Keep face

An engineer has developed a state-of-the-art system that can photograph an image of a person’s face and ear which then compares it against previously stored images.

This technology, which boasts 95-100 percent accuracy, could bring face recognition via a passport photograph to a higher level of security.

Mohamed Abdel-Mottaleb, professor and chair in the Department of Electrical and Computer Engineering at the University of Miami (UM), designed the system to use 3D facial images (or combine 2-D images of the face with 3-D models of the ear), which is constructed from a sequence of video frames.

To increase the computational efficiency of the method, Abdel-Mottaleb reduced the number of distinguishable landmarks of each face to be considered when matching the 3D data and selected landmarks primarily in the nose, eye brows, mouth, and chin regions.

He merged the method with a second one called Multi-Modal Ear and Face Modeling and Recognition, which takes the data from the first method and combines it with a 3-D ear recognition component.

In the lab, the UM team found the methods together achieved an identification rate of 100 per cent. No single approach can give you 100 percent accuracy," Abdel-Mottaleb said. "One way to increase the accuracy is to use different biometrics and then combine them."

Airport security

Meet a Role Model involved in the security at Jinnah International Airport Karachi Pakistan.
 

You’ve read it. Now review it.

Back to top

Back to top