Rapid animation image generation method, system and device and storage medium

Rapid animation image generation method, system and device and storage medium

The invention discloses a rapid animation image generation method, system and device and a storage medium, and the method comprises the steps: carrying out the fixed square segmentation of an image, and generating rectangular superpixels; calculating a color mean value and a variance of the superpix...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WEN DILONG, ZHENG YUNPING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
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 WEN DILONG
ZHENG YUNPING
description The invention discloses a rapid animation image generation method, system and device and a storage medium, and the method comprises the steps: carrying out the fixed square segmentation of an image, and generating rectangular superpixels; calculating a color mean value and a variance of the superpixels, performing similarity comparison on each rectangular superpixel and an adjacent superpixel, and combining the similar superpixels; calculating various characteristics of each region; secondly, mapping a region set to a new space which is more beneficial to clustering by using segmented flat embedding, and merging similar regions by using a clustering algorithm through setting region number limitation to obtain different results; and finally, averaging the pixel color values in the region to obtain an animation image of the original image. According to the method, the requirement that a large amount of fine annotations are needed for training is avoided by using an unsupervised algorithm, and the calculation co
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114549703A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114549703A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114549703A3</originalsourceid><addsrcrecordid>eNrjZPANSizITFFIzMvMTSzJzM9TANLpqQrpqXmpRRCB3NSSjPwUHYXiyuKS1FygyhSFlNSyzORUMLO4JL8IpCE3NSWzNJeHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmA80tiXf2MzQ0MTWxNDcwdjQmRg0AvsQ19Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Rapid animation image generation method, system and device and storage medium</title><source>esp@cenet</source><creator>WEN DILONG ; ZHENG YUNPING</creator><creatorcontrib>WEN DILONG ; ZHENG YUNPING</creatorcontrib><description>The invention discloses a rapid animation image generation method, system and device and a storage medium, and the method comprises the steps: carrying out the fixed square segmentation of an image, and generating rectangular superpixels; calculating a color mean value and a variance of the superpixels, performing similarity comparison on each rectangular superpixel and an adjacent superpixel, and combining the similar superpixels; calculating various characteristics of each region; secondly, mapping a region set to a new space which is more beneficial to clustering by using segmented flat embedding, and merging similar regions by using a clustering algorithm through setting region number limitation to obtain different results; and finally, averaging the pixel color values in the region to obtain an animation image of the original image. According to the method, the requirement that a large amount of fine annotations are needed for training is avoided by using an unsupervised algorithm, and the calculation co</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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&amp;date=20220527&amp;DB=EPODOC&amp;CC=CN&amp;NR=114549703A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220527&amp;DB=EPODOC&amp;CC=CN&amp;NR=114549703A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WEN DILONG</creatorcontrib><creatorcontrib>ZHENG YUNPING</creatorcontrib><title>Rapid animation image generation method, system and device and storage medium</title><description>The invention discloses a rapid animation image generation method, system and device and a storage medium, and the method comprises the steps: carrying out the fixed square segmentation of an image, and generating rectangular superpixels; calculating a color mean value and a variance of the superpixels, performing similarity comparison on each rectangular superpixel and an adjacent superpixel, and combining the similar superpixels; calculating various characteristics of each region; secondly, mapping a region set to a new space which is more beneficial to clustering by using segmented flat embedding, and merging similar regions by using a clustering algorithm through setting region number limitation to obtain different results; and finally, averaging the pixel color values in the region to obtain an animation image of the original image. According to the method, the requirement that a large amount of fine annotations are needed for training is avoided by using an unsupervised algorithm, and the calculation co</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</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>eNrjZPANSizITFFIzMvMTSzJzM9TANLpqQrpqXmpRRCB3NSSjPwUHYXiyuKS1FygyhSFlNSyzORUMLO4JL8IpCE3NSWzNJeHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmA80tiXf2MzQ0MTWxNDcwdjQmRg0AvsQ19Q</recordid><startdate>20220527</startdate><enddate>20220527</enddate><creator>WEN DILONG</creator><creator>ZHENG YUNPING</creator><scope>EVB</scope></search><sort><creationdate>20220527</creationdate><title>Rapid animation image generation method, system and device and storage medium</title><author>WEN DILONG ; ZHENG YUNPING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114549703A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>WEN DILONG</creatorcontrib><creatorcontrib>ZHENG YUNPING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WEN DILONG</au><au>ZHENG YUNPING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Rapid animation image generation method, system and device and storage medium</title><date>2022-05-27</date><risdate>2022</risdate><abstract>The invention discloses a rapid animation image generation method, system and device and a storage medium, and the method comprises the steps: carrying out the fixed square segmentation of an image, and generating rectangular superpixels; calculating a color mean value and a variance of the superpixels, performing similarity comparison on each rectangular superpixel and an adjacent superpixel, and combining the similar superpixels; calculating various characteristics of each region; secondly, mapping a region set to a new space which is more beneficial to clustering by using segmented flat embedding, and merging similar regions by using a clustering algorithm through setting region number limitation to obtain different results; and finally, averaging the pixel color values in the region to obtain an animation image of the original image. According to the method, the requirement that a large amount of fine annotations are needed for training is avoided by using an unsupervised algorithm, and the calculation co</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN114549703A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
title Rapid animation image generation method, system and device and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T16%3A02%3A42IST&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=WEN%20DILONG&rft.date=2022-05-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114549703A%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