Table image recognition method and device

A technology of image recognition and tables, applied in the computer field, to achieve the effect of improving reliability, improving efficiency, and narrowing the search space

Active Publication Date: 2021-08-13
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing form image recognition methods are often affected by the shooting quality of form images, therefore, it is urgent to provide a more reliable form image recognition method

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
  • Table image recognition method and device
  • Table image recognition method and device
  • Table image recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The solutions provided in this specification will be described below in conjunction with the accompanying drawings.

[0027] Before describing the solution provided by the embodiment of the present specification, the inventive concept of the solution is explained as follows.

[0028] The traditional table image recognition method can be as follows: first, row and column segmentation is performed on the table image. Afterwards, each cell image of the table image is determined based on the segmentation result, and text recognition is performed on each cell image. Finally, the table structure is restored based on the recognition results. The text recognition is based on OCR technology. However, when recognizing images based on OCR technology, it is often affected by image shooting quality (illumination conditions, picture tilt / bend, camera resolution). Therefore, traditional form image recognition techniques are less accurate.

[0029] For this reason, the inventors of ...

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 table image recognition method and device; in the table image recognition method, for a table image with header information, attribute categories of a plurality of areas divided for the table image are determined according to the header information; and each region is input into a text recognition model corresponding to the attribute category of the region for text recognition. For a table image without header information, an attribute category prediction model is used to predict respective attribute categories of a plurality of areas divided for the table image. And each region is input into a text recognition model corresponding to the attribute category of the region for text recognition.

Description

technical field [0001] One or more embodiments of this specification relate to the field of computer technology, and in particular to a form image recognition method and device. Background technique [0002] Tables are commonly used data carriers in documents. Tables are more and more widely used in our daily life. Expressing data in the form of tables can be visualized and concise. At present, most enterprises, especially IT, banking, finance and other industries, have to deal with an astonishing number of forms every day. However, in practical applications, we will encounter some documents containing tables in PDF format or image format, that is, we will encounter some table images. In these cases, if we want to obtain table data, we need to identify the table images deal with. [0003] Existing form image recognition methods are often affected by the shooting quality of form images, therefore, there is an urgent need to provide a more reliable form image recognition me...

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): G06K9/00G06K9/32G06K9/34G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V30/412G06V30/416G06V20/62G06V30/153G06V10/44G06V30/10G06N3/044G06N3/045
Inventor 孙增辉
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
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