Goodbye, anonymity

Hitachi Kokusai Electric has built a high-performance facial recognition surveillance system that can pull a face from an image and identify it from a database of 36 million in one second.

Welcome to the next generation in surveillance technology. A Japanese company, Hitachi Kokusai Electric, has unveiled a novel surveillance camera that is able to capture a face and search up to 36 million faces in one second for a similar match in its database.

While the same task would typically require manually sifting through hours upon hours of recordings, the company´s new technology searches algorithmically for a facial match. It enables any organization, from a retail outlet to the government, to monitor and identify pedestrians or customers from a database of faces.

Hitachi's software is able to recognize a face with up to 30 degrees of deviation turned vertically and horizontally away from the camera, and requires faces to fill at least 40 pixels by 40 pixels for accurate recognition. Any image, whether captured on a mobile phone, handheld camera, or a video still, can be uploaded and  searched against its database for matches.

"This high speed is achieved by detecting faces through image recognition when the footage from the camera is recorded, and also by grouping similar faces," Seiichi Hirai, Hitachi Kokusai Electric researcher told DigInfo TV.

If a department store shoplifter is caught on camera, the suspected individual's image can be isolated and Hitachi's software will sift through its database to look for prior visits to that store. From there, it can generate clips of all the other footage the suspect appears in. These could allow authorities or shop owners to peruse the suspect's actions before and during the incident, potentially generating more clues that could identify him or her. {Read on}