Image style migration method

A style and image technology, applied in the field of image processing, can solve problems such as difficulty in switching image styles and low quality of synthesized images

Pending Publication Date: 2020-03-24
湖北讯獒信息工程有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the prior art, it is difficult to switch the image style while extracting the image content, resulting in the low quality of the synthesized image

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 migration method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, an image style transfer method, including:

[0041] S1, based on the artificial neural network library TensorFlow, realizes the convolutional neural network CNN;

[0042] S2, capture the intrinsic information of the picture, and build a feature space based on the original CNN representation, and the feature space is used to capture the style of the input image;

[0043] S3, in the CNN network, the convolutional layer extracts features from the image, the features of the lower layer of the convolutional layer are used to describe the specific visual features of the image, and the features of the higher layer of the convolutional layer are used to describe the abstract image content;

[0044] S4, combined with the extracted content information of another content picture, the synthetic picture learning is carried out under the same network, and after the predetermined loss is reached, the target picture after style transfer can be obtained.

[...

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 migration method, which comprises the steps of S1, realizing a convolutional neural network (CNN) based on an artificial neural network library TensorFlow; S2, capturing intrinsic information of the picture, and establishing a feature space on the basis of original CNN representation, the feature space being used for capturing a style of an input image; S3, in the CNN network, the convolution layer extracting features from the image, the features of the lower layer of the convolution layer being used for describing specific visual features of the image, and the features of the higher layer of the convolution layer being used for describing abstract image content and the like. According to the method, perfect conversion of styles can be realized on thebasis of accurately extracting the content pictures, the synthesized pictures in any style can be generated, and the method can be applied to the fields of mobile phone APP image style migration, computer vision picture creation, fashion design, movie lens design, animation style rendering, game vision effect synthesis and the like.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to an image style transfer method. Background technique [0002] In recent years, the wave of artificial intelligence technology led by deep learning has begun to be more and more widely applied to various fields of society, especially in the field of computer vision. Image style transfer, as a new technology, has rapidly become the field of artificial intelligence research. one of the hot topics. Image style transfer can be used to synthesize new images based on different styles and texture features, and has a broad market in the field of art design. However, in the prior art, it is difficult to switch image styles while extracting image content, resulting in low-quality synthetic images. Contents of the invention [0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide an image style migration method, ...

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): G06T3/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06T3/04
Inventor 王孝元
Owner 湖北讯獒信息工程有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap