Font style migration and transformation method based on Manchu character pictures

A technology of font style and font, applied in the field of image processing, can solve the problems of limited number of people, high time cost, etc.

Active Publication Date: 2021-05-04
DALIAN NATIONALITIES UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Most of the existing styles of Manchu fonts are transformed by inputting Manchu characters into text editing software according to Roman transliteration, and then using various existing Manchu fonts to transform them. It takes a lot of time to read and write, and the operator needs to have a certain ability to identify Manchu, and Manchu, as an endangered language, has a very limited number of people who can read, write, and identify Manchu.

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
  • Font style migration and transformation method based on Manchu character pictures
  • Font style migration and transformation method based on Manchu character pictures
  • Font style migration and transformation method based on Manchu character pictures

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] Below in conjunction with embodiment and accompanying drawing, the present invention is described in detail

[0045] The present invention provides a method for image-based Manchu character style migration, and the specific process for realizing the method is divided into the following steps:

[0046] Step 1. Construct the Manchu font style transformation data set. (Manchu text training data set, Manchu font style transfer data set)

[0047] Step 2. Construct the conditional generative adversarial network model required to realize the transfer of Manchu font style.

[0048] Step 3. Perform step-by-step training on the Manchu font style transfer model constructed in step 2. First, use the Manchu text training data set to train the model to complete the Manchu character learning, and then use the Manchu font style transfer training data set to train the model. Train again to complete the transfer learning of Manchu font style.

[0049] Step 4. Call the model generated ...

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 font style transfer transformation method based on Manchu character images belongs to the field of image processing, and solves the problem of greatly reducing the time and labor costs spent on processing a large number of Manchu character images. The key point is to train the Manchu font style transfer model step by step: Using the Manchu character training data set to train the model to learn Manchu characters; using the Manchu font style transfer data set to retrain the model to realize Manchu font style transfer learning, the effect is to save a lot of time and labor costs.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for processing Manchu font styles. Background technique [0002] Most of the existing styles of Manchu fonts are transformed by inputting Manchu characters into text editing software according to Roman transliteration, and then using various existing Manchu fonts to transform them. It takes a high time cost to read and write, and the operator needs to have a certain ability to identify Manchu, and Manchu, as an endangered language, has a very limited number of people who can read, write, and identify Manchu. Therefore, training a highly versatile generative adversarial network model to transfer the font style of Manchu characters from the image level can save a lot of time and labor costs. Contents of the invention [0003] The present invention mainly implements a generative confrontation network model capable of learning the transfer process between Manchu font style...

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): G06K9/68
CPCG06V30/245G06V30/287
Inventor 郑蕊蕊李敏毕佳晶贺建军许爽吴宝春
Owner DALIAN NATIONALITIES UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap