Text content extraction method and device

Text content extraction method and device

The invention provides a text content extraction method and device, and the method comprises the steps: carrying out the character recognition processing of a target image, and determining a marking graph containing a character identifier according to a processing result; inputting the mark graph co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN YIMING, CHEN HUAHUA, LIN JINSHU, CHEN LIJUAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator CHEN YIMING
CHEN HUAHUA
LIN JINSHU
CHEN LIJUAN
description The invention provides a text content extraction method and device, and the method comprises the steps: carrying out the character recognition processing of a target image, and determining a marking graph containing a character identifier according to a processing result; inputting the mark graph containing the character identification into an image processing model for processing, and obtaining a reference graph which is output by the image processing model and contains prediction lines; determining mark information corresponding to the character identifier in the mark graph and line information corresponding to the predicted line in the reference graph; calculating connection parameters according to the mark information and the line information, and constructing a target relation graph corresponding to the target image based on the connection parameters; and extracting the text content in the target image by using the target relation graph, thereby improving the text integrity degree of text content extract
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116092100A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116092100A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116092100A3</originalsourceid><addsrcrecordid>eNrjZNAMSa0oUUjOzytJzStRALKLEpNLMvPzFHJTSzLyUxQS81IUUlLLMpNTeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGZgaWRoYGBozExagAHeyid</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Text content extraction method and device</title><source>esp@cenet</source><creator>CHEN YIMING ; CHEN HUAHUA ; LIN JINSHU ; CHEN LIJUAN</creator><creatorcontrib>CHEN YIMING ; CHEN HUAHUA ; LIN JINSHU ; CHEN LIJUAN</creatorcontrib><description>The invention provides a text content extraction method and device, and the method comprises the steps: carrying out the character recognition processing of a target image, and determining a marking graph containing a character identifier according to a processing result; inputting the mark graph containing the character identification into an image processing model for processing, and obtaining a reference graph which is output by the image processing model and contains prediction lines; determining mark information corresponding to the character identifier in the mark graph and line information corresponding to the predicted line in the reference graph; calculating connection parameters according to the mark information and the line information, and constructing a target relation graph corresponding to the target image based on the connection parameters; and extracting the text content in the target image by using the target relation graph, thereby improving the text integrity degree of text content extract</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230509&amp;DB=EPODOC&amp;CC=CN&amp;NR=116092100A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230509&amp;DB=EPODOC&amp;CC=CN&amp;NR=116092100A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN YIMING</creatorcontrib><creatorcontrib>CHEN HUAHUA</creatorcontrib><creatorcontrib>LIN JINSHU</creatorcontrib><creatorcontrib>CHEN LIJUAN</creatorcontrib><title>Text content extraction method and device</title><description>The invention provides a text content extraction method and device, and the method comprises the steps: carrying out the character recognition processing of a target image, and determining a marking graph containing a character identifier according to a processing result; inputting the mark graph containing the character identification into an image processing model for processing, and obtaining a reference graph which is output by the image processing model and contains prediction lines; determining mark information corresponding to the character identifier in the mark graph and line information corresponding to the predicted line in the reference graph; calculating connection parameters according to the mark information and the line information, and constructing a target relation graph corresponding to the target image based on the connection parameters; and extracting the text content in the target image by using the target relation graph, thereby improving the text integrity degree of text content extract</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAMSa0oUUjOzytJzStRALKLEpNLMvPzFHJTSzLyUxQS81IUUlLLMpNTeRhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGZgaWRoYGBozExagAHeyid</recordid><startdate>20230509</startdate><enddate>20230509</enddate><creator>CHEN YIMING</creator><creator>CHEN HUAHUA</creator><creator>LIN JINSHU</creator><creator>CHEN LIJUAN</creator><scope>EVB</scope></search><sort><creationdate>20230509</creationdate><title>Text content extraction method and device</title><author>CHEN YIMING ; CHEN HUAHUA ; LIN JINSHU ; CHEN LIJUAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116092100A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN YIMING</creatorcontrib><creatorcontrib>CHEN HUAHUA</creatorcontrib><creatorcontrib>LIN JINSHU</creatorcontrib><creatorcontrib>CHEN LIJUAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN YIMING</au><au>CHEN HUAHUA</au><au>LIN JINSHU</au><au>CHEN LIJUAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Text content extraction method and device</title><date>2023-05-09</date><risdate>2023</risdate><abstract>The invention provides a text content extraction method and device, and the method comprises the steps: carrying out the character recognition processing of a target image, and determining a marking graph containing a character identifier according to a processing result; inputting the mark graph containing the character identification into an image processing model for processing, and obtaining a reference graph which is output by the image processing model and contains prediction lines; determining mark information corresponding to the character identifier in the mark graph and line information corresponding to the predicted line in the reference graph; calculating connection parameters according to the mark information and the line information, and constructing a target relation graph corresponding to the target image based on the connection parameters; and extracting the text content in the target image by using the target relation graph, thereby improving the text integrity degree of text content extract</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116092100A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Text content extraction method and device
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T19%3A53%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=CHEN%20YIMING&rft.date=2023-05-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116092100A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true