Semantic analysis method and system for quality inspection report scanning image table

A technology for quality inspection and scanning images, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problem that table recognition cannot retain structured information, wrongly recognized content is not matched, does not contain semantic analysis of recognized text information, etc. question

Active Publication Date: 2021-05-25
GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, the existing image semantic analysis technology can only recognize scanned image text based on the horizontal direction, cannot retain the original structured information for table recognition, and does not include semantic analysis of recognized text information, and has no matching for wrongly recognized content error correction scheme

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
  • Semantic analysis method and system for quality inspection report scanning image table
  • Semantic analysis method and system for quality inspection report scanning image table
  • Semantic analysis method and system for quality inspection report scanning image table

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Based on the RRPN target recognition model, the DenseNet convolutional neural network, and the RNN sequence model, the present invention proposes a semantic analysis method and system for scanning image tables of quality inspection reports. Through the method, the text data of the scanned image table can be extracted and corrected.

[0058] The method provided by the invention can use computer software technology to realize the process, see figure 1 . Embodiment Take a closed switchgear quality inspection report scan image form as an example to carry out a specific elaboration on the process of the present invention, as follows:

[0059] 1) Perform image preprocessing on the scanned image form of the quality inspection report;

[0060] 2) Locate and recognize the text of the quality inspection report scanned image, which is cut into the table at different angles;

[0061] 3) Semantic analysis and error correction of the text recognition results of the scanned image o...

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 multi-directional error-correctable semantic analysis method and system for a quality inspection report scanning image table of closed switch equipment. The method specifically comprises the following steps: 1) carrying out image preprocessing on a quality inspection report scanning image table; 2) positioning and identifying characters of different-angle segmented tables of an scanned image of a quality inspection report; and 3) carrying out semantic analysis and error correction on the character recognition result of the scanned image of the quality inspection report to obtain a result. The method has the advantages that form lines are used for recognizing and positioning characters, and shadow interference of a scanned document is removed; detection of inclined texts and multi-scale texts is realized; and automatic error correction of wrong characters and wrong words in text recognition is realized.

Description

technical field [0001] The invention belongs to computer and information service technology, in particular to a method and system for semantic analysis of form content of a specific scanned image. Background technique [0002] Semantic analysis is the focus and difficulty of high-level cognition in image and text understanding. For the scanned image form of the closed switch equipment quality inspection report, we hope to use the image and text understanding algorithm to identify the scanned image, and perform semantic analysis on the recognition results to realize closed switch equipment. Automatic acceptance of equipment. [0003] For image understanding algorithms, text can be located and recognized. At present, the relatively mature text detection framework is CTPN (Connectionist Text Proposal Network), which has good accuracy, but the detection time is long, and it can only detect text in the horizontal direction, so there is a lot of room for optimization. [0004] F...

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): G06K9/00G06K9/20G06K9/40G06K9/62G06N3/08
CPCG06N3/08G06V30/413G06V30/412G06V10/22G06V10/30G06V30/10G06F18/2415
Inventor 尹旷喇元叶建斌张宇朱博苏海博方健
Owner GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID 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