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

Chinese character font generation method based on conditional generation antagonistic network

A conditional generation and Chinese character technology, applied in the field of conditional generation adversarial networks, can solve the problems of insufficient regularity of the skeleton, inability to cover well, complex situation at the bifurcation, etc., achieving less labor and time consumption, various generation results, and simple training process. Effect

Inactive Publication Date: 2018-12-21
XIAMEN UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the skeleton is often not regular enough, the situation at the fork is often more complicated, this method does not cover all situations very well

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 generation method based on conditional generation antagonistic network
  • Chinese character font generation method based on conditional generation antagonistic network
  • Chinese character font generation method based on conditional generation antagonistic network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0042] The overall process framework of the font generation system of the present invention is mainly divided into two parts: network training and font generation.

[0043] The network training part first extracts the strokes of the two fonts, clusters the strokes, and uses the stroke category information and font category information represented by one-hot encoding as conditions, and the stroke bitmap as a training sample, which is sent to the least squares confrontation network for training .

[0044] Given two point sets X and Y, and the set Y can be regarded as the center of a Gaussian mixture model, the EM algorithm is used to calculate the maximum likelihood estimate of the fitted point set X. The coherent point drift algorithm is widely used in image registration, and the key problem of stroke extraction in the present invention is the matchin...

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 relates to a Chinese character font generation method based on a conditional generation antagonistic network, which relates to Chinese character font generation. Stroke information of Chinese character bitmap is extracted by using central skeleton extraction and coherent point drift method. The new style strokes are generated by the conditional antagonism generation network. A methodfor extract strokes by use Lian Zhouhui is broadened, and that stroke extraction is expanded from handwritten font without thick and thin information to Chinese character bitmap with thick and thin information; In font generation, the proposed method has the advantages of diverse generation results, simple training process, no special prior knowledge, and less manpower and time consumption.

Description

technical field [0001] The invention relates to the generation of Chinese character fonts, in particular to a method for generating Chinese character fonts based on conditional generation confrontation networks. Background technique [0002] For Chinese, due to the large number of Chinese characters and complex strokes, a complete set of fonts usually needs to contain more than 20,000 Chinese characters encoded in GBK, which requires at least 5 to 6 man-years, so designing a new set of fonts is a task. This is a arduous project, which also leads to a small number of fonts for Chinese characters. [0003] Font generation is currently mainly using some traditional methods. These methods require experts to build models in advance, divide Chinese characters into multiple levels such as radicals and strokes, and generate new fonts by recombining internal parts of the level, or using complex control parameters to control shape features. Font generation has always been a relative...

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): G06T11/00G06T7/13G06F17/21
CPCG06F40/109G06T7/13G06T11/001
Inventor 纪荣嵘林贤明李杰
Owner XIAMEN 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