Front face synthesis method and system based on generative adversarial network

Abstract

The invention provides a front face synthesis method and system based on a generative adversarial network, and the method comprises the steps: detecting and segmenting a face part from an input image,and carrying out the face alignment, so as to obtain a to-be-synthesized face image; estimating the head posture according to the face key points, and dividing the face data set into a front face setand a non-front face set according to the degree of freedom of head rotation; utilizing a pre-training model of a face recognition deep neural network to extract identity features of an input face image to perform training of a supervision network; and synthesizing a corresponding front face image based on the generative adversarial network according to the input side face image. Through face symmetry constraint and identity feature constraint, the synthesized front face is more natural, and the identity features of the front face are better maintained.

Description

technical field [0001] The disclosure belongs to the fields of computer vision, pattern recognition and digital image processing, and specifically relates to a method and system for synthesizing a frontal face based on a generative confrontation network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0004] Traditional face recognition algorithms are mostly based on artificially designed features (such as LBP, HOG, SIFT, Gabor, etc.) and machine learning algorithms (such as PCA, linear discriminant algorithm, support vector machine algorithm, etc.). The number of face databases obtained at the same time is not only limited, but also the face types are too single, so the recognition accurac...

AI Technical Summary

Problems solved by technology

At present, the model of frontal face synthesis usually has a complex structure and many model parameters, resulting in very time-consuming training and verification, and the training requires paired inputs, resulting in more training data constraints.

At the same time, the synthesized face images are often not natural enough, and the effect of recognizing the network is not satisfactory

Images