Character recognition method and system based on super-resolution multi-scale reconstruction

A super-resolution, text recognition technology, applied in the field of text recognition, can solve the problems of reducing the overall accuracy of text recognition, unable to accurately edit text information, difficult to recognize small fonts, etc., to achieve precise editing, improve accuracy, and improve overall The effect of precision

Inactive Publication Date: 2022-01-07
BEIJING WILION TIME TECH
View PDF6 Cites 2 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 text recognition method and system based on super-resolution multi-scale reconstruction, which is used to improve the difficulty in accurately recognizing small fonts in the prior art, which greatly reduces the overall accuracy of text recognition. A problem that prevents readers from accurately editing text information in images

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
  • Character recognition method and system based on super-resolution multi-scale reconstruction
  • Character recognition method and system based on super-resolution multi-scale reconstruction
  • Character recognition method and system based on super-resolution multi-scale reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] Some implementations of the present application will be described in detail below in conjunction with the accompanying drawings. In the case of no conflict, each of the following embodiments and each feature in the embodiments can be combined with each other.

[0066] Please see figure 1 , figure 1 It is a flowchart of a character recognition method based on super-resolution multi-scale reconstruction provided by an embodiment of the present invention. The text recognition method based on super-resolution multi-scale reconstruction comprises the following steps:

[0067] Step S110: Obtain and build a text template library based on multiple sample text image sets; the above sample text image set refers to a certain number of text images selected for each Chinese character, which may include multiple small-size text images. The above-mentioned text template library refers to a text image library established based on a plurality of sample text images. The text template ...

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 provides a character recognition method and system based on super-resolution multi-scale reconstruction, and relates to the technical field of character recognition. The method comprises the steps: establishing a character template library; obtaining a to-be-recognized small-font character image; performing image sharpening on the to-be-recognized small-font character image by using a Laplace operator; then, carrying out multi-scale reconstruction on the enhanced small-word-size character image by adopting a super-resolution multi-scale reconstruction method; then performing similarity calculation on the small-font character images of each scale and character pictures in a character template library; and obtaining an identification result of the to-be-identified small-font character image according to the plurality of similarity results. According to the method, the small-size fonts are subjected to super-resolution multi-scale reconstruction, accurate recognition of the small-size fonts is realized by utilizing a template matching mode on the basis of the multi-scale reconstruction, the recognition accuracy of the small-size fonts is improved, the overall accuracy of character recognition is further improved, and a reader can accurately edit character information in an image.

Description

technical field [0001] The present invention relates to the technical field of character recognition, in particular to a method and system for character recognition based on super-resolution multi-scale reconstruction. Background technique [0002] In the era of digital media, many contracts, agreements, and papers are stored in the form of images, which greatly saves physical storage space and makes reading more convenient. More importantly, the text recognition technology can more accurately recognize the text in the image, which greatly facilitates users to edit it. [0003] However, the fonts in many contracts, agreements, and papers have obvious differences. Traditional text recognition technology is difficult to accurately recognize small fonts, which greatly reduces the overall accuracy of text recognition, making it impossible for readers to accurately edit text information in images. Contents of the invention [0004] The purpose of the present invention is to p...

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): G06V30/10G06V30/19G06K9/62G06T5/00G06F40/194G06F40/186
CPCG06T5/003G06F40/186G06F40/194G06F18/22
Inventor 边聪聪
Owner BEIJING WILION TIME TECH
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