Form recognition method and device in image, electronic equipment and storage medium

A recognition method, a technology in an image, applied in the field of image recognition

Active Publication Date: 2020-10-23
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned deficiencies in the prior art, the present invention provides a form recognition method, device, electronic equipment and storage medium in an image, which simultaneously solve various types of forms such as full-framed forms, partially-framed forms, and frameless forms. Improve the recognition accuracy of table structure and content

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 and device in image, electronic equipment and storage medium
  • Form recognition method and device in image, electronic equipment and storage medium
  • Form recognition method and device in image, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] Such as figure 1 As shown, the present invention provides a kind of form recognition method in the image, comprises the following steps:

[0083] S1. Obtain an image containing a table area to be identified;

[0084] In this embodiment, the image to be recognized includes a table area, and there may be one or more table areas, which is not limited in this embodiment. If the form is in paper format, you can scan the paper form with a scanner or use an electronic device such as a mobile phone with a scanning function to shoot and perform projection transformation correction to obtain an image to be recognized. Such as figure 2 shown.

[0085] S2. Use the deep learning model and the straight line detection method to perform cascade correction on the image; the implementation method is as follows:

[0086] S201. Use the deep learning model to classify the image horizontally and vertically, and adjust the image to be horizontal;

[0087] S202. Use the text detection me...

Embodiment 2

[0138] Based on the above method, the present invention also provides a recognition device for a form in an image, such as Figure 12 shown, including:

[0139] The image acquisition module is used to obtain the image containing the table area to be recognized; the image correction module is used to perform cascading correction on the image by using the deep learning model and the line detection method respectively; the table area detection module is used to use the deep learning model to detect The table area in the image after cascading correction is output; the table structure recognition module is used to detect row list grid lines from the table area image and reconstruct the table structure; the cell text recognition module is used to segment the text in the cell in the table structure Text, and use the text recognition model to recognize the text in the cell; the output module is used to format and output the recognition result, and complete the recognition of the table...

Embodiment 3

[0142] The present invention also provides an electronic device, including a processor, and a memory connected to the processor, the memory is used to store executable instructions of the processor; the executable instructions are loaded and executed by the processor, so as to realize the Operations performed in the table recognition method in images described above.

[0143] In this embodiment, the memory can be used to store software programs and various data. The memory can include a program storage area and a data storage area. The program storage area can store an operating system and an application program required by at least one function. The storage data area can store combined image information or target image information, etc. In addition, the memory may include high-speed random access memory or non-volatile memory, such as at least one magnetic disk storage device, flash memory device or other volatile solid-state storage devices.

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 provides a form recognition method and device in an image, electronic equipment and a storage medium. The form recognition method comprises the steps of obtaining a to-be-recognized image; performing cascade correction based on deep learning and straight line detection; performing form area detection based on deep learning; detecting row and column table lines from the form area image, and reconstructing a table structure; recognizing texts in the cells based on a text recognition model of deep learning; realizing identification result formatted output. Through the design, the identification problem of various different types of forms such as a full-frame-line form, a partial-frame-line form and a frameless-line form is solved at the same time, and the form structure and content identification accuracy is improved.

Description

technical field [0001] The invention belongs to image recognition technology, and in particular relates to a table recognition method, device, electronic equipment and storage medium in an image. Background technique [0002] Tables are a common form of content in documents, which can represent structured content, and thus contain a large amount of information, and play an important role in documents. Paper form documents can be seen everywhere in life, and can be seen everywhere in various paper documents in life, such as product lists, information collection forms, and other list reports. With the massive growth of paper form documents, the work of finding information and checking information from documents has become increasingly heavy, which has brought huge labor costs, and the error rate of manually reading data from documents is high. Therefore, using computer technology The need to automatically digitize tabular documents is becoming more common. Using computers to...

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): G06K9/00G06K9/32G06K9/34G06K9/62G06N3/04
CPCG06V30/413G06V30/43G06V10/242G06V10/243G06V10/267G06N3/045G06F18/214
Inventor 孔垂鑫王鉴宇郑嘉文李文段立新
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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