Washington, June 10 : Indian researchers have a new idea to boost security surveillance, and recognition of terrorists and outlaws.
C. Nandini of the Vidya Vikas Institute of Engineering and Technology, and C.N. Ravi Kumar of the S.J. College of Engineering in Mysore say that computer software with the ability to recognise people's gait may facilitate these purposes.
The researchers say that human gait typifies the motion characteristics of an individual, as everybody has a unique style of walking.
As to how their concept will work, they say that a camera with a side view can record a set of key frames as a person heads for the security desk at an airport, military installation or bank, for instance.
Such key frames can later be converted into silhouette form, and eventually be classified through a statistical analysis using so-called Shannon entropy, height measurements, and periodicity of the gait.
A database of different gaits thus created may enable security officials to recognise the gait of individuals checking in at an airport, even before they entered the concourse.
The researchers say that a comparison of such data with CCTV footage may also be used to track suspect terrorists or criminals who may otherwise be disguising their features or be carrying forged documents.
They insist that gait recognition has a significant advantage over more well-known biometrics, including fingerprinting and iris scanning, in that it is entirely unobtrusive.
They say that it can be used to identify an individual potentially from a considerable distance.
"The ability to identify a possible threat from a distance gives personnel a longer time frame in which to react before a possible suspect becomes a real threat," the researchers say.
Explaining their concept in the inaugural issue of the Inderscience publication, the International Journal of Biometrics, the researchers also revealed that they had already conducted initial tests on 20 people.
The researchers said that they recorded walk in a straight line at normal speed and stride as well as back and forth in front of a video camera placed perpendicular to their path.
Upon using the Shannon entropy equation and the individual's height, added the researchers, they could obtain good recognition rates.
Recognition performance of the system was sensitive to changes in big viewing angle above ten degrees, but was reasonably robust even when the individuals changed walking speed.