Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

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

A technology of semantic segmentation and deep convolution, applied in the field of deep learning, can solve problems such as unsatisfactory migration effect, unsatisfactory effect, large randomness of images, etc.

Active Publication Date: 2020-03-13
HENGYANG NORMAL UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Portrait Style Transfer Method Based on Semantic Segmentation and Deep Convolutional Neural Network
  • A Portrait Style Transfer Method Based on Semantic Segmentation and Deep Convolutional Neural Network
  • A Portrait Style Transfer Method Based on Semantic Segmentation and Deep Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] see figure 1 and figure 2 , are respectively the system flowchart and the model architecture diagram of the present invention, see Figure 4 , this embodiment selects an artistic image as the style portrait Choose another image as content portrait like image 3 shown. where w c , h c are the length and width of the content portrait image respectively, w s , h s are the length and width of the content portrait image respectively; then use the semantic-based image segmentation algorithm to semantically segment the style portrait and content portrait:

[0057] Step 1. Select the CRF as RNN model developed by Oxford University as the model for the semantic segmentation of the image portrait area, perform semantic segmentation on the content image and style image respectively, and segment the portrait area and background area,

[0058] Step 2. Use the OpenFace face area segmentation algorithm, and then calibrate the face, nose, eyes, mouth, and body areas in the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/00G06T7/11G06T7/194
CPCG06T7/11G06T7/194G06T2207/30201G06T2207/30196G06T2207/10004G06T2207/20084G06T2207/20076G06T3/04
Inventor 赵辉煌郑金华孙雅琪
Owner HENGYANG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products