Feeds

Google Glass to recognize you by your FASHION SENSE

'I'm not staring at your butt, my spatiogram analysis system is'

Intelligent flash storage arrays

The überhyped Google Glass augmented-reality specs will take a step beyond mere facial recognition technology, and recognize you not only by your features, but by what you're wearing.

The technology to be incorporated into Google's geeky goggles is called InSight, and was developed by Srihari Nelakuditi of the University of South Carolina, reports New Scientist in its March 9 issue.

Nelakuditi might want to do a trademark search on hybrid cars, IT consulting, and cable companies – but we digress...

The problem that Nelakuditi sought to solve is that facial recognition is all well and good if a subject is looking directly into a camera, but when you're wearing Google Glass you might find yourself scanning an entire crowd, searching for someone who may or may not be looking directly at you.

In a partnership with Romit Roy Choudhury and his crew at Durham, North Carolina's Duke University, Nelakuditi developed a recognition system that recognizes not your mug, but instead your "fashion fingerprint" – what you're wearing, including your clothing, jewelry, glasses, and the like. And, somewhat ominously for secure areas, your badge.

The group's prototype used a smartphone app to snap pictures of its subjects while they were web browsing, emailing, and the like, then used those images to create a spatiogram – esentially a histogram with added spatial-context information – that contained information on the distribution of colors, patterns, and textures of those subjects' garb.

Those spatiograms were then fed into a Google Glass headset and used to pick people out of a crowd. Even when the targets had their backs were to the camera, the system was 93 per cent successful in early testings with 15 different subjects.

InSight, disappointingly, won't flash snarky value judgments about a person's sartorial sophistication onto your Google Glass eyepiece – but what's a third-party app ecosystem for, eh?

There's one small drawback to the InSight echnology, however: people change their clothes. If your spatiogram was developed when you were wearing, say, a loud Hawaiian shirt, it's not going to identify you when you next appear in a Zuckerbergian hoodie.

"A person's visual fingerprint is only temporary, say for a day or an evening," Nelakuditi told New Scientist.

Maybe so – but we suggest that the spatiograms of such a-fashionistas as Chairman Mao, Larry Fine of The Three Stooges, many a black-shirted emo kid, and your decidedly dowdy and unimaginatively conventional Reg reporter might be reasonably consistent on a longer-term basis.

For that matter, you might be able to skip recalibrating your InSight-equipped Google Glass entirely during your next holiday at Southern California's famous Glen Eden nudist resort. ®

Intelligent flash storage arrays

Whitepapers

Designing and building an open ITOA architecture
Learn about a new IT data taxonomy defined by the four data sources of IT visibility: wire, machine, agent, and synthetic data sets.
How to determine if cloud backup is right for your servers
Two key factors, technical feasibility and TCO economics, that backup and IT operations managers should consider when assessing cloud backup.
Getting started with customer-focused identity management
Learn why identity is a fundamental requirement to digital growth, and how without it there is no way to identify and engage customers in a meaningful way.
Reg Reader Research: SaaS based Email and Office Productivity Tools
Read this Reg reader report which provides advice and guidance for SMBs towards the use of SaaS based email and Office productivity tools.
Website security in corporate America
Find out how you rank among other IT managers testing your website's vulnerabilities.