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

Multi-style font generation method

A font and style technology, applied in the field of computer graphics processing, can solve the problem of low font recognition accuracy, achieve the effect of improving the image quality of Chinese characters and reducing dependence

Pending Publication Date: 2021-12-24
CHINA JILIANG UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And some data sets of handwritten fonts and artistic fonts are also difficult to collect in large quantities, resulting in low accuracy of font recognition

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 font generation method
  • Multi-style font generation method
  • Multi-style font generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The specific implementation of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0053] Such as figure 1 As shown, the method of generating fonts of various styles based on StarGAN improvement includes the following steps:

[0054] First, select the most commonly used print as the source font, and use PIL (Python Image Library) to generate font images through the Chinese character font file data ttf that comes with the PC; select handwritten Chinese character images in the Chinese handwriting database and some common Internet art The fonts constitute the target font dataset, taking the most commonly used 670 Chinese characters. The font image size in the dataset is adjusted to 255*255. Encode the target font style label with one-hot encoding rules, and then send the source font image and target font style label to the generator G at the same time to generate a font image corresponding to the target style. ...

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 font generation method based on StarGAN improvement, original generator network structures of a coding layer, a conversion layer and a decoding layer are replaced by combination of two special structures of Attention U-NET and DenseNet, and the problem that character stroke information is lost due to direct convolution operation is solved. Meanwhile, a U-shaped structure and jump connection in the Attention U-NET can effectively integrate details and semantic features of the image, the attention mechanism of the network can solve the problem that local information is lost or redundant in the font generation process of an existing model, and the pixel error rate of Chinese character generation is reduced. According to the method, a paired data set is not needed, and automatic generation of various font styles can be directly realized only by training one model. The method solves the problem of data set missing in Chinese character recognition, improves the font recognition accuracy, and creates conditions for insufficient quantity in the small sample field and the data migration field.

Description

technical field [0001] The invention belongs to the technical field of computer graphics processing, in particular to the technical field of image generation by generative confrontation networks, and in particular to an improved method for generating fonts of various styles based on StarGAN. Background technique [0002] The number of Chinese character fonts is huge, the structure is complex, and the style of each font is very different. Designing a font with a uniform style often requires a lot of manpower and material resources. Therefore, the generation of Chinese characters and the conversion of font styles have become a hot research issue in recent years. [0003] Chinese calligraphy has a long history, and the art of calligraphy has become a treasure of Chinese traditional culture. For many calligraphy lovers, it has become a pleasure to collect the authentic works of their favorite calligraphers or copy the fonts of their favorite calligraphers. When the authentic cal...

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): G06N3/04G06N3/08G06K9/68
CPCG06N3/08G06N3/045
Inventor 徐向纮李金金
Owner CHINA JILIANG 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