Face recognition technology gets a lift

Tuesday, April 13, 2010 @ 03:04 PM gHale


There are now ways to make face recognition technology more efficient and more accurate.

While quite a few states in the U.S. now use facial recognition technology when issuing drivers licenses, obtaining accurate results remains a time intensive activity.

There is now a system capable of photographing an image of someone’s face and ear and comparing it against pre-stored images of the same person, with 95-100% accuracy, said Mohamed Abdel-Mottaleb, professor and chair in the University of Miami Department of Electrical and Computer Engineering.

The system researchers designed can use 3-D facial images, or combine 2-D images of the face with 3-D models of the ear, which they construct from a sequence of video frames, to identify people by unique facial features and ear shapes.

In the first method, researchers use 3-D facial images with over 95% recognition rate, in the lab setting. Conventional shape matching methods commonly used in 3-D face recognition are time consuming. Abdel-Mottaleb used a method that effectively increases computational efficiency while maintaining an acceptable recognition rate. He reduces the number of vertices (distinguishable landmarks of each face) considered when matching 3-D facial data, by automatically selecting the most discriminative facial regions. These automatically selected landmarks usually were within the regions of the nose, eye brows, mouth, and chin.

The second method called “Multi-Modal Ear and Face Modeling and Recognition” obtains a set of facial landmarks from frontal facial images and combines this data with a 3-D ear recognition component, which is a much more difficult identification process given the technique’s sensitivity to lighting conditions.

Fusing the scores of these two modalities, researchers achieved an identification rate of 100% in the lab. “No single approach can give you 100% accuracy,” Abdel-Mottaleb said. “One way to increase the accuracy is to use different biometrics and then combine them.”

These high-tech identification tools could help fight crime, and enforce border security. Researchers’ next goal is to expand their techniques to faces demonstrating facial expressions and to recognize faces using only profile images.



Leave a Reply

You must be logged in to post a comment.