License plate recognition model generation method, license plate recognition method, device and storage medium
The invention discloses a license plate recognition model generation method. The method comprises the following steps: acquiring a training license plate image, and a feature graph tensor and a text label of the training license plate image; the training license plate image is spliced with the layer...
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 | WANG ZHENPING YUE XUYAO HUANG YUHENG XU TIANSHI ZHANG HUAJUN |
| description | The invention discloses a license plate recognition model generation method. The method comprises the following steps: acquiring a training license plate image, and a feature graph tensor and a text label of the training license plate image; the training license plate image is spliced with the layer as the unit, the processed image and the feature graph tensor of the processed image are determined, and the training license plate is composed of at least one layer of characters; and according to the feature graph tensor and the text label of the processed image, updating the network weight of the training license plate image so as to generate a license plate recognition model. According to the method and the device, the training license plate images can be spliced by taking layers as units, so that unified end-to-end identification on the existing single-layer license plate and double-layer license plate is realized, and the size of the processed image is controlled through the feature graph tensor of the image |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117115797A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117115797A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117115797A3</originalsourceid><addsrcrecordid>eNqNjLEKAjEQRNNYiPoPa69FEAmWcigWYmV_LJcxBnLZkES_34DXClYDb97MXMWrHxALKAWuoIxBXPTVS6RRLAI5RGT-AtSn2A2F35PJsHg3hzhaKlUyO7TK-te4VLMHh4LVlAu1Pp_u3WWLJD1K4vaM2nc3rY3We3Mwx90_zgfe8kLH</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>License plate recognition model generation method, license plate recognition method, device and storage medium</title><source>esp@cenet</source><creator>WANG ZHENPING ; YUE XUYAO ; HUANG YUHENG ; XU TIANSHI ; ZHANG HUAJUN</creator><creatorcontrib>WANG ZHENPING ; YUE XUYAO ; HUANG YUHENG ; XU TIANSHI ; ZHANG HUAJUN</creatorcontrib><description>The invention discloses a license plate recognition model generation method. The method comprises the following steps: acquiring a training license plate image, and a feature graph tensor and a text label of the training license plate image; the training license plate image is spliced with the layer as the unit, the processed image and the feature graph tensor of the processed image are determined, and the training license plate is composed of at least one layer of characters; and according to the feature graph tensor and the text label of the processed image, updating the network weight of the training license plate image so as to generate a license plate recognition model. According to the method and the device, the training license plate images can be spliced by taking layers as units, so that unified end-to-end identification on the existing single-layer license plate and double-layer license plate is realized, and the size of the processed image is controlled through the feature graph tensor of the image</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; 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&date=20231124&DB=EPODOC&CC=CN&NR=117115797A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76517</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231124&DB=EPODOC&CC=CN&NR=117115797A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG ZHENPING</creatorcontrib><creatorcontrib>YUE XUYAO</creatorcontrib><creatorcontrib>HUANG YUHENG</creatorcontrib><creatorcontrib>XU TIANSHI</creatorcontrib><creatorcontrib>ZHANG HUAJUN</creatorcontrib><title>License plate recognition model generation method, license plate recognition method, device and storage medium</title><description>The invention discloses a license plate recognition model generation method. The method comprises the following steps: acquiring a training license plate image, and a feature graph tensor and a text label of the training license plate image; the training license plate image is spliced with the layer as the unit, the processed image and the feature graph tensor of the processed image are determined, and the training license plate is composed of at least one layer of characters; and according to the feature graph tensor and the text label of the processed image, updating the network weight of the training license plate image so as to generate a license plate recognition model. According to the method and the device, the training license plate images can be spliced by taking layers as units, so that unified end-to-end identification on the existing single-layer license plate and double-layer license plate is realized, and the size of the processed image is controlled through the feature graph tensor of the image</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>eNqNjLEKAjEQRNNYiPoPa69FEAmWcigWYmV_LJcxBnLZkES_34DXClYDb97MXMWrHxALKAWuoIxBXPTVS6RRLAI5RGT-AtSn2A2F35PJsHg3hzhaKlUyO7TK-te4VLMHh4LVlAu1Pp_u3WWLJD1K4vaM2nc3rY3We3Mwx90_zgfe8kLH</recordid><startdate>20231124</startdate><enddate>20231124</enddate><creator>WANG ZHENPING</creator><creator>YUE XUYAO</creator><creator>HUANG YUHENG</creator><creator>XU TIANSHI</creator><creator>ZHANG HUAJUN</creator><scope>EVB</scope></search><sort><creationdate>20231124</creationdate><title>License plate recognition model generation method, license plate recognition method, device and storage medium</title><author>WANG ZHENPING ; YUE XUYAO ; HUANG YUHENG ; XU TIANSHI ; ZHANG HUAJUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117115797A3</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG ZHENPING</creatorcontrib><creatorcontrib>YUE XUYAO</creatorcontrib><creatorcontrib>HUANG YUHENG</creatorcontrib><creatorcontrib>XU TIANSHI</creatorcontrib><creatorcontrib>ZHANG HUAJUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG ZHENPING</au><au>YUE XUYAO</au><au>HUANG YUHENG</au><au>XU TIANSHI</au><au>ZHANG HUAJUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>License plate recognition model generation method, license plate recognition method, device and storage medium</title><date>2023-11-24</date><risdate>2023</risdate><abstract>The invention discloses a license plate recognition model generation method. The method comprises the following steps: acquiring a training license plate image, and a feature graph tensor and a text label of the training license plate image; the training license plate image is spliced with the layer as the unit, the processed image and the feature graph tensor of the processed image are determined, and the training license plate is composed of at least one layer of characters; and according to the feature graph tensor and the text label of the processed image, updating the network weight of the training license plate image so as to generate a license plate recognition model. According to the method and the device, the training license plate images can be spliced by taking layers as units, so that unified end-to-end identification on the existing single-layer license plate and double-layer license plate is realized, and the size of the processed image is controlled through the feature graph tensor of the image</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117115797A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | License plate recognition model generation method, license plate recognition method, 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=2025-02-13T07%3A56%3A37IST&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=WANG%20ZHENPING&rft.date=2023-11-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117115797A%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 |