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

Form recognition method, device, electronic device, storage medium

A recognition method and table technology, applied in the field of image recognition, can solve the problems of inability to accurately identify table data, poor robustness of table recognition, and inability to accurately identify tables, etc.

Active Publication Date: 2020-10-27
上海交通大学苏州人工智能研究院
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] OCR technology has also been applied to identify form images. The current OCR technology uses the method of recognizing the full text of the form. However, when the form is skewed or deformed, the form cannot be accurately identified, and thus the data in different areas of the form cannot be accurately identified. Poor table recognition robustness

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
  • Form recognition method, device, electronic device, storage medium
  • Form recognition method, device, electronic device, storage medium
  • Form recognition method, device, electronic device, storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 It is a schematic flow chart of a form recognition method provided in Embodiment 1 of the present application. This method is applicable to the situation of recognizing forms in OCR technology. The method can be executed by an electronic device used to recognize an image. The electronic device can be a personal computer, a tablet computer or smartphone, etc., the method includes:

[0026] Step 110, extract the intersection points contained in the table to be recognized.

[0027] Wherein, the table to be recognized includes a line segment in the first direction and a line segment in the second direction, the line segment in the first direction intersects the line segment in the second direction, and the intersection point is the point where the line segment in the first direction intersects the line segment in the second direction.

[0028] The table to be recognized is located in the currently processed image. In the scenario used in this application, the use...

Embodiment 2

[0051] figure 2 The schematic flow diagram of the form recognition method provided in Embodiment 2 of the present application, as an example of the above embodiment, in this example, the form to be recognized is a rectangular form, such as image 3 As shown, the table to be recognized has four vertices, namely vertex A, vertex B, vertex C and vertex D, vertex A and vertex B constitute the table edge AB, vertex B and vertex D constitute the table edge BD, vertex C and vertex D A table edge CD is formed, and vertex A and vertex C form a table edge AC. The edge of the table includes intersection point a, intersection point b, intersection point c, intersection point d, intersection point e and intersection point f. Vertex A, Vertex B, Vertex C, and Vertex D can also be considered intersection points. When identifying the form to be extracted, the method may be implemented through the following steps:

[0052] Step 201, using morphological transformation to obtain all intersec...

Embodiment 3

[0078] Figure 4 The structural diagram of the form recognition device provided in Embodiment 3 of the present application, the device may be located in an electronic device for recognizing images, and the electronic device may be a personal computer, a tablet computer, or a smart phone, etc., and the device includes: an intersection point extraction module 310, a network grid division module 320 , target grid intersection statistics module 330 and target table generation module 340 . in:

[0079] The intersection point extraction module 310 is used to extract the intersection points contained in the table to be recognized, the table to be recognized includes a line segment in the first direction and a line segment in the second direction, the line segment in the first direction and the line segment in the second direction intersect, and the intersection point is a line segment in the first direction the point where the line segment intersects the line segment in the second d...

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 application discloses a form recognition method, device, electronic equipment, and storage medium. The method includes: extracting the intersection points included in the form to be recognized, determining the size of the grid according to the distance between the intersection points on the sides of the form to be recognized, Divide the table to be recognized according to the grid, so that each grid contains at most one intersection point, and the adjacent grids of each grid do not contain intersection points; find the target grid where the prior intersection points are located, and count the target grid and the target network The number of target intersections in the grid that is contained in the adjacent grid of the grid in the target direction; determine whether to retain the line segment of the target grid in the target direction according to the number of target intersections; generate the target table according to the retained line segment of the target direction. According to the number of intersection points, it is determined whether there is a line segment in the target grid in the target direction, and then the table line segment associated with the prior intersection point in the table to be recognized is accurately identified, and the robustness of table recognition is improved.

Description

technical field [0001] The embodiments of the present application relate to image recognition technologies, and in particular to a form recognition method, device, electronic equipment, and storage medium. Background technique [0002] With the development of the times, the demand for image recognition is becoming more and more common. Optical Character Recognition (OCR) technology is applied to recognize text in images. OCR technology checks the characters printed on paper, determines its shape by detecting dark and light patterns, and then uses character recognition methods to translate the shape into computer text. [0003] OCR technology has also been applied to identify form images. The current OCR technology uses the method of recognizing the full text of the form. However, when the form is skewed or deformed, the form cannot be accurately identified, and thus the data in different areas of the form cannot be accurately identified. Table recognition is less robust. ...

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): G06K9/00G06K9/46
CPCG06V30/412G06V30/43G06V10/44
Inventor 梁宇舒
Owner 上海交通大学苏州人工智能研究院
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