A Portrait Style Transfer Method Based on Semantic Segmentation and Deep Convolutional Neural Network

Abstract

The invention discloses a portrait style transfer method based on semantic segmentation and deep convolutional neural network. First, the portrait to be converted and the target style portrait are selected, and then semantic segmentation is performed on the two images to segment the portrait area and background. area, and then segment the specific facial features from the portrait area, and then define the portrait style transfer loss function. The deep convolutional neural network VGG‑19 is used as the basic model for image advanced style feature extraction. After setting the content constraint layer and style constraint layer, Define the content constraint layer and style constraint layer in the VGG‑19 model to establish a new model structure. Input the segmented semantic image and the original image into the new VGG‑19 model respectively, extract the high-level style features and content features of the image, use the portrait style transfer loss function, adopt the gradient descent method, and minimize the loss function through multiple iterations , and finally generate the style transfer result image.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to a portrait style transfer method based on semantic segmentation and deep convolutional neural network. Background technique [0002] With the rapid development of technology, in the field of deep learning research, the process of using CNN to fuse the semantic content of a picture with different styles is called neural style transfer (Neural Style Transfer). Gatys et al. The report article "image Style Transfer Using Convolutional NeuralNetworks" confirmed the amazing ability of convolutional neural network (CNN) in image style transfer: by separating and recombining image content and style, CNN can create works with artistic charm . Since then, there has been great interest in neural style transfer in academic research and industrial applications. Transferring artistic styles from artworks to everyday photos has become a very important computer vision task in both academia and indu...

AI Technical Summary

Problems solved by technology

[0003] The problems existing in the existing style transfer methods mainly include: the style transfer of images is very random, which leads to unsatisfactory results in many cases.

Especially for the style transfer of portraits, some mistakes sometimes occur, such as transferring the features of the eyes in the style image to the mouth, or transferring the features of the image background to the portrait, and the transfer effect is very unsatisfactory.

Images