SIAMESE RECONSTRUCTION CONVOLUTIONAL NEURAL NETWORK FOR POSE-INVARIANT FACE RECOGNITION

摘要

A computer-implemented method, system, and computer program product is provided for pose-invariant facial recognition. The method includes generating, by a processor using a recognition neural network (150), a rich feature embedding for identity information and non-identity information for each of one or more images. The method also includes generating, by the processor using a Siamese reconstruction network (160), one or more pose-invariant features (170) by employing the rich feature embedding for identity information and non-identity information. The method additionally includes identifying, by the processor, a user (180) by employing the one or more pose-invariant features. The method further includes controlling an operation of a processor-based machine to change a state of the processor-based machine, responsive to the identified user in the one or more images.