Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for generating Chinese character fonts based on dcgan deep network

A technology of deep network and font library, which is applied in the fields of electronic digital data processing, character and pattern recognition, instruments, etc., can solve the problems of wasting labor costs, time-consuming and labor-intensive, etc.

Active Publication Date: 2021-06-01
GUANGDONG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides a method and device for generating a Chinese character library based on the DCGAN deep network, which solves the problem that due to the similarity of the Chinese character structure itself, more than 6,000 commonly used Chinese characters and tens of thousands of uncommon characters must be included in the design of new fonts. A lot of repetitive work, resulting in time-consuming and labor-intensive technical problems that waste labor costs

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
  • A method and device for generating Chinese character fonts based on dcgan deep network
  • A method and device for generating Chinese character fonts based on dcgan deep network
  • A method and device for generating Chinese character fonts based on dcgan deep network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The embodiment of the present invention provides a method and device for generating a Chinese character library based on a DCGAN deep network, which solves the problem of designing more than 6,000 commonly used Chinese characters and tens of thousands of uncommon characters due to the similarity of the Chinese character structure itself. It inevitably involves a lot of repetitive labor, resulting in time-consuming, labor-intensive, and technical problems that waste labor costs.

[0071] In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other ...

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 embodiment of the present invention discloses a method and device for generating a Chinese character library based on a DCGAN deep network, which is used to solve the problem of designing more than 6,000 new fonts for common Chinese characters and tens of thousands of very common characters due to the similarity of the Chinese character structure itself. Words inevitably contain a lot of repetitive labor, resulting in time-consuming, labor-intensive, and technical problems that waste human costs.

Description

technical field [0001] The invention relates to the technical field of computer word processing, in particular to a method and device for generating a Chinese character library based on a DCGAN deep network. Background technique [0002] There have been deep neural network (DCNN) based methods that, given a small set of letters in a certain font, generate the rest of the letters in the same style. [0003] For example, in paper 1 (Baluja S. Learning Typographic Style [J]. arXiv: ComputerVision and Pattern Recognition, 2016.), a method for generating English fonts based on a deep neural network (DCNN) is discussed. By inputting the four letters "B, A, S, Q" of a certain font into the DCNN network, pictures of other uppercase English letters in this font can be generated. This method is mainly based on the pixel-by-pixel L2 loss. By learning the font information of the four letters "B, A, S, and Q" in various fonts such as lines, radians, and inclinations, a font information ...

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 Patents(China)
IPC IPC(8): G06F40/109G06F40/126G06K9/68
CPCG06F40/126G06F40/109G06V30/245
Inventor 叶武剑徐佐腾刘怡俊翁韶伟张子文
Owner GUANGDONG UNIV OF TECH