With the potential to replace other systems of identification like retinal scanners and fingerprinting at locations such as airports where people pass through security checkpoints, computer scientists have created technology that can recognize and identify people based on their style of walking.

Publishing their findings in IEEE Transactions on Pattern Analysis and Machine Intelligence, the team of scientists found that their artificial intelligence-powered footstep recognition system can find patterns in a person's gate and can use that information to identify the person with near perfect accuracy.

“Each human has approximately 24 different factors and movements when walking, resulting in every individual person having a unique, singular walking pattern,” Omar Costilla Reyes, the lead author of the new study and a computer scientist at the University of Manchester, said in a statement.

Calling the system SfootBD, the scientists have determined that the system is almost 380 times more accurate than other methods of identification as well as being far less invasive than other biometric verification systems such as retinal scanners and fingerprinting.

“Focusing on non-intrusive gait recognition by monitoring the force exerted on the floor during a footstep is very challenging,” said Reyes. “That’s because distinguishing between the subtle variations from person to person is extremely difficult to define manually, that is why we had to come up with a novel AI system to solve this challenge from a new perspective.”

In order to develop the system, Reyes and the team gathered data about 20,000 footstep signals from over 120 individuals. The team applied an AI system called a deep residual neural network to the data where it collected information about factors such as gait speed, weight distribution and 3D measurement of walking style.

SfootBD was put to the test in three different environments: at home, at work and at airport security checkpoints where it demonstrated an almost 100 percent rate of accuracy, even when imposters mimicking another person’s gait were employed.

Unfortunately, with such technology comes concerns for privacy, and whether it is practical and or possible to gather data concerning individuals’ footsteps versus simply gathering photos for facial recognition. Likewise, the system requires tools such as floor pads and high-res cameras in order to work.