Image recognition method and device, storage medium and terminal

The invention discloses an image recognition method, and relates to the technical field of image recognition. Firstly, obtaining a document image of a document currently displayed on a screen; determining at least one feature layer corresponding to the document image based on an image recognition mo...

Full description

Saved in:
Bibliographic Details
Main Author DENG CHUNLONG
Format Patent
LanguageChinese
English
Published 27.08.2021
Subjects
Online AccessGet full text

Cover

Loading…
Abstract The invention discloses an image recognition method, and relates to the technical field of image recognition. Firstly, obtaining a document image of a document currently displayed on a screen; determining at least one feature layer corresponding to the document image based on an image recognition model; and finally, based on the image identification model, cutting a suggested region corresponding to each feature layer, and determining paragraph prediction types and paragraph prediction positions corresponding to different paragraphs in the document image according to the suggested regions. The feature layer and the suggested area corresponding to the document image are determined based on the image recognition model, and the paragraph prediction types and paragraph prediction positions corresponding to different paragraphs in the document image are determined according to the suggested area, so that the accuracy of recognizing the document image based on the image recognition model can be improved, and the pa
AbstractList The invention discloses an image recognition method, and relates to the technical field of image recognition. Firstly, obtaining a document image of a document currently displayed on a screen; determining at least one feature layer corresponding to the document image based on an image recognition model; and finally, based on the image identification model, cutting a suggested region corresponding to each feature layer, and determining paragraph prediction types and paragraph prediction positions corresponding to different paragraphs in the document image according to the suggested regions. The feature layer and the suggested area corresponding to the document image are determined based on the image recognition model, and the paragraph prediction types and paragraph prediction positions corresponding to different paragraphs in the document image are determined according to the suggested area, so that the accuracy of recognizing the document image based on the image recognition model can be improved, and the pa
Author DENG CHUNLONG
Author_xml – fullname: DENG CHUNLONG
BookMark eNrjYmDJy89L5WRw8MxNTE9VKEpNzk_PyyzJzM9TyE0tychPUUjMS1FISS3LTE7VUSguyS8CKctNTckszQVLlaQW5WbmJebwMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQ2NjQ2MDMzNHY2LUAAC42zKu
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
DocumentTitleAlternate 图像识别方法、装置、存储介质以及终端
ExternalDocumentID CN113313066A
GroupedDBID EVB
ID FETCH-epo_espacenet_CN113313066A3
IEDL.DBID EVB
IngestDate Fri Aug 16 05:50:23 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language Chinese
English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_CN113313066A3
Notes Application Number: CN202110701859
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210827&DB=EPODOC&CC=CN&NR=113313066A
ParticipantIDs epo_espacenet_CN113313066A
PublicationCentury 2000
PublicationDate 20210827
PublicationDateYYYYMMDD 2021-08-27
PublicationDate_xml – month: 08
  year: 2021
  text: 20210827
  day: 27
PublicationDecade 2020
PublicationYear 2021
RelatedCompanies OPPO GUANGDONG MOBILE TELECOMMUNICATIONS CO., LTD
RelatedCompanies_xml – name: OPPO GUANGDONG MOBILE TELECOMMUNICATIONS CO., LTD
Score 3.4799414
Snippet The invention discloses an image recognition method, and relates to the technical field of image recognition. Firstly, obtaining a document image of a document...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Title Image recognition method and device, storage medium and terminal
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210827&DB=EPODOC&locale=&CC=CN&NR=113313066A
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5qfd40KlofRJCcDKZJms0egtpNQhWaFqnSW8kTFZsUkyL4651d09aLXneWZRj4ZnZ2v5kBuDTwyprZKVVj3eioPGKoka6ZaqJl1CKaRWOTVyP3A6v3ZD6MO-MGvC1qYUSf0E_RHBERFSPeK-GvZ6tHLFdwK8vr6BWXiht_5LhKnR1j_mLrRHG7jjccuAOmMOawQAkenTbmYuiuLetuDdb5NZr32feeu7wqZfY7pPi7sDHE0_JqDxpfLxJss8XkNQm2-vWHtwSbgqEZl7hYo7Dch9v7KXoBecn9KXL5ZxC0HOaJnKQc_Fcypz3ybfz3fD4Vopr58n4AF743Yj0VlZosLTBhwUp_4xCaeZGnRyAbhhESalFdj20-OZpSEoeIyk6mhalGomNo_X1O6z_hCexwa_LHU52cQrP6mKdnGH2r6FyY7Rs92oc4
link.rule.ids 230,309,786,891,25594,76903
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3fT8IwEL4g_sA3RY3ir5mYPbk4NrauD4tKxzKUDWLQ8LZsY0SNDCIjJv71XusAX_S1bZrmku-uX_vdHcCljlfWkZVSJdF0Q-ERQ4k1taEM1RE1iWrSpMGzkf3A9J4a9wNjUIK3RS6MqBP6KYojIqISxHsu_PV09YjlCG3l7Dp-xaHJjdu3Hblgx8hfLI3ITtNu9bpOl8mM2SyQg0e7jlwM3bVp3q3BOkFKKKjSc5NnpUx_hxR3BzZ6uFuW70Lp66UKFbbovFaFLb_48K7CplBoJjMcLFA424Pb9hi9gLTU_kwy6acRtBRlQ2mYcvBfSVz2yJfx3_P5WEwVypf3fbhwW33mKXiocGmBkAWr8-sHUM4mWXoIkq7rEaEm1bTE4p2jKSVJhKg0RmqUqiQ-gtrf-9T-mzyHitf3O2GnHTwcwza3LH9I1cgJlPOPeXqKkTiPz4QJvwG1aIoi
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Image+recognition+method+and+device%2C+storage+medium+and+terminal&rft.inventor=DENG+CHUNLONG&rft.date=2021-08-27&rft.externalDBID=A&rft.externalDocID=CN113313066A