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

Multi-style traditional Chinese painting peanut forming method based on neural network

A neural network, multi-style technology, applied in the field of image processing, can solve the problem of high-quality pictures that cannot be clearly displayed, and achieve the effect of reducing training complexity, saving time, and rich colors.

Active Publication Date: 2020-05-15
SICHUAN UNIV
View PDF14 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, a kind of generation method based on neural network style Chinese painting flowers provided by the invention solves that in the classification research of traditional methods, due to the abstraction and complexity of Chinese painting styles, it is impossible to generate clear pictures. The problem with high-quality images

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
  • Multi-style traditional Chinese painting peanut forming method based on neural network
  • Multi-style traditional Chinese painting peanut forming method based on neural network
  • Multi-style traditional Chinese painting peanut forming method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0070] The present invention provides a kind of multi-style traditional Chinese painting flower generation method based on neural network, such as figure 1 As shown, the implementation method is as follows:

[0071] S1. Construct the data set picture of Chinese painting flowers, and preprocess the data set picture to obtain the source picture a. The implementation method is as follows:

[0072] S101. Obtain the picture of Chinese painting flower, construct three non-paired forms of Chinese painting flower data set pictures of line drawing, fine brushwork and ink painting, and compress it into a fixed size, and save the picture in the format of Image.ANTIALIAS;

[0073] S102. Cutting the image in Image.ANTIALIAS format 6 times, and selecting the image with the largest density of flowers;

[0074] S103. Adjust the size of all pictures to 384×384 by means of Image.BILINEAR to obtain the source picture a;

[0075] S2. Input the source picture a into the neural network-based Chi...

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 provides a multi-style traditional Chinese painting peanut forming method based on a neural network, and the method comprises the steps: mapping from white painting to crafts or Chineseink painting through employing an attention architecture, carrying out training through employing a non-paired data set to acquire crafts and Chinese ink paintings with certain style characteristics.According to the invention, a new loss MSSSIM loss function is introduced into a GAN-based attention architecture; the distance between the reconstructed image and the source image is compared in a multi-scale manner from three aspects of brightness, contrast and structure, and the image style and content are guided to be accurately generated together with a cyclic consistency loss L1 function, sothat the problems of unclear original network picture, artifacts, fuzzy ink marks, noisy points and the like are solved. According to the method, the problem that high-quality pictures with clear pictures cannot be generated due to abstraction and complexity of traditional Chinese painting styles in research of a traditional method is solved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a neural network-based method for generating style Chinese painting flowers. Background technique [0002] With the development of the times, traditional Chinese painting has continued to innovate on the basis of inheritance, among which meticulous painting and ink painting have become the mainstream of today's painting. It is not only used for collection, as home decoration, gift, but also used in animation, games, clothing design and other fields. The content of traditional Chinese painting is mainly natural scenery, especially Chinese flower painting, which is an important and classic form of expression in Chinese painting. Figure 16 Three common styles of traditional Chinese flower painting are shown, namely, white drawing, meticulous painting and ink painting, ranging from Figure 16 In the picture, we can see that real line drawing pictures need clear ...

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
IPC IPC(8): G06T3/00
CPCG06T2207/20132G06T2207/20081G06T2207/20084G06T3/04Y02P90/30
Inventor 吕建成付菲菲李茂孙亚楠
Owner SICHUAN 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com