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

A multi-level image style conversion method and device based on sparse representation

A sparse representation, multi-level technology, applied in the direction of graphic image conversion, image analysis, image enhancement, etc., can solve the problem of not being widely used, few training dictionary images, etc., and achieve good visual effects.

Inactive Publication Date: 2019-05-07
PEKING UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is based on the assumption that there is an external training set, but in real life, after encountering a specific picture, people usually hope to transfer the target style to their own pictures through this only style picture, As a result, there are too few image pairs for training the dictionary, so this method has not been widely used

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 multi-level image style conversion method and device based on sparse representation
  • A multi-level image style conversion method and device based on sparse representation
  • A multi-level image style conversion method and device based on sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The specific embodiments of the invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0040] figure 1 It shows a schematic flowchart of a multi-level image style conversion method based on sparse representation provided by an embodiment of the present invention, as shown in figure 1 As shown, the method includes the following steps:

[0041] 101. Convert the color image to be converted into a first grayscale image, reconstruct the structure layer and texture layer of the first grayscale image by extracting the edge features of the first grayscale image and the target style image, and include The image of the structural layer is used as a second grayscale image, and the image including the texture layer is used as a third grayscale image;

[0042] 102. Accor...

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 multi-level image style conversion method and device based on sparse representation. The method includes: converting a color image to be converted into a first grayscale image, and extracting the relationship between the first grayscale image and the target style image. The edge features reconstruct the structure layer of the first grayscale image as the second grayscale image and the texture layer as the third grayscale image, obtain the salient areas and non-salient areas in the color image, and use different weights in the salient areas and non-salient areas. The second grayscale image and the third grayscale image are value-fused to obtain a fourth grayscale image, and the saturation contrast of the fourth grayscale image is adjusted according to the target style image to obtain a color image with the same style as the target style image. This method not only retains the structural characteristics of the image to be converted, but also adds the texture characteristics of the target style image, realizing the style conversion of the image to be converted through a target style image, demonstrating good visual effects.

Description

technical field [0001] The invention relates to the technical field of image synthesis and reconstruction, in particular to a sparse representation-based multi-level image style conversion method and device. Background technique [0002] Image stylization aims to transform an image of one style into an image of another specified style. The input image to be converted and the output converted image have the same content but have a completely different visual experience. [0003] Image stylization has been a hot area of ​​research over the past few decades. Hertzmann proposed to synthesize a stylized image by superimposing virtual strokes. This method is suitable for converting the image to be converted into a fixed target style image, such as oil painting style and crayon style, but it is not suitable for custom style conversion of the input image. . [0004] In order to transplant the user-defined image style to the image to be converted, a method of mapping in the feature...

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): G06T3/00G06T7/41
CPCG06T2207/10024G06T3/10
Inventor 宋思捷杨撒博雅刘家瑛郭宗明
Owner PEKING 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