Supercharge Your Innovation With Domain-Expert AI Agents!

Method for generating family fonts based on AttGan model

A model generation and font technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as unpredictability, uncontrollable GANs model generation process, and poor detail recognition

Pending Publication Date: 2020-09-15
DALIAN NATIONALITIES UNIVERSITY
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the entire generation process of the GANs model is uncontrollable and unpredictable, the recognition of details is not handled well, and the generated fonts usually contain blurred and ghosting artifacts

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
  • Method for generating family fonts based on AttGan model
  • Method for generating family fonts based on AttGan model
  • Method for generating family fonts based on AttGan model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solutions in the implementation of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. It can be understood that the described examples are only some examples of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

[0042] figure 1 A flowchart showing a method for generating family fonts based on the AttGan model, figure 2 A network structure diagram of a method for generating family fonts based on the AttGan model is shown. The specific implementation steps of this method for generating family fonts are as follows:

[0043] Firstly, convert the bold and thin data sets of the target font provided by the designer into image format, adjust the size, and uniforml...

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 method for generating family fonts based on an AttGan model, and belongs to the technical field of computer graphic processing. The method for generating family fonts based on the AttGan model comprises steps that based on an encoder-decoder based structure, attribute classification constraints, reconstruction and adversarial learning are reasonably used; finally, a plurality of interested attributes can be better modified by utilizing one model and other regions are kept unchanged. An attribute classification constraint layer is added through the AttGan network model, parameter attribute values such as different word weights and word heights in family fonts are modified, smooth interpolation between different fonts is realized, and a transition font image for controlling font styles is generated. And a font generation style is determined through the parameter attribute value, thereby constructing a complete font family. According to the family font generationmethod, the burden of a designer can be greatly reduced, the design cycle time is shortened, the designer is helped to solve the problem of a large amount of repeated work, and the working efficiencyis improved.

Description

technical field [0001] The invention relates to a method for generating family fonts by interpolation, in particular to a method for generating family fonts based on an AttGan model, and belongs to the technical field of computer graphics processing. Background technique [0002] At present, there are many domestic researches on Chinese Character Recognition, and with the application of deep learning, it has achieved very high results. However, in the aspect of Chinese character generation, there is much less research at home and abroad, and the research in this area is quite challenging, because Chinese Chinese character font styles are varied, the font structure is complex, and the number of Chinese characters is huge. As a result, much of the research literature on algorithms for font generation focuses on English and Latin characters. Because the number of English and Latin characters is many times smaller than that of Chinese characters, and their font style changes ar...

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): G06K9/62G06K9/32G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06N3/045G06F18/24G06F18/214
Inventor 王存睿张煜
Owner DALIAN NATIONALITIES UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com