3D boost for face recognition accuracy
05 August 2011 12:48 GMT

Face recognition gets boost from 3D

2D to 3D facial recognition technology is not new, but the extent to which it can now increase matching accuracy is impressive. 

CyberExtruder has announced the release of its new Aureus 3D facial reconstruction software, and the company is claiming that it can increase facial recognition matching accuracy by as much as 26.5 percent when compared to even the best 2D facial recognition products.

Impressive claims, but the company says they are based on evidence from tests by the U.S. Department of Homeland Security.

Aureus 3D improves the accuracy of facial recognition systems by taking a subject’s facial image and reconstructing it into a 3D format that factors in varied poses and facial expressions, and compensates for poor lighting and partial images. When Aureus 3D reconstructs a face, its patented processes are able to determine the person’s original pose relative to the camera. This information enables Aureus 3D to produce results which lead to matches when a subject may be turned away from the camera as much as 70 degrees and a downward (or upward) angle of 25 degrees.

Securlinx CEO Barry Hodge deploys Aureus 3D in his company’s forensics applications. He is currently using the technology with a major law enforcement agency in New Jersey, as well as for AmberVision enabling local law enforcement personnel to indentify missing children.

“Our ability to integrate Aureus 3D into portable (laptop) forensic stations for law enforcement agency investigative units is helping them identify images from crime scenes (i.e. convenience store robbery and other places with surveillance cameras) and occasionally from police sketches,” said Hodge. “We extract faces from surveillance videos, present them to Aureus 3D and then through the face matching software, where we are seeing a significant improvement in indentifying unknown suspects.”