METHOD EMPLOYING GENERATIVE ADVERSARIAL NETWORK FOR PREDICTING FACE CHANGE

摘要

A method employing generative adversarial network for predicting a face change, comprising: S1 of acquiring face data samples; S2 of constructing a generative adversarial network model consisting of a generator and a discriminator, designing a loss function, and performing iterative training on the generator and the discriminator; and S3 of inputting a target young face image to be processed into the trained generative adversarial network model, and outputting a target aged face image corresponding to the target young face image. The method is adopted to construct a unique generative adversarial network model and loss function, provides robustness for aging, and accounts for change information including the forehead, hair, and the like, thereby improving the accuracy and uniqueness of prediction.