less accurate, a match still can be established,” Singh said.
SenseTime recently announced a face mask-busting tech and explained that its algorithm is designed to the issue by reading over 240 facial feature key points around the eyes, mouth and nose. It can make a match using just the parts of the face that are visible.
Facial recognition system generally does not need more data, but it does need more accurate data, according to Yufei Wei, Chief Marketing Officer at facial recognition company Qingfei Technologies.
Earlier, researchers from the University of Bradford led by professor Hassan Ugail improved their facial recognition model by feeding it with partial facial images and achieved 90 percent identification. A similar procedure was applied by another Chinese facial recognition company that claims it can now recognise people with masks.