Researchers at the University of South Carolina and Duke University, partly backed by Google, have developed InSight, a human-recognition system designed for the Google Glass platform that can recognize people by the clothes they are wearing.
InSight develops a "fashion fingerprint" for a specific person based on their clothes, jewelry, badges, and glasses. The fingerprint is constructed by a smartphone app, which snaps a series of photos of the user as they read online content. The app then creates a spatiogram that captures the spatial distribution of colors, textures, and patterns of the clothes the user is wearing. In early tests using 15 volunteers, the system correctly identified people 93 percent of the time, even when they had their backs to the headset user.
The researchers say the system could help people with a condition known as face blindness, a neurological disorder that makes it impossible to recognize others, by telling them the names of nearby friends.
The researchers note that a person's fashion fingerprint changes each time they change their clothes, which helps protect their privacy.
From New Scientist
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found