Video character face replacement method based on deep learning
The invention discloses a video character face replacement method based on deep learning. The method comprises: selecting a certain number of face image data of the replaced persons and the target persons by a worker; Training image input training model, obtaining feature values of the replaced pers...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| 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 | XU JIANJUN LUO ZHIZHONG LOU BAIHONG WANG GUANQING WANG SHANGHUA |
| description | The invention discloses a video character face replacement method based on deep learning. The method comprises: selecting a certain number of face image data of the replaced persons and the target persons by a worker; Training image input training model, obtaining feature values of the replaced person and the target person; more image data are autonomously retrieved and extracted from the Internetaccording to the characteristic values; intercepting a facial part in the image data, combining facial features of an output layer into the overall facial contour to serve as facial expressions, establishing an expression deep learning model, taking the facial expressions as a visible layer, taking the change of the contour corresponding to the facial expressions as a first hidden layer, and taking the emotion features as the output layer; Inputting each frame of image of the to-be-replaced video into the expression deep learning model, analyzing corresponding emotion characteristics, and replacing the facial express |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN109754364A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN109754364A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN109754364A3</originalsourceid><addsrcrecordid>eNrjZLALy0xJzVdIzkgsSkwuSS1SSEtMTlUoSi3IAdK5qXklCrmpJRn5KQpJicWpKQr5eQopqakFCjmpiUV5mXnpPAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbgAaEheakm8s5-hgaW5qYmxmYmjMTFqADF6MEE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Video character face replacement method based on deep learning</title><source>esp@cenet</source><creator>XU JIANJUN ; LUO ZHIZHONG ; LOU BAIHONG ; WANG GUANQING ; WANG SHANGHUA</creator><creatorcontrib>XU JIANJUN ; LUO ZHIZHONG ; LOU BAIHONG ; WANG GUANQING ; WANG SHANGHUA</creatorcontrib><description>The invention discloses a video character face replacement method based on deep learning. The method comprises: selecting a certain number of face image data of the replaced persons and the target persons by a worker; Training image input training model, obtaining feature values of the replaced person and the target person; more image data are autonomously retrieved and extracted from the Internetaccording to the characteristic values; intercepting a facial part in the image data, combining facial features of an output layer into the overall facial contour to serve as facial expressions, establishing an expression deep learning model, taking the facial expressions as a visible layer, taking the change of the contour corresponding to the facial expressions as a first hidden layer, and taking the emotion features as the output layer; Inputting each frame of image of the to-be-replaced video into the expression deep learning model, analyzing corresponding emotion characteristics, and replacing the facial express</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2019</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=20190514&DB=EPODOC&CC=CN&NR=109754364A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190514&DB=EPODOC&CC=CN&NR=109754364A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XU JIANJUN</creatorcontrib><creatorcontrib>LUO ZHIZHONG</creatorcontrib><creatorcontrib>LOU BAIHONG</creatorcontrib><creatorcontrib>WANG GUANQING</creatorcontrib><creatorcontrib>WANG SHANGHUA</creatorcontrib><title>Video character face replacement method based on deep learning</title><description>The invention discloses a video character face replacement method based on deep learning. The method comprises: selecting a certain number of face image data of the replaced persons and the target persons by a worker; Training image input training model, obtaining feature values of the replaced person and the target person; more image data are autonomously retrieved and extracted from the Internetaccording to the characteristic values; intercepting a facial part in the image data, combining facial features of an output layer into the overall facial contour to serve as facial expressions, establishing an expression deep learning model, taking the facial expressions as a visible layer, taking the change of the contour corresponding to the facial expressions as a first hidden layer, and taking the emotion features as the output layer; Inputting each frame of image of the to-be-replaced video into the expression deep learning model, analyzing corresponding emotion characteristics, and replacing the facial express</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>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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLALy0xJzVdIzkgsSkwuSS1SSEtMTlUoSi3IAdK5qXklCrmpJRn5KQpJicWpKQr5eQopqakFCjmpiUV5mXnpPAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbgAaEheakm8s5-hgaW5qYmxmYmjMTFqADF6MEE</recordid><startdate>20190514</startdate><enddate>20190514</enddate><creator>XU JIANJUN</creator><creator>LUO ZHIZHONG</creator><creator>LOU BAIHONG</creator><creator>WANG GUANQING</creator><creator>WANG SHANGHUA</creator><scope>EVB</scope></search><sort><creationdate>20190514</creationdate><title>Video character face replacement method based on deep learning</title><author>XU JIANJUN ; LUO ZHIZHONG ; LOU BAIHONG ; WANG GUANQING ; WANG SHANGHUA</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN109754364A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</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>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>XU JIANJUN</creatorcontrib><creatorcontrib>LUO ZHIZHONG</creatorcontrib><creatorcontrib>LOU BAIHONG</creatorcontrib><creatorcontrib>WANG GUANQING</creatorcontrib><creatorcontrib>WANG SHANGHUA</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XU JIANJUN</au><au>LUO ZHIZHONG</au><au>LOU BAIHONG</au><au>WANG GUANQING</au><au>WANG SHANGHUA</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Video character face replacement method based on deep learning</title><date>2019-05-14</date><risdate>2019</risdate><abstract>The invention discloses a video character face replacement method based on deep learning. The method comprises: selecting a certain number of face image data of the replaced persons and the target persons by a worker; Training image input training model, obtaining feature values of the replaced person and the target person; more image data are autonomously retrieved and extracted from the Internetaccording to the characteristic values; intercepting a facial part in the image data, combining facial features of an output layer into the overall facial contour to serve as facial expressions, establishing an expression deep learning model, taking the facial expressions as a visible layer, taking the change of the contour corresponding to the facial expressions as a first hidden layer, and taking the emotion features as the output layer; Inputting each frame of image of the to-be-replaced video into the expression deep learning model, analyzing corresponding emotion characteristics, and replacing the facial express</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN109754364A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Video character face replacement method 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=2024-12-23T03%3A45%3A06IST&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=XU%20JIANJUN&rft.date=2019-05-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN109754364A%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 |