Mobile terminal face age editing method based on StyleGAN

Abstract

The invention discloses a mobile terminal face age editing method based on a StyleGAN. The method comprises the steps of S1 preparing a face picture training data set, and labeling part of face pictures in the face picture training data set to obtain age labels; S2 training a feature extraction model and a generation model by using the face picture training data set; S3 training a face age classifier by utilizing partial data in the face picture training data set and the feature extraction model; S4 selecting a resolution ratio and a channel coefficient according to user configuration and expected waiting time, and inputting the resolution ratio and the channel coefficient into the generation model to obtain a sub-model; S5 extracting a coefficient of the face age classifier, namely an attribute vector capable of judging the face age; and S6 editing the to-be-edited face picture by using the sub-model and the attribute vector. According to the technical scheme, deployment and maintenance cost can be reduced, user data security is enhanced, personal privacy leakage is avoided, dependence of software on a network is removed, and a user can use the software anytime and anywhere.

Description

technical field [0001] The invention belongs to the technical field of image processing, and more specifically, relates to a method for editing face age at a mobile terminal based on StyleGAN. Background technique [0002] Generative Adversarial Networks (GANs) are one of the most promising approaches for unsupervised learning on complex distributions in recent years. The model produces quite good output through the mutual game learning of two modules in the framework: the generative model and the discriminative model. GAN can generate data that does not exist in the real world, and plays an important role in image generation, image denoising, and data enhancement. [0003] StyleGAN designs a new generator network structure inspired by style transfer. The new network structure can decouple and separate the high-level semantic attributes of the image through unsupervised automatic learning, such as the pose and identity of the face image, and the random changes of the gener...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for editing face age at the mobile terminal based on StyleGAN, the purpose of which is to directly deploy on the mobile phone to edit the age of the face, thereby solving the problem of high system deployment cost , need to upload image data, technical problems with long processing time

Images