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

A text recognition method, device, readable storage medium and equipment

A text recognition and recognition technology, which is applied in the field of image information recognition, can solve problems such as error-prone and low text recognition accuracy, and achieve the effect of avoiding sentence confusion and improving text recognition accuracy

Active Publication Date: 2022-03-25
江西中业智能科技有限公司
View PDF29 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on this, the object of the present invention is to provide a text recognition method, device, readable storage medium and equipment to solve the technical problems of low precision and error-prone existing text recognition

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
  • A text recognition method, device, readable storage medium and equipment
  • A text recognition method, device, readable storage medium and equipment
  • A text recognition method, device, readable storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] see figure 1, shows the text recognition method in the first embodiment of the present invention, the text recognition method can be implemented by software and / or hardware, and the method specifically includes steps S01-step S04.

[0056] Step S01, acquiring an image to be recognized.

[0057] Specifically, when the document to be identified is a paper document (such as printed matter), it can be converted into an image to be identified in the corresponding format by taking a photo or scanning. When taking a photo or scanning a paper document, try to ensure that the paper quality Documents should be placed flat and free of obvious stains on the surface to minimize noise interference in subsequent images. When the file to be identified belongs to an electronic file (such as PDF format) but not an image format, the file to be identified can be converted into an image to be identified in a corresponding format by means of image conversion.

[0058] Step S02 , using a pr...

Embodiment 2

[0067] see figure 2 , shows the text recognition method in the second embodiment of the present invention, the text recognition method can be implemented by software and / or hardware, and the method specifically includes steps S1-step S5.

[0068] Step S1, acquiring an image to be recognized, and performing preprocessing on the image to be recognized.

[0069] In this embodiment, the image to be recognized is converted from a paper document, and the specific conversion process is: converting the text into a pdf document by taking pictures or scanning, and then converting the pdf document through measures such as resolution control and file size filtering. Perform format parsing and convert to images to be recognized in specific formats (such as jpg, png, etc.).

[0070] Wherein, the preprocessing manner includes one or more of image size normalization, grayscale processing, binarization processing, bilateral filtering processing, mathematical morphology processing, and image ...

Embodiment 3

[0131] Another aspect of the present invention also provides a text recognition device, please refer to image 3 , shows the text recognition device in the third embodiment of the present invention, the text recognition device includes:

[0132] An image acquisition module 11, configured to acquire an image to be identified;

[0133] The information recognition module 12 is used to use a preset image recognition model to perform text and form recognition on the image to be recognized, so as to extract the text data, table structure and their respective coordinate information in the image to be recognized;

[0134] The area segmentation module 13 is used to segment the connected area of ​​the table structure based on the preset area segmentation module, so as to identify the effective rectangular area defined by the table structure, and determine the effective rectangular area according to the coordinate information of the table structure. Coordinate information of the rectang...

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 present invention provides a text recognition method, device, readable storage medium and equipment. The method includes: acquiring an image to be recognized; using a preset image recognition model to perform text and table recognition on the image to be recognized, so as to extract the image to be recognized The text data, table structure and their respective coordinate information; based on the preset area segmentation module, the connected area of ​​the table structure is segmented to identify the effective rectangular area defined by the table structure, and the effective rectangle is determined according to the coordinate information of the table structure The coordinate information of the area; according to the coordinate information of the text data and the effective rectangular area, the text data and the effective rectangular area are fused according to the coordinate correspondence, and the fusion result is output to identify the text content recorded in the image to be recognized. The invention realizes the automatic connection and combination of the multi-line text in the form and the form, avoids problems such as sentence confusion and semantic incomprehension in the recognition result, and improves the text recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of image information recognition, in particular to a text recognition method, device, readable storage medium and equipment. Background technique [0002] With the continuous development of computer technology, information technology occupies an increasingly important position in people's daily life. The rapid development of information technology has continuously updated information in all aspects of human society. People need to obtain the knowledge they need from a large amount of information. , it is necessary to process a large amount of information. All kinds of documents and materials are complicated, and these documents must be classified, stored, and sorted before they can be used. For some document information, corresponding documents and archives must be established. Sometimes it is necessary to exchange and retrieve some intelligence information. In order to Reduce labor costs while improving ef...

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): G06V30/148G06T7/11G06T7/187G06T7/62G06V10/80
CPCG06T7/62G06T7/187G06T7/11
Inventor 刘丹张恒星
Owner 江西中业智能科技有限公司
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