A Chinese company says it has created a new facial recognition system that can identify people even if they are wearing masks.
Engineers at the Beijing-based Hanwang Technology Ltd. say their system is the first to be created to effectively identify people wearing face masks. A team of 20 people built the system in about a month. The system is based on existing technologies developed over the past 10 years. The process involved adding a collection of about 6 million unmasked faces and a much smaller collection of masked faces.
Hanwang is now selling two main kinds of products that use the new technology. One performs "single channel" recognition, which is designed to be used at the entrances to buildings. The other product is a "multi-channel" recognition system that uses groups of surveillance cameras (监控摄像头).
"When wearing a mask, the recognition rate can reach about 95 percent, which can ensure that most people can be identified," said Huang Lei, Hanwang's vice president. He added that the system's success rate for people not wearing a mask is about 99.5 percent.
Huang said Hanwang's technology can be used to identify and track people as they move about. He added the system can identify crime suspects, terrorists or make reports or warnings.
However, the new system struggles to identify people wearing both a mask and sunglasses. "In this situation, all of the key facial information is lost. In such cases recognition is tough," Huang said.
It was not immediately clear how people were reacting to the new technology. While some have expressed opposition to such tools, many others seem to have showed interest in the new system and accepted it as a way to deal with the current health emergency — the spread of the novel coronavirus (新型冠状病毒). Huang says he sees the interest likely expanding if the virus continues to spread and the use of face masks increases.
