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

Defective ancient book Chinese character restoration method based on conditional adversarial network

A repair method, a technology of Chinese characters, applied in the field of image processing, can solve problems such as the difficulty of repairing damaged fonts, achieve the effect of getting rid of manual repair, repairing fonts, and reducing costs

Active Publication Date: 2019-10-15
陕西集大成得智慧教育科技有限公司
View PDF10 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for repairing damaged ancient Chinese characters based on conditional confrontation network, which solves the problem of difficult repair of damaged fonts in a large number of damaged ancient books existing in the prior art

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
  • Defective ancient book Chinese character restoration method based on conditional adversarial network
  • Defective ancient book Chinese character restoration method based on conditional adversarial network
  • Defective ancient book Chinese character restoration method based on conditional adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0047] The method for repairing Chinese characters in ancient books based on conditional confrontation network of the present invention is specifically implemented according to the following steps:

[0048] Step 1. Create n folders corresponding to n different handwritten Chinese character images, put m Chinese character images in each folder, and finally get n*m pictures as a handwritten Chinese character data set;

[0049] Step 2. Train the handwritten Chinese character image data obtained in step 1, and iteratively update the discriminator neural network weights and generator neural network weights through the gradient backpropagation algorithm, such as figure 1 Shown is the framework process diagram of the training, which is implemented according to the following steps:

[0050] Step 2.1. Randomly take a k-dimensional vector z from a Gau...

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 defective ancient book Chinese character restoration method based on a conditional adversarial network, and the method comprises the steps: building n folders which respectively correspond to n different handwritten Chinese character images, respectively placing m Chinese character images in each folder, and finally obtaining n * m images as a handwritten Chinese character data set; training the obtained handwritten Chinese character image data, and iteratively updating a discriminator neural network weight and a generator neural network weight through a gradient backpropagation algorithm; and finally, substituting a to-be-processed defective handwritten Chinese character image data sample into the updated discriminator and generator for iteration to obtain a restored handwritten Chinese character image. The problem that in the prior art, damaged characters in a large number of damaged ancient books and literatures are difficult to repair is solved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for repairing missing ancient Chinese characters based on a conditional confrontation network. Background technique [0002] As a carrier of information, images play an important role in cultural inheritance. At present, many ancient books and documents have been damaged to varying degrees due to the influence of different temperatures, humidity and climates. The most important part of them is the Chinese characters in the documents, which carry the excellent civilization of China. It is a pity that some Chinese characters are seriously damaged. Although they can be repaired by manpower based on contextual inference, there are so many ancient books and documents that the cost and time of manpower restoration alone are difficult to estimate. Therefore, it is very necessary to repair Chinese character images by replacing manpower with computer technol...

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): G06T5/00G06T5/50
CPCG06T5/50G06T2207/10004G06T2207/20081G06T2207/20084G06T5/77
Inventor 张九龙郭铭涛屈晓娥
Owner 陕西集大成得智慧教育科技有限公司
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