New rumored features about the Google Glass are coming out faster than the facts, with the latest being InSight: an app designed especially for Glass that will identify people based on their clothing.
Google Glass is the company's hot new "wearable computer" that will be released later this year and allows the wearer to have all of the information available on a smartphone embedded in his eyeglass lenses.
"CAN'T find a face in the crowd? Not to worry, a human recognition system can spot people for you — even when their faces aren't visible," New Scientist reports.
After InSight — which has been funded in part by Google itself — identifies the friend by his clothes, the person's name is overlaid across the Glass wearer's line of vision.
Insight was first unveiled last week at Georgia's Jekyll Island HotMobile Technology Conference.
"[InSight] aims to help users find their friends and be spotted themselves in busy places like shopping centres, sports stadia and airports," New Scientist says.
This is an important feature for Google Glass, as — according to InSight developer Srihari Nelakuditi — a face recognition system wouldn't work. People need to be facing the Google Glass wearer for face recognition software to be properly functional, Nelakuditi says.
Nelakuditi, who hails from the University of South Carolina in Columbia, worked closely with Romit Roy Choudhury and other colleagues from Duke University to dredge InSight from the stuff of sci-fi to that of the real.
By analyzing clothes, jewelry, glasses and other sartorial paraphernalia, InSight creates a "fashion fingerprint" of the person the Google Glass wearer might be looking at.
"This fingerprint is constructed by a smartphone app which snaps a series of photos of the user as they read web pages, emails or tweets," New Scientist says. "It then creates a file — called a spatiogram — that captures the spatial distribution of colours, textures and patterns (vertical or horizontal stripes, say) of the clothes they are wearing. This combination of colour, texture and pattern analysis makes someone easier to identify at odd viewing angles or over long distances."
As a means of protecting privacy, the fashion fingerprint is rendered moot once the person having been InSight'd changes his or her clothes.
"A person's visual fingerprint is only temporary, say for a day or an evening," Nelakuditi says.
InSight could be used as a practical application for those trying to "attract attention to themselves and their CV at a job fair, or outside a stadium where they are selling a spare ticket," Nelakuditi's team says.
Those with face blindness — a neurological disorder that makes recognizing other people impossible for the sufferer — could also benefit from InSight's ability to identify people by their clothing.
Preliminary testing has shown that the app is quite accurate. With 15 volunteers involved, InSight made correct identifications 93 percent of the time, even when the persons being looked at had their backs turned.
Like what you're reading? Follow @profklickberg.
