acm-header
Sign In

Communications of the ACM

ACM TechNews

Studies at the ­ji Advance in Recognizing People By the Way They Walk


View as: Print Mobile App Share:
A famous foursome cross the street.

A new biometric security technique recognizes individuals based on the way they walk, combined with their unique silhouettes.

Credit: Apple (Parlophone)/EMI

Jaume I University researchers are developing a biometric security technique that is based on the way people walk and their silhouette.

The researchers note that their technique offers significant advantages since recognition can be done remotely and does not require the cooperation of the subject. "Although it is easy to manipulate and consciously change, each person walks in a different way," says Jaume I University's Ramon Mollineda.

The researchers used a video of a subject walking to create a system that distinguishes a background silhouette. The background image becomes a sequence of silhouettes, placed one upon the other, resulting in a summary image. The final representation stores all of the subject's physical appearance and walking movements, which creates a unique mark for each subject.

Mollineda notes their technique would be much more effective if it is combined with facial recognition. "They are complementary methods: the way you walk can be detected from a distance and does not require a high-resolution image, while face recognition is performed close-up and with a high-resolution image," he says.

From Jaume I University (Spain)
View Full Article

 

Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account