Biometrics firm Chincotech has developed a 3D transforming face algorithm that has the ability to continually learn from various racial faces allowing it to better identify people in 2D pictures.The system takes into account lighting conditions, expressions, compromised poses and bad image resolution.The company says that while there are plenty of facial recognition systems that utilize photos to fit 3D models into 2D faces; this is fundamentally flawed as the inherent differences found in different races are ignored. Chincotech's system embraces the differences and uses 3D face models that are based around multi-racial characteristics.Chincotech's Head Software Development Engineer – Paul Rashford said, “Our tests have proved that this technique coupled with a system that is taught to learn the difference between races and you have a system that delivers significantly more accurate results.”
Chincotech announces ‘multi-racial’ face recognition system
