Researchers at The University of Manchester have developed technology that can recognize individuals by the way they walk. The artificial intelligence (AI) system was found to accurately identify a person by their walk 99.3 percent of the time.
Fingerprints, facial recognition, and retinal scans are all physical biometrics that are commonly used for security screening. Behavioral biometrics, such as footstep recognition, can detect unique characteristics in a person’s natural movement.
“Each human has approximately 24 different factors and movements when walking, resulting in every individual person having a unique, singular walking pattern,” said lead author Omar Costilla Reyes. “Therefore monitoring these movements can be used, like a fingerprint or retinal scan, to recognize and clearly identify or verify an individual.”
While study participants walked, 3D data was collected using floor sensors and high-resolution cameras. The team used this information to create the largest-ever footstep database that includes almost 20,000 footstep signals from 127 study participants.
The experts tested the AI system by using some of the participants and also “imposters” in real-world security scenarios at homes, airport security checkpoints, and in the workplace.
“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.”
The new technology will provide a non-intrusive way for security screening, as individuals will not even have to take off their shoes for the recognition process to work.
“The research is also being developed to address the healthcare problem of markers for cognitive decline and onset of mental illness, by using raw footstep data from a wide-area floor sensor deployable in smart dwellings,” said Reyes. “Human movement can be a novel biomarker of cognitive decline, which can be explored like never before with novel AI systems.”
The study is published in the journal IEEE Transactions on Pattern Analysis and Machine Intelligence.