New Take on Anti-Face Recognition (and a full-scale staging of “Brazil”)

In an ongoing saga of creative anti-face recognition devices from Dr. Zoz’s DEFCON hat to exotic makeup, there’s a new contender… a Japanese researcher mounting IR leds to glasses.

The goal of this system is to put bright illumination where the face is normally dark. LEDs around the bridge of the nose, eyebrows, and eyes light up super-bright, so face recognition systems don’t see the dark spots they’d expect.

For glasses wearers, one option might be tiny SMD chip LEDs. Connect some 1x2mm jobs with some suitably fine wire, and nobody need notice you’re a privacy nut (except the CCTV watchers)… it would just look like you’re wearing some neat arty glasses.

Brazil: Attention Terry Gilliam fans. Some bravely bureaucratic Brits put on an all-out full-scale staging of Brazil, complete with magnifier-equipped computer screens in a duct-and-wiring-jammed office… and Harry Tuttle & his team on rappel. The choice of Flickr for photo hosting is perhaps unintentionally appropriate in this prismatic age.

“You can try wearing sunglasses. But sunglasses alone can’t prevent face detection. Because face detection uses features like the eyes and nose, it’s hard to prevent just by concealing your eyes,” notes Isao Echizen, Associate Professor at the Digital Content and Media Sciences Research Division of Japan’s National Institute of Informatics.

So, with the help of colleagues, the Professor Echizen has developed a device he dubbed “privacy visor”, which uses 11 near-infrared LEDs to thwart face detection systems.

“Light from these near-infrared LEDs can’t be seen by the human eye, but when it passes through a camera’s imaging device, it appears bright. The LEDs are installed in these locations because, a feature of face detection is, the eyes and part of the nose appear dark, while another part of the nose appears bright. So, by placing light sources mostly near dark parts of the face, we’ve succeeded in canceling face detection characteristics, making face detection fail,” he explained for DigInfo TV.”

%d bloggers like this: