Image style migration method, system and device and storage medium

Abstract

The invention discloses an image style migration method, system and device and a storage medium. The method comprises the following steps: obtaining a content picture; inputting the content picture into a pre-trained image style migration model for style migration processing, and outputting a target picture which has a specific style and retains the original content; enabling the image conversionnetwork and the discrimination network to form a generative adversarial network (GAN), and carrying out alternate updating in the model training process. According to the method, the network is continuously updated and optimized by sensing the adversarial loss function until the loss is minimized, and the image style migration model with a better effect is obtained, so that the output picture closer to the content picture and the style picture can be obtained, the problem of picture background distortion is effectively avoided, and the method, system and device can be widely applied to the field of data image processing.

Description

technical field [0001] The present invention relates to the field of data and image processing, in particular to an image style transfer method, system, device and storage medium based on deep learning. Background technique [0002] In recent years, deep learning, as the hottest direction in the field of artificial intelligence, has shown powerful learning and processing capabilities, and even surpasses human performance in some fields. Image style transfer is a typical application of deep learning, and it is also a popular research direction at home and abroad. Image style migration is to replace an image with another style while keeping the content unchanged, so that ordinary people or scenery pictures can be converted into various artistic style effects. This technology can be widely used in image processing, computer picture synthesis and computer vision etc. [0003] The initial image style transfer is an optimization-based method proposed by Gatys et al., which uses ...

AI Technical Summary

Problems solved by technology

[0004] Johnson's stylized network, as a landmark achievement in the field of deep learning, has been proven to measure the difference between images from the high-dimensional visual perception level through the fixed loss network pre-trained by the ImageNet dataset, but its fixed The loss network (VGG16) has certain limitations

The VGG16 network was originally trained for classification, so it can clearly identify the main body of the picture (human and animal), but its ability to identify the background is weak, so the background is usually distorted

Images