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

Deep stacking network-based structure information guided Chinese character library generation method

A font library and network technology, applied in neural learning methods, biological neural network models, editing/combining graphics or text, etc., can solve problems such as wrong Chinese character structure, unreasonable strokes, uncontrollability, etc.

Active Publication Date: 2019-04-16
PEKING UNIV
View PDF7 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the entire generation process is uncontrollable and unpredictable, and blurring and false edges are unavoidable in the generated Chinese character images
In addition, for Chinese characters with complex structures or sloppy writing styles, end-to-end methods often get unreasonable strokes or even wrong Chinese character structures

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
  • Deep stacking network-based structure information guided Chinese character library generation method
  • Deep stacking network-based structure information guided Chinese character library generation method
  • Deep stacking network-based structure information guided Chinese character library generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0063] The present invention provides a method for automatically generating a handwritten Chinese character library guided by structural information based on a deep stack network. The user only needs to write a small number of Chinese characters, and uses a multi-level deep neural network to model the writing style, and generates two parts through skeleton synthesis and style rendering. Chinese character images to obtain a complete font file with the user's writing style.

[0064] The flowchart of the inventive method and the network structure diagram are as attached figure 1 , figure 2 and image 3 As shown, the specific implementation includes the following steps:

[0065] 1) The user writes 775 Chinese characters of the specified input set on the template form or white paper, scans it into a pic...

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 automatic generation method of a handwritten Chinese character library, which comprises the following steps of: predicting a Chinese character skeleton flow field by adopting a two-stage convolutional neural network G through a writing track synthesis stage and a font style rendering stage on the basis of a deep stacking network and structure information guidance; firstly, the writing style is learned from a small amount of handwritten Chinese characters written by a user, so that the writing track of unwritten Chinese characters is synthesized; The handwriting styleof the target is rendered; and generating a complete GB2312 Chinese handwriting word stock file with the writing style of the user. The method can ensure the structural accuracy and style consistencyof the generated fonts at the same time, is simple, efficient, low in cost and high in quality, and can meet the actual application requirements of ordinary people for quickly making personalized handwriting fonts.

Description

technical field [0001] The invention belongs to the technical fields of computer graphics and image processing, artificial intelligence and deep learning, and relates to Chinese word processing technology, in particular to a method for automatically generating a handwritten Chinese character library guided by structural information based on a deep stacking network. Based on empirical knowledge and deep neural network, it learns writing style and generates a complete Chinese character library. Background technique [0002] Personalized fonts make information dissemination more vivid and intuitive. Compared with standardized printing fonts, more and more people hope to use personalized fonts, especially handwriting fonts, in electronic mobile devices to communicate and communicate. On the one hand, personalized fonts can render text into a unique writing style, expressing the writer's style and feelings more flexibly; on the other hand, the visual effects of personalized font...

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): G06K9/68G06F17/21G06N3/04G06N3/08G06T11/60
CPCG06N3/08G06T11/60G06F40/109G06V30/245G06N3/045Y02D10/00
Inventor 连宙辉江月唐英敏肖建国
Owner PEKING 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