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

Image style transfer synthesis method based on stroke synthesis

A synthesis method and stroke technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve problems such as complex operation, and achieve the effect of strong randomness

Inactive Publication Date: 2014-12-24
NANJING UNIV
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is too complicated for users to operate

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
  • Image style transfer synthesis method based on stroke synthesis
  • Image style transfer synthesis method based on stroke synthesis
  • Image style transfer synthesis method based on stroke synthesis

Examples

Experimental program
Comparison scheme
Effect test

preparation example Construction

[0052] The invention relates to an image style transfer synthesis method, which uses the input sample image as a palette, analyzes the style features on it, and then uses the obtained features to convert the stroke transfer synthesis problem into each quadrilateral in the sample image The matching search problem, establish an energy equation of the consistency measurement problem, and optimize the energy equation according to the similar block offset statistical method, solve the energy minimum value, in order to complete the style of the stroke curve obtained in the specified area of ​​the target map Migrate and synthesize, and then transfer the color information of the target image to the result image, and the final result is the result image with the same painting style as the sample image. The method of the invention can efficiently and automatically complete the transfer of the personalized art style of the target image.

[0053] Such as figure 1 Shown, in the present in...

Embodiment

[0061] Each step of the present invention is described below according to an embodiment.

[0062] Step (1), performing image segmentation on the target image input by the user.

[0063] right Figure 3b As shown in the input target image, this embodiment adopts the document 5 Lim, Joseph J., C.Lawrence Zitnick, and Piotr Dollár."Sketch tokens: A learned mid-level representation for contour and object detection."Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013. The proposed method performs image segmentation on the target image.

[0064] Step (2), according to the segmentation result of step (1), perform stroke setting for each region of the segmented target image.

[0065] In this embodiment, according to the segmentation result of the target image, corresponding strokes are laid out on the boundary of each region and in the region. In this embodiment, the stroke is defined as S, which is set as a curve with a certain radian determined alo...

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 an image style transfer synthesis method based on stroke synthesis. The method comprises the following steps that first, image segmentation is carried out on a target image input by a user, and a set of image regions are obtained; second, according to the image regions obtained in the first step, stroke setting is carried out on all the regions of the segmented target image; third, feature analysis is carried out on a sample image, and a result image is obtained on the basis of stroke transfer synthesis of trapezoids; fourth, the color information of the target image is transferred to the result image, and the result image with the color information of an original image maintained is obtained.

Description

technical field [0001] The invention relates to the technical fields of computer image processing and computer graphics, in particular to an image style transfer synthesis method based on stroke synthesis. Background technique [0002] The stylized rendering of images has become a research hotspot in non-photorealistic rendering. It can simulate the manual drawing process and Effect. In recent years, researchers at home and abroad have proposed many effective methods from different research perspectives. According to different starting points, the representative methods can be roughly divided into two categories: one is the simulation-based rendering technology ( Simulation-based), which is committed to simulating the real painting creation process, and obtains different styles of result pictures by superimposing strokes of various colors and sizes on the canvas, such as the document 1Hertzmann A. Fast Paint Texture. Proceedings of the 2nd international symposium on Non-ph...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46
Inventor 张岩缪峥郑智斌孙正兴
Owner NANJING 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