IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

This application discloses a method, apparatus, device, and storage medium for training an image processing model, and relates to the field of artificial intelligence technologies. The method includes: obtaining a predicted recognition result of a first sample face image and first occlusion indicati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: QIU, Haibo, LI, Zhifeng, GONG, Dihong, LIU, Wei
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
CALCULATING
COMPUTING
COUNTING
PHYSICS
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 QIU, Haibo
LI, Zhifeng
GONG, Dihong
LIU, Wei
description This application discloses a method, apparatus, device, and storage medium for training an image processing model, and relates to the field of artificial intelligence technologies. The method includes: obtaining a predicted recognition result of a first sample face image and first occlusion indication information based on an image processing model, the first occlusion indication information being used for indicating an image feature of a face occlusion area of the first sample face image; obtaining a recognition error based on the predicted recognition result and a target recognition result corresponding to the first sample face image; obtaining a classification error based on the first occlusion indication information and a target occlusion pattern corresponding to the first sample face image, an occlusion pattern of the first sample face image being used for indicating a position and a size of the face occlusion area; and updating a model parameter of the image processing model according to the recognition error and the classification error.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4099217A4</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4099217A4</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4099217A43</originalsourceid><addsrcrecordid>eNrjZAjw9HV0d1UICPJ3dg0O9vRzV_D1d3H1UQgJcvT0A3NdQzz8XRQc_YA4IMAxyDEkNFhHwcU1zNPZVQcsHBziHwQyw9fVxTPUl4eBNS0xpziVF0pzMyi4uYY4e-imFuTHpxYXJCan5qWWxLsGmBhYWhoZmjuaGBOhBADpmi5I</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM</title><source>esp@cenet</source><creator>QIU, Haibo ; LI, Zhifeng ; GONG, Dihong ; LIU, Wei</creator><creatorcontrib>QIU, Haibo ; LI, Zhifeng ; GONG, Dihong ; LIU, Wei</creatorcontrib><description>This application discloses a method, apparatus, device, and storage medium for training an image processing model, and relates to the field of artificial intelligence technologies. The method includes: obtaining a predicted recognition result of a first sample face image and first occlusion indication information based on an image processing model, the first occlusion indication information being used for indicating an image feature of a face occlusion area of the first sample face image; obtaining a recognition error based on the predicted recognition result and a target recognition result corresponding to the first sample face image; obtaining a classification error based on the first occlusion indication information and a target occlusion pattern corresponding to the first sample face image, an occlusion pattern of the first sample face image being used for indicating a position and a size of the face occlusion area; and updating a model parameter of the image processing model according to the recognition error and the classification error.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</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=20230621&amp;DB=EPODOC&amp;CC=EP&amp;NR=4099217A4$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230621&amp;DB=EPODOC&amp;CC=EP&amp;NR=4099217A4$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>QIU, Haibo</creatorcontrib><creatorcontrib>LI, Zhifeng</creatorcontrib><creatorcontrib>GONG, Dihong</creatorcontrib><creatorcontrib>LIU, Wei</creatorcontrib><title>IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM</title><description>This application discloses a method, apparatus, device, and storage medium for training an image processing model, and relates to the field of artificial intelligence technologies. The method includes: obtaining a predicted recognition result of a first sample face image and first occlusion indication information based on an image processing model, the first occlusion indication information being used for indicating an image feature of a face occlusion area of the first sample face image; obtaining a recognition error based on the predicted recognition result and a target recognition result corresponding to the first sample face image; obtaining a classification error based on the first occlusion indication information and a target occlusion pattern corresponding to the first sample face image, an occlusion pattern of the first sample face image being used for indicating a position and a size of the face occlusion area; and updating a model parameter of the image processing model according to the recognition error and the classification error.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZAjw9HV0d1UICPJ3dg0O9vRzV_D1d3H1UQgJcvT0A3NdQzz8XRQc_YA4IMAxyDEkNFhHwcU1zNPZVQcsHBziHwQyw9fVxTPUl4eBNS0xpziVF0pzMyi4uYY4e-imFuTHpxYXJCan5qWWxLsGmBhYWhoZmjuaGBOhBADpmi5I</recordid><startdate>20230621</startdate><enddate>20230621</enddate><creator>QIU, Haibo</creator><creator>LI, Zhifeng</creator><creator>GONG, Dihong</creator><creator>LIU, Wei</creator><scope>EVB</scope></search><sort><creationdate>20230621</creationdate><title>IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM</title><author>QIU, Haibo ; LI, Zhifeng ; GONG, Dihong ; LIU, Wei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4099217A43</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>QIU, Haibo</creatorcontrib><creatorcontrib>LI, Zhifeng</creatorcontrib><creatorcontrib>GONG, Dihong</creatorcontrib><creatorcontrib>LIU, Wei</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>QIU, Haibo</au><au>LI, Zhifeng</au><au>GONG, Dihong</au><au>LIU, Wei</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM</title><date>2023-06-21</date><risdate>2023</risdate><abstract>This application discloses a method, apparatus, device, and storage medium for training an image processing model, and relates to the field of artificial intelligence technologies. The method includes: obtaining a predicted recognition result of a first sample face image and first occlusion indication information based on an image processing model, the first occlusion indication information being used for indicating an image feature of a face occlusion area of the first sample face image; obtaining a recognition error based on the predicted recognition result and a target recognition result corresponding to the first sample face image; obtaining a classification error based on the first occlusion indication information and a target occlusion pattern corresponding to the first sample face image, an occlusion pattern of the first sample face image being used for indicating a position and a size of the face occlusion area; and updating a model parameter of the image processing model according to the recognition error and the classification error.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4099217A4
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title IMAGE PROCESSING MODEL TRAINING METHOD AND APPARATUS, 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=2025-01-14T16%3A45%3A51IST&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=QIU,%20Haibo&rft.date=2023-06-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4099217A4%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