15 Apr Hanvon innovation can recognise workers when wearing masks
Hanvon, the company behind FaceGo, has developed China’s first facial recognition technology that can identify people when they are wearing a mask, as an aid in the fight against Covid-19. In China, the coronavirus has resulted in almost everyone wearing a surgical mask outdoors in the hope of warding off the virus. Face recognition, which uses facial geometry to identify users, generally has problems identifying people when their face is partially covered.
Hanvon’s technology is applicable to population face recognition, but they have also developed a standalone version that is used to identify previously enrolled individuals in a work environment. This is particularly useful for clinical settings, where the simple act of removing a mask for face recognition purposes can result in increased infections.
The product can be connected to a temperature sensor, measuring body temperature while performing user identification, allowing the system to raise an alert if it detects a body temperature above 38 degrees.
Hanvon committed a team of 20 staff to this development, building on its core technology developed over the past 10 years, using a sample database of about 6 million unmasked faces and a much smaller database of masked faces.
The team began work on the system in January, as the coronavirus outbreak gathered pace, and began rolling it out to the market after just a month.
When wearing a mask, the recognition rate can reach about 95%, which can ensure that most people can be identified. Without a mask the rate rises to 99.5%.
April 16, 2020