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

Style character generation method based on small number of samples and containing various normalization processing

A character generation and normalization technology, applied in neural learning methods, electrical digital data processing, natural language data processing, etc., can solve problems such as slow training speed

Pending Publication Date: 2020-10-09
XIAN JIAOTONG LIVERPOOL UNIV
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the training speed of this method is slow and requires continuous training for several months to obtain an effective model

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
  • Style character generation method based on small number of samples and containing various normalization processing
  • Style character generation method based on small number of samples and containing various normalization processing
  • Style character generation method based on small number of samples and containing various normalization processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] Embodiment: A style character generation method based on a small number of samples and including multiple normalization processes, a style reference character data set is composed of several style characters, and a variety of standard font characters with the same content are used as character content prototype data sources , using an image translation model based on a deep generative adversarial network that includes a mixer and multiple normalization methods, and using the adversarial loss function proposed in this patent during training, an image translation model that includes multiple normalization methods for character style transfer can be trained. Unified character generation model; a fully trained model can use a small number or even one character with the same style as a style reference template to generate any character with the same writing or printing style, and the content of the generated character is determined by the input Content archetype with standard...

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 style character generation method based on a small number of samples and containing various normalization processing. A style reference character data set is formed by usinga plurality of style characters; a plurality of standard font characters with the same content are used as a character content prototype data source; an image translation model which is based on a deep generative adversarial network and comprises a mixer and multiple normalization modes is used, an adversarial loss function provided by the patent is used in training, and finally, a character generation model which is used for character style migration and contains multiple normalization processing can be trained. According to the fully trained model, any character with the same writing or printing style can be generated by taking a small number of or even one character with the same style as a style reference template, and the content of the generated character is determined by an input content prototype with a standard style.

Description

technical field [0001] The invention relates to a method for generating style characters, in particular to a method for generating handwritten or printed characters based on a small number of sample styles. Background technique [0002] Fonts have a very important position and significance in the writing and culture of various countries, especially in China, where the art of calligraphy has a long history, but because of the large number of Chinese characters, it poses a huge challenge to the production of computer fonts. [0003] In 2016, Z.H.Lian published the paper "Automatic generation of large-scale handwriting fonts via style learning" on SIGGRAPHASIA, and proposed a method that allows users to provide 266 characters to generate 27,533 characters with similar styles. However, the training of this model needs to provide a large amount of labeled data, and the user needs more standardized input to get the expected results, and the effect is not good in the case of less l...

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): G06F40/109G06F40/106G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 黄开竹江浩川杨关禹程飞
Owner XIAN JIAOTONG LIVERPOOL 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