TWI751593B

The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing,...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	YI, SHUAI, ZHOU, XINI, TIAN, MAO-QING, ZHOU, DONG-ZHAN, OU, YANG-WAN-LI
Format:	Patent
Sprache:	chi
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
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	YI, SHUAI ZHOU, XINI TIAN, MAO-QING ZHOU, DONG-ZHAN OU, YANG-WAN-LI
description	The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_TWI751593BB</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>TWI751593BB</sourcerecordid><originalsourceid>FETCH-epo_espacenet_TWI751593BB3</originalsourceid><addsrcrecordid>eNrjZOAKCfc0NzU0tTR24mFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8QgNTsZEKAEADD4biw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>TWI751593B</title><source>esp@cenet</source><creator>YI, SHUAI ; ZHOU, XINI ; TIAN, MAO-QING ; ZHOU, DONG-ZHAN ; OU, YANG-WAN-LI</creator><creatorcontrib>YI, SHUAI ; ZHOU, XINI ; TIAN, MAO-QING ; ZHOU, DONG-ZHAN ; OU, YANG-WAN-LI</creatorcontrib><description>The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.</description><language>chi</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</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&date=20220101&DB=EPODOC&CC=TW&NR=I751593B$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220101&DB=EPODOC&CC=TW&NR=I751593B$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YI, SHUAI</creatorcontrib><creatorcontrib>ZHOU, XINI</creatorcontrib><creatorcontrib>TIAN, MAO-QING</creatorcontrib><creatorcontrib>ZHOU, DONG-ZHAN</creatorcontrib><creatorcontrib>OU, YANG-WAN-LI</creatorcontrib><title>TWI751593B</title><description>The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZOAKCfc0NzU0tTR24mFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8QgNTsZEKAEADD4biw</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>YI, SHUAI</creator><creator>ZHOU, XINI</creator><creator>TIAN, MAO-QING</creator><creator>ZHOU, DONG-ZHAN</creator><creator>OU, YANG-WAN-LI</creator><scope>EVB</scope></search><sort><creationdate>20220101</creationdate><title>TWI751593B</title><author>YI, SHUAI ; ZHOU, XINI ; TIAN, MAO-QING ; ZHOU, DONG-ZHAN ; OU, YANG-WAN-LI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_TWI751593BB3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>YI, SHUAI</creatorcontrib><creatorcontrib>ZHOU, XINI</creatorcontrib><creatorcontrib>TIAN, MAO-QING</creatorcontrib><creatorcontrib>ZHOU, DONG-ZHAN</creatorcontrib><creatorcontrib>OU, YANG-WAN-LI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YI, SHUAI</au><au>ZHOU, XINI</au><au>TIAN, MAO-QING</au><au>ZHOU, DONG-ZHAN</au><au>OU, YANG-WAN-LI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>TWI751593B</title><date>2022-01-01</date><risdate>2022</risdate><abstract>The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	chi
recordid	cdi_epo_espacenet_TWI751593BB
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
title	TWI751593B
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T03%3A40%3A47IST&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=YI,%20SHUAI&rft.date=2022-01-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ETWI751593BB%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