US 10,762,337 B2 · Face synthesis using generative adversarial networks

Abstract

Training a generative adversarial network (GAN) for use in facial recognition, comprising providing an input image of a particular face into a facial recognition system to obtain a faceprint; obtaining, based on the input faceprint and a noise value, a set of output images from a GAN generator; obtaining feedback from a GAN discriminator, wherein obtaining feedback comprises inputting each output image into the GAN discriminator and determining a set of likelihood values indicative of whether each output image comprises a facial image; determining, based on each output image, a modified noise value; inputting each output image into a second facial recognition network to determine a set of modified faceprints; defining, based on each modified noise value and modified faceprint, feedback for the GAN generator, wherein the feedback comprises a first value and a second value; and modifying control parameters of the GAN generator.

Claims20

Dependent claims

A method of training a facial recognition system, comprising:

providing an input image of a particular face into a first facial recognition system;
obtaining, from the first facial recognition system, an input faceprint;
obtaining, based on the input faceprint and a noise value, a first set of output images and a second set of output images from a pre-trained generative adversarial network (GAN) generator, wherein the pre-trained GAN generator generates the first set of output images recognizable as images of the particular face and the second set of output images recognizable as negative images of the particular face, and wherein negative images of the particular face comprise images not recognizable as images of the particular face;
and
training, based on the first set of output images and the second set of output images, a second facial recognition system to recognize the particular face.

2 more elements

An apparatus for training a facial recognition system, comprising:

one or more processors;
a memory coupled to the one or more processors and comprising instructions executable by the one or more processors to cause the apparatus to:
provide an input image of a particular face into a first facial recognition system;
obtain, from the first facial recognition system, an input faceprint;
obtain, based on the input faceprint and a noise value, a first set of output images and a second set of output images from a pre-trained generative adversarial network (GAN) generator, wherein the pre-trained GAN generator generates the first set of output images recognizable as images of the particular face and the second set of output images recognizable as negative images of the particular face, and wherein negative images of the particular face comprise images not recognizable as images of the particular face;
and
train, based on the first set of output images and the second set of output images, a second facial recognition system to recognize the particular face.

4 more elements

A non-transitory computer readable medium comprising instructions for training a facial recognition system, wherein the instructions are executable by one or more processors to:

provide an input image of a particular face into a first facial recognition system;
obtain, from the first facial recognition system, an input faceprint;
obtain, based on the input faceprint and a noise value, a first set of output images and a second set of output images from a pre-trained generative adversarial network (GAN) generator,
wherein the pre-trained GAN generator generates the first set of output images recognizable as images of the particular face and the second set of output images recognizable as negative images of the particular face, and
wherein negative images of the particular face comprise images not recognizable as images of the particular face;
and
train, based on the first set of output images and the second set of output images, a second facial recognition system to recognize the particular face.

4 more elements

Dependencies are inferred from the claim text.

Face synthesis using generative adversarial networks

Life of this patent

Face synthesis using generative adversarial networks

Life of this patent

Abstract

Claims20