At a time when use of electronic surveillance.
This is not the first time a facial recognition system for those wearing masks has been developed. A machine learning algorithm that uses key facial points for recognition was developed by Clearview AI data breach.
As China's first. The company informs that this system has been designed specifically to help with coronavirus containment since masked faces have become so common in Chinese cities plagued by the outbreak. This new surveillance system will most likely be put to use soon since one of Hanwang's main clients is the Chinese Ministry of Public Security. That's the section of government that oversees law enforcement.
Designed To Help Contain Coronavirus
The system comes in two variants. One is a single channel version that is useful for entrances to offices and other buildings, while the second one is a sophisticated multi-channel model designed for crowd identification. The latter one uses multiple surveillance cameras and the company claims it can identify a crowd of up to 30 people in one second. While it is not clear if this uses a similar machine learning method to the one employed by the Cambridge researchers, what is unique is that this technology can be converted into a coronavirus screening system by connecting it to a temperature sensor to monitor the body temperature at the same time. Still, the technology is not perfect. If someone wears a mask and sunglasses, then much of the key facial information is lost, making detection tough.
Using thermal detectors to find people with unusually high body temperatures has become a trusted tool in the fight to contain coronavirus. However, this might be the first time that has been combined with facial recognition for the specific task at hand. It will be interesting to see if other governments begin to invest in similar surveillance systems to help swell the outbreak in their own countries. Either way, it is important to keep in mind that this is still a controversial technology, considering it can be bought and used by companies and law enforcement authorities for privacy-invading purposes other than containing a viral outbreak, like coronavirus.
Source: Reuters