Researchers use multiple sources to identify faces

Researchers at Queensland University of Science and Technology (QUT; Brisbane, Australia) are attempting to develop a system that will be able to identify a person without the need to stand face on to a camera.

The project is supported by an Australian Research Council Discovery grant awarded to key researchers Professor Sridha Sridharan and Associate Professor Clinton Fookes from QUT's Science and Engineering Faculty.

Chief investigator Professor Fookes said that the focus of the research project would be to develop mathematical algorithms that would make it possible to take features from several video sources and convert them into a 3-D model from which facial features could be recognized.

The system would then be able to identify a shortlist of possible candidates. It would then be up to a human observer to authenticate the correct match.

The project is a joint collaboration with Professor Massimo Tistarelli from the University of Sassari in Italy and Dr Simon Lucey from the CSIRO.

-- by Dave Wilson, Senior Editor, Vision Systems Design