Document image deblurring method, system and equipment based on deep learning

The invention discloses a document image deblurring method, system and device based on deep learning, and relates to the field of image restoration and reconstruction. According to the method, firstly, blurred document images with different blurring degrees are generated in batches in a blurring ker...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YUAN HONGWU, ZHOU YANG, JIN RUI, XI YULIANG, XU GUOMING, CAO XUYAN, WAN XINWEN, YANG YUMU
Format: Patent
Sprache:chi ; 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 YUAN HONGWU
ZHOU YANG
JIN RUI
XI YULIANG
XU GUOMING
CAO XUYAN
WAN XINWEN
YANG YUMU
description The invention discloses a document image deblurring method, system and device based on deep learning, and relates to the field of image restoration and reconstruction. According to the method, firstly, blurred document images with different blurring degrees are generated in batches in a blurring kernel generation mode based on an original clear document image; forming an image data set by the fuzzy document image and the corresponding original clear document image; constructing a convolutional neural network model comprising a residual error backbone network and a feature fusion module; training and testing the convolutional neural network model by using the image data set to obtain a trained convolutional neural network model as a deblurring model of the document image; and inputting a document image to be deblurred into the deblurring model, and directly outputting a corresponding clear document image in an end-to-end manner. The document image subjected to blurring removal through the method has high conte
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118096587A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118096587A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118096587A3</originalsourceid><addsrcrecordid>eNrjZPB1yU8uzU3NK1HIzE1MT1VISU3KKS0qysxLV8hNLcnIT9FRKK4sLknNVUjMS1FILSzNLACrTkosTk1RyM8DakgtUMhJTSzKA-rhYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhhYGlmamFuaOxsSoAQDRNTYl</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Document image deblurring method, system and equipment based on deep learning</title><source>esp@cenet</source><creator>YUAN HONGWU ; ZHOU YANG ; JIN RUI ; XI YULIANG ; XU GUOMING ; CAO XUYAN ; WAN XINWEN ; YANG YUMU</creator><creatorcontrib>YUAN HONGWU ; ZHOU YANG ; JIN RUI ; XI YULIANG ; XU GUOMING ; CAO XUYAN ; WAN XINWEN ; YANG YUMU</creatorcontrib><description>The invention discloses a document image deblurring method, system and device based on deep learning, and relates to the field of image restoration and reconstruction. According to the method, firstly, blurred document images with different blurring degrees are generated in batches in a blurring kernel generation mode based on an original clear document image; forming an image data set by the fuzzy document image and the corresponding original clear document image; constructing a convolutional neural network model comprising a residual error backbone network and a feature fusion module; training and testing the convolutional neural network model by using the image data set to obtain a trained convolutional neural network model as a deblurring model of the document image; and inputting a document image to be deblurred into the deblurring model, and directly outputting a corresponding clear document image in an end-to-end manner. The document image subjected to blurring removal through the method has high conte</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2024</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=20240528&amp;DB=EPODOC&amp;CC=CN&amp;NR=118096587A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240528&amp;DB=EPODOC&amp;CC=CN&amp;NR=118096587A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YUAN HONGWU</creatorcontrib><creatorcontrib>ZHOU YANG</creatorcontrib><creatorcontrib>JIN RUI</creatorcontrib><creatorcontrib>XI YULIANG</creatorcontrib><creatorcontrib>XU GUOMING</creatorcontrib><creatorcontrib>CAO XUYAN</creatorcontrib><creatorcontrib>WAN XINWEN</creatorcontrib><creatorcontrib>YANG YUMU</creatorcontrib><title>Document image deblurring method, system and equipment based on deep learning</title><description>The invention discloses a document image deblurring method, system and device based on deep learning, and relates to the field of image restoration and reconstruction. According to the method, firstly, blurred document images with different blurring degrees are generated in batches in a blurring kernel generation mode based on an original clear document image; forming an image data set by the fuzzy document image and the corresponding original clear document image; constructing a convolutional neural network model comprising a residual error backbone network and a feature fusion module; training and testing the convolutional neural network model by using the image data set to obtain a trained convolutional neural network model as a deblurring model of the document image; and inputting a document image to be deblurred into the deblurring model, and directly outputting a corresponding clear document image in an end-to-end manner. The document image subjected to blurring removal through the method has high conte</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPB1yU8uzU3NK1HIzE1MT1VISU3KKS0qysxLV8hNLcnIT9FRKK4sLknNVUjMS1FILSzNLACrTkosTk1RyM8DakgtUMhJTSzKA-rhYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhhYGlmamFuaOxsSoAQDRNTYl</recordid><startdate>20240528</startdate><enddate>20240528</enddate><creator>YUAN HONGWU</creator><creator>ZHOU YANG</creator><creator>JIN RUI</creator><creator>XI YULIANG</creator><creator>XU GUOMING</creator><creator>CAO XUYAN</creator><creator>WAN XINWEN</creator><creator>YANG YUMU</creator><scope>EVB</scope></search><sort><creationdate>20240528</creationdate><title>Document image deblurring method, system and equipment based on deep learning</title><author>YUAN HONGWU ; ZHOU YANG ; JIN RUI ; XI YULIANG ; XU GUOMING ; CAO XUYAN ; WAN XINWEN ; YANG YUMU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118096587A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YUAN HONGWU</creatorcontrib><creatorcontrib>ZHOU YANG</creatorcontrib><creatorcontrib>JIN RUI</creatorcontrib><creatorcontrib>XI YULIANG</creatorcontrib><creatorcontrib>XU GUOMING</creatorcontrib><creatorcontrib>CAO XUYAN</creatorcontrib><creatorcontrib>WAN XINWEN</creatorcontrib><creatorcontrib>YANG YUMU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YUAN HONGWU</au><au>ZHOU YANG</au><au>JIN RUI</au><au>XI YULIANG</au><au>XU GUOMING</au><au>CAO XUYAN</au><au>WAN XINWEN</au><au>YANG YUMU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Document image deblurring method, system and equipment based on deep learning</title><date>2024-05-28</date><risdate>2024</risdate><abstract>The invention discloses a document image deblurring method, system and device based on deep learning, and relates to the field of image restoration and reconstruction. According to the method, firstly, blurred document images with different blurring degrees are generated in batches in a blurring kernel generation mode based on an original clear document image; forming an image data set by the fuzzy document image and the corresponding original clear document image; constructing a convolutional neural network model comprising a residual error backbone network and a feature fusion module; training and testing the convolutional neural network model by using the image data set to obtain a trained convolutional neural network model as a deblurring model of the document image; and inputting a document image to be deblurred into the deblurring model, and directly outputting a corresponding clear document image in an end-to-end manner. The document image subjected to blurring removal through the method has high conte</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118096587A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Document image deblurring method, system and equipment based on deep learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T07%3A06%3A19IST&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=YUAN%20HONGWU&rft.date=2024-05-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118096587A%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