Deep learning network processing device and method, and image processing unit

Deep learning network processing device and method, and image processing unit

The invention relates to the technical field of image processing, and discloses a deep learning network processing method, which comprises the following steps: compressing to-be-processed image data into a data packet, uploading the compressed data packet to an image processing unit, and vectorizing...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: WU TONGMING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PICTORIAL COMMUNICATION, e.g. TELEVISION
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 WU TONGMING
description The invention relates to the technical field of image processing, and discloses a deep learning network processing method, which comprises the following steps: compressing to-be-processed image data into a data packet, uploading the compressed data packet to an image processing unit, and vectorizing the to-be-processed image data by using a data packet-based preprocessing mode by the image processing unit; performing multi-threshold selection of the image data vector by using an Otsu method based on an optimization algorithm to obtain an initial threshold of an image data vector histogram; carrying out image boundary enhancement on the image vector histogram by utilizing an image region boundary enhancement algorithm based on the histogram according to the selected initial threshold value; performing feature extraction on the enhanced image vector data by using a multi-channel sensing network; and performing image reconstruction processing on the extracted image features by using a multi-scale residual networ
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN112991204A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN112991204A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN112991204A3</originalsourceid><addsrcrecordid>eNrjZPB1SU0tUMhJTSzKy8xLV8hLLSnPL8pWKCjKT04tLgYJpaSWZSanKiTmpSjkppZk5KfogNmZuYnpqcjqSvMyS3gYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyKtCGeGc_Q0MjS0tDIwMTR2Ni1AAAysQ2Bg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep learning network processing device and method, and image processing unit</title><source>esp@cenet</source><creator>WU TONGMING</creator><creatorcontrib>WU TONGMING</creatorcontrib><description>The invention relates to the technical field of image processing, and discloses a deep learning network processing method, which comprises the following steps: compressing to-be-processed image data into a data packet, uploading the compressed data packet to an image processing unit, and vectorizing the to-be-processed image data by using a data packet-based preprocessing mode by the image processing unit; performing multi-threshold selection of the image data vector by using an Otsu method based on an optimization algorithm to obtain an initial threshold of an image data vector histogram; carrying out image boundary enhancement on the image vector histogram by utilizing an image region boundary enhancement algorithm based on the histogram according to the selected initial threshold value; performing feature extraction on the enhanced image vector data by using a multi-channel sensing network; and performing image reconstruction processing on the extracted image features by using a multi-scale residual networ</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PICTORIAL COMMUNICATION, e.g. TELEVISION</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=20210618&amp;DB=EPODOC&amp;CC=CN&amp;NR=112991204A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210618&amp;DB=EPODOC&amp;CC=CN&amp;NR=112991204A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU TONGMING</creatorcontrib><title>Deep learning network processing device and method, and image processing unit</title><description>The invention relates to the technical field of image processing, and discloses a deep learning network processing method, which comprises the following steps: compressing to-be-processed image data into a data packet, uploading the compressed data packet to an image processing unit, and vectorizing the to-be-processed image data by using a data packet-based preprocessing mode by the image processing unit; performing multi-threshold selection of the image data vector by using an Otsu method based on an optimization algorithm to obtain an initial threshold of an image data vector histogram; carrying out image boundary enhancement on the image vector histogram by utilizing an image region boundary enhancement algorithm based on the histogram according to the selected initial threshold value; performing feature extraction on the enhanced image vector data by using a multi-channel sensing network; and performing image reconstruction processing on the extracted image features by using a multi-scale residual networ</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRICITY</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PICTORIAL COMMUNICATION, e.g. TELEVISION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPB1SU0tUMhJTSzKy8xLV8hLLSnPL8pWKCjKT04tLgYJpaSWZSanKiTmpSjkppZk5KfogNmZuYnpqcjqSvMyS3gYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyKtCGeGc_Q0MjS0tDIwMTR2Ni1AAAysQ2Bg</recordid><startdate>20210618</startdate><enddate>20210618</enddate><creator>WU TONGMING</creator><scope>EVB</scope></search><sort><creationdate>20210618</creationdate><title>Deep learning network processing device and method, and image processing unit</title><author>WU TONGMING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN112991204A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRICITY</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PICTORIAL COMMUNICATION, e.g. TELEVISION</topic><toplevel>online_resources</toplevel><creatorcontrib>WU TONGMING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU TONGMING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep learning network processing device and method, and image processing unit</title><date>2021-06-18</date><risdate>2021</risdate><abstract>The invention relates to the technical field of image processing, and discloses a deep learning network processing method, which comprises the following steps: compressing to-be-processed image data into a data packet, uploading the compressed data packet to an image processing unit, and vectorizing the to-be-processed image data by using a data packet-based preprocessing mode by the image processing unit; performing multi-threshold selection of the image data vector by using an Otsu method based on an optimization algorithm to obtain an initial threshold of an image data vector histogram; carrying out image boundary enhancement on the image vector histogram by utilizing an image region boundary enhancement algorithm based on the histogram according to the selected initial threshold value; performing feature extraction on the enhanced image vector data by using a multi-channel sensing network; and performing image reconstruction processing on the extracted image features by using a multi-scale residual networ</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN112991204A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PICTORIAL COMMUNICATION, e.g. TELEVISION
title Deep learning network processing device and method, and image processing unit
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T17%3A58%3A30IST&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=WU%20TONGMING&rft.date=2021-06-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN112991204A%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