How Japan's Privacy Visor fools face-recognition cameras

The visor angles overhead light into cameras, confusing computer vision systems

Staffers at the National Institute of Informatics in Tokyo on August 11, 2015, show how a facial recognition system can identify someone wearing sunglasses (right) but not someone wearing the Privacy Visor (left), developed at the institute.

Staffers at the National Institute of Informatics in Tokyo on August 11, 2015, show how a facial recognition system can identify someone wearing sunglasses (right) but not someone wearing the Privacy Visor (left), developed at the institute.

If you're worried about Big Brother monitoring you from security cameras, Japan has developed eyewear that can keep you anonymous.

The Privacy Visor consists of a lightweight, wraparound, semitransparent plastic sheet fitted over eyewear frames. It's bulky and not exactly stylish, but it could have customized designs.

It's meant to thwart face-recognition camera systems through a very simple trick. It reflects overhead light into the camera lens, causing the area around the eyes to appear much brighter than it normally does.

That's enough to trick standard face-recognition systems, such as the Viola-Jones object detection framework, according to the National Institute of Informatics (NII), which has been developing the visor for years.

At a demo on Tuesday, NII staffers showed how a face-recognition program can easily identify someone by comparing video input to a database of head shots. The system also works when the subject is wearing sunglasses.

But the program couldn't identify a face when the subject was wearing the latest Privacy Visor prototype, which has a plastic film wrapped around 3D-printed frames.

Because the white plastic sheet is angled downward, such that the part near the nostrils sticks out more than the part near the eyes, it sends bright light toward the camera. That's the opposite of what some face-recognition algorithms expect, namely darker areas around the eyes and brighter areas around the nose and cheekbones. Those are the kinds of landmarks they need to find a face.

"This is a way to prevent privacy invasion through the many image sensors in smartphones and other devices that can unintentionally photograph people in the background," said NII researcher Isao Echizen, who has been developing the visor through several prototypes. He cited facial recognition apps such as NameTag for Google Glass as an example of how the technology is spreading.

A 2012 version, powered by a lithium-ion battery, included LED lights around the nose that shined near-infrared light toward cameras. Computer-vision systems were also fooled by the bright light, but the visor looked dorky and required a bulky power source.

While the latest prototype doesn't need power, it cuts incoming light by about 50 percent, but one's surroundings are still easily visible. The white pattern on the surface of the wraparound film can be created in various custom designs including horizontal lines, hexagons, or a web pattern -- as long as there's enough white material to reflect the overhead light.

NII plans to sell a more compact, stylish version of the latest prototype with titanium frames next year.

An NII partnership with eyewear manufacturers has raised two-thirds of its ¥2 million (US$16,016) goal in a crowdfunding campaign aimed at commercializing the glasses. Early-bird backers can order them for about ¥20,000 but they'll cost at least ¥30,000 when they go on sale in June 2016.

Tim Hornyak covers Japan and emerging technologies for The IDG News Service. Follow Tim on Twitter at @robotopia.

Join the CSO newsletter!

Error: Please check your email address.

Tags consumer electronicsNational Institute of Informaticssecurityprivacy

More about GoogleIDGIsaoNewsTwitter

Show Comments

Featured Whitepapers

Editor's Recommendations

Solution Centres

Stories by Tim Hornyak

Latest Videos

  • 150x50

    CSO Webinar: The Human Factor - Your people are your biggest security weakness

    ​Speakers: David Lacey, Researcher and former CISO Royal Mail David Turner - Global Risk Management Expert Mark Guntrip - Group Manager, Email Protection, Proofpoint

    Play Video

  • 150x50

    CSO Webinar: Current ransomware defences are failing – but machine learning can drive a more proactive solution

    Speakers • Ty Miller, Director, Threat Intelligence • Mark Gregory, Leader, Network Engineering Research Group, RMIT • Jeff Lanza, Retired FBI Agent (USA) • Andy Solterbeck, VP Asia Pacific, Cylance • David Braue, CSO MC/Moderator What to expect: ​Hear from industry experts on the local and global ransomware threat landscape. Explore a new approach to dealing with ransomware using machine-learning techniques and by thinking about the problem in a fundamentally different way. Apply techniques for gathering insight into ransomware behaviour and find out what elements must go into a truly effective ransomware defence. Get a first-hand look at how ransomware actually works in practice, and how machine-learning techniques can pick up on its activities long before your employees do.

    Play Video

  • 150x50

    CSO Webinar: Get real about metadata to avoid a false sense of security

    Speakers: • Anthony Caruana – CSO MC and moderator • Ian Farquhar, Worldwide Virtual Security Team Lead, Gigamon • John Lindsay, Former CTO, iiNet • Skeeve Stevens, Futurist, Future Sumo • David Vaile - Vice chair of APF, Co-Convenor of the Cyberspace Law And Policy Community, UNSW Law Faculty This webinar covers: - A 101 on metadata - what it is and how to use it - Insight into a typical attack, what happens and what we would find when looking into the metadata - How to collect metadata, use this to detect attacks and get greater insight into how you can use this to protect your organisation - Learn how much raw data and metadata to retain and how long for - Get a reality check on how you're using your metadata and if this is enough to secure your organisation

    Play Video

  • 150x50

    CSO Webinar: How banking trojans work and how you can stop them

    CSO Webinar: How banking trojans work and how you can stop them Featuring: • John Baird, Director of Global Technology Production, Deutsche Bank • Samantha Macleod, GM Cyber Security, ME Bank • Sherrod DeGrippo, Director of Emerging Threats, Proofpoint (USA)

    Play Video

  • 150x50

    IDG Live Webinar:The right collaboration strategy will help your business take flight

    Speakers - Mike Harris, Engineering Services Manager, Jetstar - Christopher Johnson, IT Director APAC, 20th Century Fox - Brent Maxwell, Director of Information Systems, THE ICONIC - IDG MC/Moderator Anthony Caruana

    Play Video

More videos

Blog Posts