Distributor DVS has taken on a GDPR-compliant facial recognition system that tackles store crime. It will be offered to its legion of resellers and CCTV security installers.
Facewatch uses cloud software-as-a-service to make advanced facial recognition “affordable for even small businesses”, it says. The company’s “watchlist” of known shoplifters lives in the cloud.
The centralised, managed database of biometric data - not stored photos – corresponds to the faces of people who have shoplifted or committed other crimes at businesses that subscribe to the service
The hardware to run Facewatch includes a standard HD CCTV camera and Intel NUC, a mini-PC that is only 4x4 inches in size and which consumes very little power. The system enables the playing and recording of video at 4K Ultra HD clarity, making it ideal for a facial recognition solution.
The cameras, placed at store entrances, send an image to an on-site NUC loaded with software that converts the image to an algorithm. The algorithm is compared to those in the Facewatch database in the cloud. If it discovers a match, an alert that includes the image of the individual entering the establishment - along with an accuracy reading - is sent to the retailer’s smartphone or other device, warning it that a known criminal on the watchlist has entered the premises.
To add a shoplifter to the watchlist “takes six key presses and about 20 seconds”, said the vendor, making it easy for store or security staff. “They simply follow a dropdown menu, the time and date are automated, tick the box, the whole thing’s designed to be simple,” said Nick Fisher, CEO of Facewatch.
The solution does not retain any personal data on anyone not on the watchlist. “If no match is discovered, the image is deleted in 0.3 seconds,” Fisher said, “and the entire process, from the moment a known shoplifter comes through the door, to the instant the retailer gets an alert, takes place in less than two seconds.”
If someone hacked into the cloud database, they could not reconstruct images of people’s faces based on the algorithm data, said Facewatch.