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

Court judgment document-oriented multi-scale learning character recognition method and system

A character recognition and multi-scale technology, applied in the field of optical character recognition, can solve problems such as unsatisfactory requirements, achieve the effect of removing seal traces, improving recognition performance, and effective recognition

Pending Publication Date: 2020-11-24
SHANDONG UNIV
View PDF0 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this type of method can only deal with a single problem. When there are multiple aspect ratio texts in the text, especially when there are large or small aspect ratios, this type of method cannot meet the needs.

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
  • Court judgment document-oriented multi-scale learning character recognition method and system
  • Court judgment document-oriented multi-scale learning character recognition method and system
  • Court judgment document-oriented multi-scale learning character recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] As mentioned in the background technology, court judgment documents, contracts and other documents with seals, etc., will be affected by the occlusion of seal marks when performing text recognition. Therefore, in this embodiment, court judgment documents are taken as an example, such as figure 1 As shown, a text recognition method for multi-scale learning of court judgment documents is provided, including:

[0034] S1: Obtain the image of the court judgment document to be recognized, and extract the seal area;

[0035] S2: Taking the maximum difference in the target RGB value as the objective function, taking the cycle consistency loss as the constraint condition, constructing a stamp generation network model based on the confrontation network, using the trained stamp generation network model to convert the RGB value of the stamp trace in the stamp area, and Remove stamp traces in the converted stamp area;

[0036] S3: Perform feature extraction on the image of court j...

Embodiment 2

[0110] This embodiment provides a character recognition system for multi-scale learning of court judgment documents, including:

[0111] The image acquisition module is used to acquire the image of the court judgment document to be recognized and extract the seal area;

[0112] The trace deletion module is used to take the maximum difference in the target RGB value as the objective function, and take the cycle consistency loss as the constraint condition, build a stamp generation network model based on the confrontation network, and use the trained stamp generation network model to perform stamp trace RGB values ​​on the stamp area conversion, and remove stamp traces in the converted stamp area;

[0113] The text recognition module is used to perform feature extraction on images of court judgment documents with stamp traces removed, perform global target detection and local detail detection on the obtained feature maps, and combine the obtained text candidate frame masks with ...

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 discloses a court judgment document-oriented multi-scale learning character recognition method and system. The method comprises the steps of: acquiring a to-be-recognized court judgmentdocument image, and extracting a seal area; constructing a seal generation network model based on an adversarial network by taking the maximum difference of the target RGB values as an objective function and taking the cyclic consistency loss as a constraint condition, performing seal trace RGB value conversion on the seal area by adopting the trained seal generation network model, and deleting the seal trace of the converted seal area; and carrying out feature extraction on the court judgment document image with the seal trace deleted, respectively carrying out global target detection and local detail detection on an obtained feature map, combining the obtained masks and progressive masks of text candidate boxes, then training a constructed text detection model, and obtaining a text recognition result by using the trained text detection model. The problems of seal trace shielding in the text image and detection of super-long and super-short texts are effectively solved.

Description

technical field [0001] The invention relates to the technical field of optical character recognition, in particular to a character recognition method and system for multi-scale learning of court judgment documents. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the wide application of platform scanners and mobile phone scanning, as well as the popularization of information automation and office automation, it is now possible to directly recognize text on images by taking photos. In the judicial system, all kinds of cases are complicated, and the work of entering judgment documents is particularly heavy. OCR technology can use optical technology and computer technology to analyze and recognize image files of text materials to obtain text information. Therefore, OCR technology for scanned images of court judgment documents can realize...

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
IPC IPC(8): G06K9/20G06K9/34G06K9/46G06K9/62
CPCG06V10/225G06V30/153G06V10/44G06V10/56G06F18/214Y02P90/30
Inventor 尹义龙秦者云袭肖明王奎奎黄瑾周子淇刘祥飞
Owner SHANDONG UNIV
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