Engineers Test Highly Accurate Face Recognition

The work of postdoctoral researcher Allen Yang, of Professor Shankar Sastry's Heterogeneous Sensor Network (HSN) group at the University of California, Berkeley, is the subject of an article in Wired magazine where a new facial-recognition algorithm was created by Yang with the help of researchers at both UC Berkeley and the University of Illinois at Urbana-Champaign.

"Most algorithms use what's known as meaningful facial features to recognize people-things like the eyes, nose and mouth," says Dr. Yang. "But that's incredibly limiting because you're only looking at pixels from a designated portion of the face and those pixels end up being much smaller than the whole image. Our algorithm shows that you only need to randomly select pixels from anywhere on the face. If you select enough of them, you can produce extremely high accuracy."

Yang's new algorithm may signal a quantum leap in face-recognition technology. Professor Ssstry, dean of UC Berkeley's College of Engineering notes that Yang's new method obsolesces years of research in this field.

Nonetheless, the new technique could have profound impact in many areas, with new models for online advertising, new ways of annotating video and still images, and new techniques for identifying people in public places.

See the complete article in Wired.