MultiView Software

Make an unlimited number of views from one image

A 2D facial recognition system that has to compare an image of a person’s face that is turned away from center with another image that is correctly posed and lit will typically have difficulty matching the two images correctly. For example, if a 2D facial recognition system has to compare a live image of a person’s face that's posed off center with a database image that's centered (or vice versa) then the facial recognition system will typically result in lower confidence matching scores.
 

CyberExtruder's MultiView Software (also available as a plug-in for AutoMesh) provides system integrators with the ability to render almost any permutation of an original image. Since the 2D image is transformed into a model in 3D space, an infinite number of possibilities exist to re-pose the subject and re-render an image that is more acceptable to the facial recognition system. Legacy database images, for example, can be converted into 3D and then rendered back into 2D at an optimal pose.

In addition to the adjustments to a subject’s pose or expression, information pertaining to the camera (like focal length or zoom) can be altered; ambient lighting and light color can also be remodeled. MultiView facilitates individual facial recognition engines such that the facial recognition systems can match images with similar compositions without themselves needing to compensate for these factors.

By employing the MultiView software, a legacy database of images can be converted into 3D using the patented CyberExtruder 2D to 3D technology and then rendered back into 2D in what ever the optimal pose might be. Additionally, the virtual camera's focal length can be altered, the ambient lighting adjusted and many other parametric modifications can be employed to assist the facial recognition system such that it can now attempt to match like with like without needing to compensate for these other factors.