Walk that walk - it's unique

It may be a swagger, a shuffle or a limp, but the a person walks is almost as unique as their fingerprints, experts have found.

A team of American researchers is now developing a security system that can identify people by their gait.

Ultimately it is hoped that walk scanning will join other emerging biometric technologies, such as face and eye recognition, which already show promise.

While these mostly rely on machine vision, the team studying gait at the Georgia Institute of Technology in Atlanta focused on radar as the the basis of its system.

Radar signals bounced off any object produce a unique signature. The Georgia team decided to explore the potential of collecting echoes from various parts of the body as a person walked.

A computer was programmed to analyse these signals to define a set of unique characteristics for a particular individual.

In tests, the researchers were able correctly to identify 80 – 95% of volunteers purely from their walk.

Engineer John Geisheimer said: “We didn’t really know whether we would find anything useful, but fairly soon we began to come out with some distinct features.

“We have also been able to detect asymmetries such as a limp.”

For this reason, it was possible the technology might have medical as well as security applications, he said.

He added that it was “pretty readily apparent” when someone tried to trick the system by deliberately walking in a strange way.

The research was reported in The Engineer magazine, which said there were still significant hurdles to overcome before the technology could be used in practice.

Initial testing was carried out at short range, indoors, and using co-operative subjects.

The Georgia team will now build a more powerful radar that can detect people at more than 152 metres, and further refine the data processing system.