Face synthesis using generative adversarial networks

Abstract

The present invention provides face synthesis using generative adversarial networks. The training a generative adversarial network (GAN) for use in facial recognition comprises 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.

Description

technical field [0001] The present disclosure relates generally to the field of digital image processing, and more specifically, to image synthesis using generative adversarial networks. Background technique [0002] Facial recognition systems require sample facial images from users to be recognized. Some facial recognition systems use a large number of cameras with known attributes placed at known locations under carefully controlled settings to generate the large number of sample facial images required for the system's enrollment process and training. In addition to being expensive and elaborate, such systems are bulky and not readily available to the average user. While facial recognition accuracy benefits from a greater number and diversity of sample facial images during enrollment, providing such images would greatly increase the burden on users. Contents of the invention [0003] In one embodiment, a method of training a generative adversarial network (GAN) for fac...

AI Technical Summary

Problems solved by technology

In addition to being expensive and elaborate, such systems are bulky and not readily available to the average user

While facial recognition accuracy benefits from a greater number and diversity of sample facial images during enrollment, providing such images would significantly increase the burden on users

Images