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

Removal of background noise and noise in copybook binarization based on conditional confrontation network

A background noise and binarization technology, applied in the field of image processing, can solve the problems of classification recognition rate and cutting accuracy reduction, and achieve the effect of improving the classification recognition rate and cutting accuracy, beautifying the font map, and improving the use value.

Active Publication Date: 2019-06-18
西安飞蝶虚拟现实科技有限公司
View PDF5 Cites 0 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 removing background noise and noise in copybook binarization based on conditional confrontation network, which solves the problem of lower classification recognition rate and cutting accuracy due to background noise in the process of digitizing existing copybooks

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
  • Removal of background noise and noise in copybook binarization based on conditional confrontation network
  • Removal of background noise and noise in copybook binarization based on conditional confrontation network
  • Removal of background noise and noise in copybook binarization based on conditional confrontation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0051] The present invention is based on the copybook binarization background noise noise removal method of conditional confrontation network, comprises the following steps:

[0052] Step 1, create a sampling sample.

[0053] First, input m pages of Chinese characters in the Word document; then convert the Word document into pdf format; finally convert the pdf format into jpg format pictures, and finally get m pictures, which are sampling samples.

[0054] Step 2, according to the sampling samples in step 1, make an artificial noise data set to obtain the final training data.

[0055] Step 2.1, for the m pictures in the sampling sample in step 1, each picture is randomly cut into i pictures with a size of c×r, that is, m×i pictures with a size of c×r are obtained;

[0056] Step 2.2, for the m×i pictures processed in step 2.1, make n circula...

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 conditional adversarial network-based copybook binary background noise point removal method. The method comprises the following steps of: 1, establishing a sampling sample; 2, making a manual noise data set according to the sampling sample in the step 1 so as to obtain final training data; 3, training the final training data obtained in the step 2 and updating a discriminator and a generator in sequence; and 4, importing a to-be-processed copybook data sample into the discriminator and the generator in the step 3 to carry out denoising, so as to obtain a noise point-removed copybook. According to the copybook binary background noise point removal method, background noise points caused to literatures by history reasons and improper digital operations can be effectively removed, a denoising operation is provided for digital platform display, and font figures are beautified; and meanwhile, the classification and recognition rate and the cutting precision are improved, and a good using value is provided.

Description

technical field [0001] The invention belongs to the technical field of image processing methods, and in particular relates to a method for removing background noise and noise in copybook binarization based on a conditional confrontation network. Background technique [0002] Guided by our country's traditional culture protection strategy, more and more ancient books, inscriptions, and Buddhist scriptures have been preserved through digital means. After digitization, these materials have high research value, but many materials are in the process of digitization. The age is too long, and there are many background noises, which seriously affect the beauty of the ancient prose and the follow-up research work. For example, in the process of classifying ancient Chinese fonts, the existence of font background noises seriously affects the classification and recognition rate of ancient Chinese fonts; in the process of font cutting, these background noises also have a great impact on ...

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): G06T5/00
CPCG06T5/002G06T2207/20081G06T2207/20084
Inventor 张九龙郭铭涛屈小娥
Owner 西安飞蝶虚拟现实科技有限公司
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