Bellus3D to demonstrate 3D face recognition solution for smartphones
Facial recognition startup Bellus3D will demonstrate its mobile 3D face recognition technology at MWCA (Mobile World Congress Americas) 2017 this week in San Francisco.
The 3D face recognition can be used to unlock an Android smartphone with a 3D camera, which Bellus3D is currently developing with its hardware partners.
The face recognition solution can also identify a person by searching a database of 3D face models on a server, using IR sensors and Laser pattern emitters to capture and compare tens of thousands of 3D points on a face.
The 3D face recognition capability works in low light or even in complete darkness, is not impacted by color or makeup, supports a range of head poses, and cannot be spoofed with a 2D photo.
In lab tests, Bellus3D face recognition can achieve FAR (False Acceptance Rate) of 0.001 percent (1 in 100,000), secure enough for financial transactions, with 10 percent FRR (False Rejection Rate) in single verification and 1 percent FRR in continuous verification.
Bellus3D’s face recognition uses 3D face models captured by Bellus3D Face Camera, a high-resolution face scanner attached to a mobile device.
The company is working with a few 3D imaging hardware companies to develop an embedded version of the 3D camera to replace the front-facing camera in new smartphones.
Users must first enroll their 3D face model and are able to register multiple facial expressions if needed.
They can then unlock the smartphone by picking it up and looking at it. The 3D camera can automatically activate and detect the nearest face to match against the registered 3D face models within a few hundred milliseconds.
“Face unlocking a phone will be the catalyst for the widespread adoption of 3D cameras in smartphones,” said Eric Chen, co-founder and CEO at Bellus3D. “We are excited to be developing leading edge technologies to accelerate the trend.”
Bellus3D face recognition can also be conducted in the cloud to determine the identity of a person, grant access to a secure facility, or customize an environment.
The face data from a 3D camera can be securely sent to a cloud server containing a database of 3D face models for identification.
The face recognition technology can compare dozens of 3D face models per second on a single server as well as run in parallel on multiple servers to search hundreds of face models in a few seconds.
The company’s face recognition solution is now available as a demo on supported Android devices with a Bellus3D Face Camera.
Bellus3D will also be demonstrating its latest Face Camera, which is set to be released in Q4 2017.