SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION

Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a predic...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HUTKOWSKI, Paul, SUCH, Felipe Petroski, PTUCHA, Raymond, BROCKLER, Frank
Format: Patent
Sprache:eng
Schlagworte:
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 HUTKOWSKI, Paul
SUCH, Felipe Petroski
PTUCHA, Raymond
BROCKLER, Frank
description Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2021034850A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2021034850A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2021034850A13</originalsourceid><addsrcrecordid>eNqNyk0KwjAQQOFuXIh6hwHXQn8Uug3ptAmmGUgmlq5KKXElWqj3RyoewNUHj7dNJt97xhaEraBFVlQB1SCVcEIyOnAoqbGaNVkIXtsG6mBMD5LsjUxYuzBgMbgv3JG7eug0KxDMaNdhn2zu42OJh5-75FgjS3WK82uIyzxO8RnfQ_B5mmdpcS4vqciK_64PMjs1wQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION</title><source>esp@cenet</source><creator>HUTKOWSKI, Paul ; SUCH, Felipe Petroski ; PTUCHA, Raymond ; BROCKLER, Frank</creator><creatorcontrib>HUTKOWSKI, Paul ; SUCH, Felipe Petroski ; PTUCHA, Raymond ; BROCKLER, Frank</creatorcontrib><description>Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2021</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=20210204&amp;DB=EPODOC&amp;CC=US&amp;NR=2021034850A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210204&amp;DB=EPODOC&amp;CC=US&amp;NR=2021034850A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HUTKOWSKI, Paul</creatorcontrib><creatorcontrib>SUCH, Felipe Petroski</creatorcontrib><creatorcontrib>PTUCHA, Raymond</creatorcontrib><creatorcontrib>BROCKLER, Frank</creatorcontrib><title>SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION</title><description>Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyk0KwjAQQOFuXIh6hwHXQn8Uug3ptAmmGUgmlq5KKXElWqj3RyoewNUHj7dNJt97xhaEraBFVlQB1SCVcEIyOnAoqbGaNVkIXtsG6mBMD5LsjUxYuzBgMbgv3JG7eug0KxDMaNdhn2zu42OJh5-75FgjS3WK82uIyzxO8RnfQ_B5mmdpcS4vqciK_64PMjs1wQ</recordid><startdate>20210204</startdate><enddate>20210204</enddate><creator>HUTKOWSKI, Paul</creator><creator>SUCH, Felipe Petroski</creator><creator>PTUCHA, Raymond</creator><creator>BROCKLER, Frank</creator><scope>EVB</scope></search><sort><creationdate>20210204</creationdate><title>SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION</title><author>HUTKOWSKI, Paul ; SUCH, Felipe Petroski ; PTUCHA, Raymond ; BROCKLER, Frank</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2021034850A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HUTKOWSKI, Paul</creatorcontrib><creatorcontrib>SUCH, Felipe Petroski</creatorcontrib><creatorcontrib>PTUCHA, Raymond</creatorcontrib><creatorcontrib>BROCKLER, Frank</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HUTKOWSKI, Paul</au><au>SUCH, Felipe Petroski</au><au>PTUCHA, Raymond</au><au>BROCKLER, Frank</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION</title><date>2021-02-04</date><risdate>2021</risdate><abstract>Embodiments of the present disclosure include a method that obtains a digital image. The method includes extracting a word block from the digital image. The method includes processing the word block by evaluating a value of the word block against a dictionary. The method includes outputting a prediction equal to a common word in the dictionary when a confidence factor is greater than a predetermined threshold. The method includes processing the word block and assigning a descriptor to the word block corresponding to a property of the word block. The method includes processing the word block using the descriptor to prioritize evaluation of the word block. The method includes concatenating a first output and a second output. The method includes predicting a value of the word block.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2021034850A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title SYSTEM AND METHOD OF CHARACTER RECOGNITION USING FULLY CONVOLUTIONAL NEURAL NETWORKS WITH ATTENTION
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T01%3A25%3A44IST&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=HUTKOWSKI,%20Paul&rft.date=2021-02-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2021034850A1%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