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

Method and system for comparing single-line text and images based on resnet

A text-picture, single-line technology, applied in the field of text recognition, can solve the problems of limited comparison accuracy rate, preparation rate, single-line text-picture comparison accuracy cannot be improved, and achieve the effect of improving comparison accuracy

Active Publication Date: 2022-06-07
珠海金智维信息科技有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the comparison accuracy of this method is usually limited by the preparation rate of OCR, and OCR is a more complicated problem than image comparison, resulting in the inability to improve the comparison accuracy of single-line text images

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
  • Method and system for comparing single-line text and images based on resnet
  • Method and system for comparing single-line text and images based on resnet
  • Method and system for comparing single-line text and images based on resnet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following describes in detail the embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, only used to explain the present invention, and should not be construed as a limitation of the present invention.

[0029] In the description of the present invention, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, exceeding, etc. are understood as not including this number, above, below, within, etc. are understood as including this number . If it is described that the first and the second are only for the purpose of distinguishing technical features, it cannot be understood as indicating or implying relative importance, or indicating the numb...

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 Resnet-based single-line text picture comparison method and system. The method includes the following steps: a training step, inputting a training data set, extracting features of a single-line text picture through a feature extraction network, and converting the Euclidean distance into Edit distance, and build a loss function based on the edit distance to complete the training of the feature extraction network; in the recognition step, input the single-line text image to be compared, and obtain the edit distance of the single-line text image to be compared through the trained feature extraction network model. The invention realizes the calculation of the editing distance based on the feature extraction neural network, and can effectively improve the comparison accuracy of single-line text pictures.

Description

technical field [0001] The invention relates to the technical field of text recognition, in particular to a Resnet-based single-line text-picture comparison method and system. Background technique [0002] At present, in order to solve the comparison problem of single-line text images, OCR technology is usually used to identify the text content and then calculate the text edit distance. However, the comparison accuracy of this method is usually limited by the preparation rate of OCR, and OCR is a more complicated problem than image comparison, resulting in the inability to improve the comparison accuracy of single-line text images. SUMMARY OF THE INVENTION [0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a Resnet-based single-line text image comparison method, which can effectively improve the contrast accuracy of single-line text images. [0004] The present inventi...

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 Patents(China)
IPC IPC(8): G06V10/74G06V10/75G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/22
Inventor 廖万里金卓肖飞林春莲
Owner 珠海金智维信息科技有限公司
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