Table picture recognition method, apparatus and device, and readable storage medium

A picture recognition and table technology, applied in the field of image processing, can solve problems such as low accuracy of table structure recognition

Pending Publication Date: 2022-03-25
ONE CONNECT SMART TECH CO LTD SHENZHEN
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to provide a form picture recognition method, device, equipment and readable storage medium, which can solve the technical problem of low accuracy rate of form structure recognition caused by form recognition based on the spatial arrangement information of text content in the prior art

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 picture recognition method, apparatus and device, and readable storage medium
  • Table picture recognition method, apparatus and device, and readable storage medium
  • Table picture recognition method, apparatus and device, and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1 of the present invention provides a table picture recognition method, specifically, figure 1 An optional flowchart of the form picture recognition method is shown, as figure 1 As shown, the form picture recognition method may include steps S1 to S4, wherein:

[0028] In step S1, the picture of the table to be recognized is obtained, and the OCR recognition is performed on the picture of the table to be recognized, and the single-line text information of each cell box in the table to be recognized is obtained.

[0029] After obtaining the form picture to be recognized, based on the OCR (Optical Character Recognition, optical character recognition) technology, the form picture to be recognized is recognized, and the single-line text content of each cell box in the form to be recognized is obtained. Preferably, each The detection frame corresponding to the single-line text content, wherein the number of single-line text content is determined by the specific t...

Embodiment 2

[0090] Embodiment 2 of the present invention also provides a form and picture recognition device, which corresponds to the form and picture recognition method provided in the first embodiment above, and the corresponding technical features and technical effects will not be described in detail in this embodiment. As mentioned above, the relevant parts can refer to the first embodiment above. specifically, Figure 5 A structural block diagram of the table picture recognition device provided by Embodiment 2 of the present invention is shown. Such as Figure 5 As shown, the form picture identification device 500 includes a first acquisition module 501, a second acquisition module 502, an identification module 503 and a generation module 504, wherein:

[0091] The first obtaining module 501 is used to obtain the image of the table to be recognized, and perform OCR recognition on the image of the table to be recognized, and obtain the single-line text information of each cell...

Embodiment 3

[0102] Figure 6 It shows a block diagram of a computer device suitable for realizing the method for identifying table pictures provided by Embodiment 3 of the present invention. In this embodiment, the computer device 600 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a cabinet server (including an independent server, or multiple A server cluster composed of servers), etc. Such as Figure 6 As shown, the computer device 600 in this embodiment at least includes but is not limited to: a memory 601 , a processor 602 , and a network interface 603 that can be communicated with each other through a system bus. It should be pointed out that, Figure 6 Only computer device 600 is shown having components 601-603, but it should be understood that implementing all of the illustrated components is not a requirement and that more or fewer components may instead be implemented.

[0103] In this ...

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 relates to the technical field of image processing, and particularly discloses a table picture recognition method, device and equipment and a readable storage medium, and the method comprises the steps: obtaining a to-be-recognized table picture, carrying out the OCR recognition of the to-be-recognized table picture, and obtaining the single-line text information of each unit frame in the to-be-recognized table; performing convolutional neural network analysis and recognition on the to-be-recognized table picture to obtain a plurality of feature maps of the to-be-recognized table picture; a pre-trained table picture recognition model is obtained, the single-line text information and the feature graph are input into the table picture recognition model, a calculation result output by the table picture recognition model is obtained, the calculation result comprises output word segments and the incidence relation between the output word segments, and the incidence relation comprises self-attention scores and relative position vectors, the output word fragment is obtained after word segmentation is carried out on single-line text information by the table picture recognition model; and generating a table structure corresponding to the to-be-recognized table picture according to the output word fragments and the incidence relation between the output word fragments.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a form image recognition method, device, equipment and readable storage medium. Background technique [0002] Tables are used by people in all walks of life as a means of organizing data. Usually, in order to prevent the content of the form from being arbitrarily changed and causing damage to the original data, the form is saved in the form of a picture. When the form data needs to be used, it can be obtained by identifying the picture of the form. [0003] In the prior art, OCR detection is used to obtain the text content of the table picture, and the rows, columns and merged cells are deduced according to the spatial arrangement information of the text. However, this table recognition mechanism has the following two problems: The text in adjacent cells will be wrongly spliced ​​together, or multiple lines of text in the same cell with large line spacing will b...

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): G06V30/412G06V20/62G06V30/18G06V30/19G06V10/764G06K9/62G06F40/289G06F40/30G06N3/04G06N3/08
CPCG06F40/289G06F40/30G06N3/08G06N3/045G06F18/2415
Inventor 林大权蔡壮壮徐亮
Owner ONE CONNECT SMART TECH CO LTD SHENZHEN
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