Unlock instant, AI-driven research and patent intelligence for your innovation.

Text recognition method and system based on paper document and computer medium

A technology for text recognition and paper documents, applied in the field of text recognition, to improve the effect of electronic conversion

Pending Publication Date: 2021-02-26
HANGZHOU WEIMING XINKE TECH CO LTD +1
View PDF30 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a text recognition method, system and computer medium based on paper documents, aiming to solve the problem that there is no text information recognition and extraction with positional relationship for paper documents such as medical examination reports

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
  • Text recognition method and system based on paper document and computer medium
  • Text recognition method and system based on paper document and computer medium
  • Text recognition method and system based on paper document and computer medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] figure 1 A schematic diagram of the steps of the paper document-based text recognition method according to the embodiment of the present application is shown in . figure 2 A schematic flowchart of a paper document-based text recognition method according to an embodiment of the present application is shown in .

[0054] Such as figure 1 As shown, the text recognition method based on paper documents in the embodiment of the present application specifically includes the following steps:

[0055] S101: Acquire an image of a paper document, identify straight lines in the image, and obtain multiple straight lines in the image.

[0056] Specifically, the straight line in the image is found through the Canny operator and the Hough line transformation, and the specific steps include:

[0057] First, convert the image to grayscale;

[0058] Then, according to the grayscale image, use an edge detection algorithm, such as the Canny operator to detect the edge, and use the prob...

Embodiment 2

[0104] This embodiment provides a text recognition system based on paper documents. For details not disclosed in the text recognition system based on paper documents in this embodiment, please refer to the text recognition methods based on paper documents in other embodiments specific implementation content.

[0105] Image 6 A schematic structural diagram of a paper document-based text recognition system according to an embodiment of the present application is shown in .

[0106] Such as Image 6 As shown, the text recognition system based on paper documents in the embodiment of the present application specifically includes an image recognition module 10 , an image correction module 20 , a text detection and recognition module 30 , an image mainline module 40 and a structured text recognition module 50 .

[0107] Image recognition module 10: used to acquire an image of a paper document, recognize straight lines in the image, and obtain multiple straight lines in the image. ...

Embodiment 3

[0135] This embodiment provides a text recognition device based on a paper document. For details not disclosed in the text recognition device based on a paper document in this embodiment, please refer to the text recognition method based on a paper document in other embodiments Or the specific implementation content of the system.

[0136] Figure 7 A schematic structural diagram of a paper document-based text recognition device 400 according to an embodiment of the present application is shown in .

[0137] Such as Figure 7 As shown, the text recognition device 400 includes:

[0138] Memory 402: for storing executable instructions; and

[0139] Processor 401: used to connect with memory 402 to execute executable instructions so as to complete the motion vector prediction method.

[0140] Those skilled in the art can understand that the Figure 7 It is only an example of the text recognition device 400, and does not constitute a limitation to the text recognition device ...

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 embodiment of the invention provides a text recognition method and system based on a paper document, and the method comprises the steps: obtaining an image of the paper document, recognizing a straight line in the image, and obtaining a plurality of straight lines in the image; correcting the image position according to the positions of the plurality of straight lines to obtain a corrected image; performing text detection and text recognition according to the text area of the corrected image to obtain a text information position and text information; according to the positions of the plurality of straight lines, carrying out straight line processing to obtain a main line in the image; and dividing a text region of the corrected image through a main line in the image, and performing position sorting on the text information according to the position of the text information to obtain a text recognition result. According to the method, a series of text information with position information is obtained through text detection and text recognition of the OCR technology, and finally, a paper edition document medical examination report is converted into electronic and structured examination report data.

Description

technical field [0001] The present application belongs to the technical field of text recognition, and in particular, relates to a text recognition method, system and computer medium based on paper documents. Background technique [0002] At present, the medical examination report is one of the important tools to assist clinical diagnosis and treatment. In 2018, the total number of visits in my country's medical institutions exceeded 8.3 billion, and each patient may generate multiple medical inspection reports for each visit. In my country, such a large number of inspection report data still relies on paper-based storage. Paper-based medical test reports are not only difficult to save, retrieve, and easily lost, but also not conducive to the extraction of patient medical test result information, and cannot be further intelligently analyzed based on the content of the test report, so that detailed diagnosis and treatment recommendations cannot be provided for patients. [0...

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
IPC IPC(8): G06K9/20G06K9/34G06T7/13
CPCG06T7/13G06V10/22G06V10/267G06V30/153G06V30/10
Inventor 王飞沈华李青李鹏飞
Owner HANGZHOU WEIMING XINKE TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com