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

Chinese character font style migration method based on deep learning

A font style and deep learning technology, applied in the field of image processing, can solve the problems of insufficient extraction of font details, deformation of font structure, loss of details, etc., to achieve the effect of excellent detail fidelity and structural integrity, and enhanced stability.

Pending Publication Date: 2020-12-11
XIAN UNIV OF TECH
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a Chinese character font style migration method based on deep learning, which overcomes the problems that existing research methods cannot fully extract font detail features, and the generated fonts have structural deformation, detail loss, and blurred outlines

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
  • Chinese character font style migration method based on deep learning
  • Chinese character font style migration method based on deep learning
  • Chinese character font style migration method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0036] The present invention provides a Chinese character font style transfer method based on deep learning, such as Figure 1-2 As shown, it specifically includes the following steps:

[0037]Step 1, obtain the Chinese character image of the specified input character set;

[0038] Step 1 is specifically implemented according to the following steps:

[0039] Download the standard TrueType font library from the font library. The text font library is a txt file composed of 775 Chinese characters, basically covering all the strokes and structures of Chinese characters in GB2312; among them, the content of the TrueType font library includes source font image x and real images of five target fonts y (Jingyu, Heiti, Benmo, Mala, Zeibai) each has 775 Chinese characters.

[0040] Step 2. By using the Python Image Library (PIL) tool, use the Image ...

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 Chinese character font style migration method based on deep learning. The Chinese character font style migration method specifically comprises the following steps: 1, acquiring a Chinese character image of a specified input character set; 2, initializing the color, the background and the size of the font image; 3, performing learning training by taking the source font image x and the real images y of the five target fonts as priori knowledge through a generator G; 4, taking the source font image x as condition input by the generator G, using a down-sampling area to extract a shallow font feature F0, restoring the feature vector into an image through an up-sampling area, and generating a generated image G (x) of the target font; 5, discriminating and classifying the generated image G (x) of the target font by using a discriminator D; and 6, calculating the value of the loss function. The method overcomes the problems that an existing research method cannot fully extract detail features of fonts, and the generated fonts have structural deformation, detail loss and fuzzy contours.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a Chinese character font style migration method based on deep learning. Background technique [0002] After a long evolution and development in the long river of history, Chinese characters have formed a variety of types and styles of glyphs, which not only play an important social role in the cultural inheritance and ideological exchange of Chinese civilization, but also form a unique artistic form symbol. With the rapid development of the mobile Internet, people's demand for personalized and exclusive fonts is increasing day by day. Due to the popularity of various online social media and computer office software, people will use a variety of fonts to process text. Standard fonts such as Song, Kai and Hei are widely used by everyone, but they lack beauty and personality. Therefore, professional designers are required to design font libraries of different s...

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): G06T3/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F18/24G06F18/214G06T3/04
Inventor 缪亚林姬怡纯贾欢欢张顺程文芳
Owner XIAN UNIV OF TECH
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