License plate recognition training data synthesis method

License plate recognition training data synthesis method

The invention relates to a license plate recognition training data synthesis method. The method comprises the following steps: S1, creating a background image; traversing each pixel in the backgroundimage, wherein each pixel has a random probability p1 to generate different basic element patterns on...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WENG ZENGREN, SHI TIANYONG
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 WENG ZENGREN
SHI TIANYONG
description The invention relates to a license plate recognition training data synthesis method. The method comprises the following steps: S1, creating a background image; traversing each pixel in the backgroundimage, wherein each pixel has a random probability p1 to generate different basic element patterns on the background image; S2, randomly selecting a vehicle body image from the vehicle body image database, randomly cutting out a local vehicle body image from the selected vehicle body image, and combining the background image and the local vehicle body image to form a composite image; and S3, randomly selecting an area on the composite image to draw a license plate image. The license plate recognition training data synthesis method has the advantages of being economical, efficient and large inamount. The problems that a traditional manual data collection method consumes manpower and material resources and is low in efficiency are solved. Infinite training data can be quickly provided for alicense plate recognition
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110399874A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110399874A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110399874A3</originalsourceid><addsrcrecordid>eNrjZLDwyUxOzStOVSjISSxJVShKTc5Pz8ssyczPUygpSszMy8xLV0hJLElUKK7MK8lILc4sVshNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYlAY1NL4p39DA0NjC0tLcxNHI2JUQMAOp8uzg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>License plate recognition training data synthesis method</title><source>esp@cenet</source><creator>WENG ZENGREN ; SHI TIANYONG</creator><creatorcontrib>WENG ZENGREN ; SHI TIANYONG</creatorcontrib><description>The invention relates to a license plate recognition training data synthesis method. The method comprises the following steps: S1, creating a background image; traversing each pixel in the backgroundimage, wherein each pixel has a random probability p1 to generate different basic element patterns on the background image; S2, randomly selecting a vehicle body image from the vehicle body image database, randomly cutting out a local vehicle body image from the selected vehicle body image, and combining the background image and the local vehicle body image to form a composite image; and S3, randomly selecting an area on the composite image to draw a license plate image. The license plate recognition training data synthesis method has the advantages of being economical, efficient and large inamount. The problems that a traditional manual data collection method consumes manpower and material resources and is low in efficiency are solved. Infinite training data can be quickly provided for alicense plate recognition</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>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&amp;date=20191101&amp;DB=EPODOC&amp;CC=CN&amp;NR=110399874A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20191101&amp;DB=EPODOC&amp;CC=CN&amp;NR=110399874A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WENG ZENGREN</creatorcontrib><creatorcontrib>SHI TIANYONG</creatorcontrib><title>License plate recognition training data synthesis method</title><description>The invention relates to a license plate recognition training data synthesis method. The method comprises the following steps: S1, creating a background image; traversing each pixel in the backgroundimage, wherein each pixel has a random probability p1 to generate different basic element patterns on the background image; S2, randomly selecting a vehicle body image from the vehicle body image database, randomly cutting out a local vehicle body image from the selected vehicle body image, and combining the background image and the local vehicle body image to form a composite image; and S3, randomly selecting an area on the composite image to draw a license plate image. The license plate recognition training data synthesis method has the advantages of being economical, efficient and large inamount. The problems that a traditional manual data collection method consumes manpower and material resources and is low in efficiency are solved. Infinite training data can be quickly provided for alicense plate recognition</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDwyUxOzStOVSjISSxJVShKTc5Pz8ssyczPUygpSszMy8xLV0hJLElUKK7MK8lILc4sVshNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYlAY1NL4p39DA0NjC0tLcxNHI2JUQMAOp8uzg</recordid><startdate>20191101</startdate><enddate>20191101</enddate><creator>WENG ZENGREN</creator><creator>SHI TIANYONG</creator><scope>EVB</scope></search><sort><creationdate>20191101</creationdate><title>License plate recognition training data synthesis method</title><author>WENG ZENGREN ; SHI TIANYONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110399874A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</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>WENG ZENGREN</creatorcontrib><creatorcontrib>SHI TIANYONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WENG ZENGREN</au><au>SHI TIANYONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>License plate recognition training data synthesis method</title><date>2019-11-01</date><risdate>2019</risdate><abstract>The invention relates to a license plate recognition training data synthesis method. The method comprises the following steps: S1, creating a background image; traversing each pixel in the backgroundimage, wherein each pixel has a random probability p1 to generate different basic element patterns on the background image; S2, randomly selecting a vehicle body image from the vehicle body image database, randomly cutting out a local vehicle body image from the selected vehicle body image, and combining the background image and the local vehicle body image to form a composite image; and S3, randomly selecting an area on the composite image to draw a license plate image. The license plate recognition training data synthesis method has the advantages of being economical, efficient and large inamount. The problems that a traditional manual data collection method consumes manpower and material resources and is low in efficiency are solved. Infinite training data can be quickly provided for alicense plate recognition</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN110399874A
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 License plate recognition training data synthesis method
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T19%3A06%3A53IST&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=WENG%20ZENGREN&rft.date=2019-11-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110399874A%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