Computer scientist develops biometric knee identification system

A computer scientist from the Lawrence Technological University in Michigan has come out with a system of biometric identification using knees, ScienceDaily reports.

The computer scientist, Lior Shamir has created the approach, based on MRI, which can quickly register and identify people in a crowd. Shamil’s tests looked at knee scans from 2,686 people and have achieved an accuracy rate of about 93 percent. Though 93 percent is a relatively low score for a stand-alone biometric, because of the difficulty to deceive this measure, it could be coupled well with other biometrics, such as facial recognition or fingerprints to verify identity.

“Deceptive manipulation requires an invasive and complicated medical procedure, and therefore it is more resistant to spoofing compared to methods such as face, fingerprints, or iris,” Shamir said.

According to the report, a roadblock to this new system for identification is that MRI scanning typically requires a large machine and takes a significant amount of time to produce an image. That being said, developments in MRI technology are quickly gaining pace.

Along the same lines, Mark Nixon at the University of Southampton is developing a system for ear biometrics, which seeks to use the shape of people’s ears for identity.

“Using ears for identification has clear advantages over other kinds of biometric identification, as, once developed, the ear changes little throughout a person’s life,” Nixon said. “This provides a cradle-to-grave method of identification.”

Article Topics

biometrics  |  fraud prevention  |  identity verification  |  secure identification  |  spoofing