Image processing method, network model training method, equipment and medium
The invention provides an image processing method, a network model training method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image processing method comprises the following steps: extracting semantic features of an obtained input image to...
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 | LIU ZHENG TANG WEI FAN SHAOJIE ZHU BAOHUI GUO XIN ZHAO WEI FEI DONG YANG HAIBIN JIA WUCAI LIU LIN LUO JING |
| description | The invention provides an image processing method, a network model training method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image processing method comprises the following steps: extracting semantic features of an obtained input image to obtain a feature map corresponding to the input image; performing position prediction on the feature map corresponding to the input image to obtain a to-be-processed image; performing grid motion prediction on the to-be-processed image based on the residual progressive regression network model to obtain a to-be-matched image; and matching the to-be-matched image with a preset grid to obtain a target image. According to the method, deviation information in a to-be-processed image is adjusted based on a residual error progressive regression network model, the consistency of image content is improved, and abnormalities such as irregular boundaries and picture distortion occurring in image splicing are reduced, so tha |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117237579A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117237579A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117237579A3</originalsourceid><addsrcrecordid>eNrjZPDxzE1MT1UoKMpPTi0uzsxLV8hNLcnIT9FRyEstKc8vylbIzU9JzVEoKUrMzEOWTi0szSzITc0rUUjMSwGKpmSW5vIwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsTkVKCp8c5-hobmRsbmpuaWjsbEqAEAoFE15A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Image processing method, network model training method, equipment and medium</title><source>esp@cenet</source><creator>LIU ZHENG ; TANG WEI ; FAN SHAOJIE ; ZHU BAOHUI ; GUO XIN ; ZHAO WEI ; FEI DONG ; YANG HAIBIN ; JIA WUCAI ; LIU LIN ; LUO JING</creator><creatorcontrib>LIU ZHENG ; TANG WEI ; FAN SHAOJIE ; ZHU BAOHUI ; GUO XIN ; ZHAO WEI ; FEI DONG ; YANG HAIBIN ; JIA WUCAI ; LIU LIN ; LUO JING</creatorcontrib><description>The invention provides an image processing method, a network model training method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image processing method comprises the following steps: extracting semantic features of an obtained input image to obtain a feature map corresponding to the input image; performing position prediction on the feature map corresponding to the input image to obtain a to-be-processed image; performing grid motion prediction on the to-be-processed image based on the residual progressive regression network model to obtain a to-be-matched image; and matching the to-be-matched image with a preset grid to obtain a target image. According to the method, deviation information in a to-be-processed image is adjusted based on a residual error progressive regression network model, the consistency of image content is improved, and abnormalities such as irregular boundaries and picture distortion occurring in image splicing are reduced, so tha</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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&date=20231215&DB=EPODOC&CC=CN&NR=117237579A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231215&DB=EPODOC&CC=CN&NR=117237579A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU ZHENG</creatorcontrib><creatorcontrib>TANG WEI</creatorcontrib><creatorcontrib>FAN SHAOJIE</creatorcontrib><creatorcontrib>ZHU BAOHUI</creatorcontrib><creatorcontrib>GUO XIN</creatorcontrib><creatorcontrib>ZHAO WEI</creatorcontrib><creatorcontrib>FEI DONG</creatorcontrib><creatorcontrib>YANG HAIBIN</creatorcontrib><creatorcontrib>JIA WUCAI</creatorcontrib><creatorcontrib>LIU LIN</creatorcontrib><creatorcontrib>LUO JING</creatorcontrib><title>Image processing method, network model training method, equipment and medium</title><description>The invention provides an image processing method, a network model training method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image processing method comprises the following steps: extracting semantic features of an obtained input image to obtain a feature map corresponding to the input image; performing position prediction on the feature map corresponding to the input image to obtain a to-be-processed image; performing grid motion prediction on the to-be-processed image based on the residual progressive regression network model to obtain a to-be-matched image; and matching the to-be-matched image with a preset grid to obtain a target image. According to the method, deviation information in a to-be-processed image is adjusted based on a residual error progressive regression network model, the consistency of image content is improved, and abnormalities such as irregular boundaries and picture distortion occurring in image splicing are reduced, so tha</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPDxzE1MT1UoKMpPTi0uzsxLV8hNLcnIT9FRyEstKc8vylbIzU9JzVEoKUrMzEOWTi0szSzITc0rUUjMSwGKpmSW5vIwsKYl5hSn8kJpbgZFN9cQZw_d1IL8-NTigsTkVKCp8c5-hobmRsbmpuaWjsbEqAEAoFE15A</recordid><startdate>20231215</startdate><enddate>20231215</enddate><creator>LIU ZHENG</creator><creator>TANG WEI</creator><creator>FAN SHAOJIE</creator><creator>ZHU BAOHUI</creator><creator>GUO XIN</creator><creator>ZHAO WEI</creator><creator>FEI DONG</creator><creator>YANG HAIBIN</creator><creator>JIA WUCAI</creator><creator>LIU LIN</creator><creator>LUO JING</creator><scope>EVB</scope></search><sort><creationdate>20231215</creationdate><title>Image processing method, network model training method, equipment and medium</title><author>LIU ZHENG ; TANG WEI ; FAN SHAOJIE ; ZHU BAOHUI ; GUO XIN ; ZHAO WEI ; FEI DONG ; YANG HAIBIN ; JIA WUCAI ; LIU LIN ; LUO JING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117237579A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LIU ZHENG</creatorcontrib><creatorcontrib>TANG WEI</creatorcontrib><creatorcontrib>FAN SHAOJIE</creatorcontrib><creatorcontrib>ZHU BAOHUI</creatorcontrib><creatorcontrib>GUO XIN</creatorcontrib><creatorcontrib>ZHAO WEI</creatorcontrib><creatorcontrib>FEI DONG</creatorcontrib><creatorcontrib>YANG HAIBIN</creatorcontrib><creatorcontrib>JIA WUCAI</creatorcontrib><creatorcontrib>LIU LIN</creatorcontrib><creatorcontrib>LUO JING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU ZHENG</au><au>TANG WEI</au><au>FAN SHAOJIE</au><au>ZHU BAOHUI</au><au>GUO XIN</au><au>ZHAO WEI</au><au>FEI DONG</au><au>YANG HAIBIN</au><au>JIA WUCAI</au><au>LIU LIN</au><au>LUO JING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Image processing method, network model training method, equipment and medium</title><date>2023-12-15</date><risdate>2023</risdate><abstract>The invention provides an image processing method, a network model training method, electronic equipment and a storage medium, and relates to the technical field of image processing. The image processing method comprises the following steps: extracting semantic features of an obtained input image to obtain a feature map corresponding to the input image; performing position prediction on the feature map corresponding to the input image to obtain a to-be-processed image; performing grid motion prediction on the to-be-processed image based on the residual progressive regression network model to obtain a to-be-matched image; and matching the to-be-matched image with a preset grid to obtain a target image. According to the method, deviation information in a to-be-processed image is adjusted based on a residual error progressive regression network model, the consistency of image content is improved, and abnormalities such as irregular boundaries and picture distortion occurring in image splicing are reduced, so tha</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117237579A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Image processing method, network model training method, equipment and medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T05%3A37%3A18IST&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=LIU%20ZHENG&rft.date=2023-12-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117237579A%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 |