High power LED lighting for CNN based image processing at frame rates of 10 kHz

CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the insp...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Blug, A, Jetter, V, Strohm, P, Carl, D, Höfler, H
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	cellular neural network (CNN) CNN image processing light-emitting diode machine vision
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	Blug, A Jetter, V Strohm, P Carl, D Höfler, H
description	CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the inspection of cylindrical metallic surfaces on aluminum wires. Frame rates of 10 kHz and exposure times of 20 µs have been achieved so far.
doi_str_mv	10.1109/CNNA.2010.5430333
format	Conference Proceeding
fullrecord	<record><control><sourceid>fraunhofer_E3A</sourceid><recordid>TN_cdi_fraunhofer_primary_oai_fraunhofer_de_N_134388</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_fraunhofer_de_N_134388</sourcerecordid><originalsourceid>FETCH-fraunhofer_primary_oai_fraunhofer_de_N_1343883</originalsourceid><addsrcrecordid>eNqdjL0OgjAUhbs4GPUB3O4LiK3FBEeDGAaDi3tT5BYagZJbjNGntyYOzk4n3_ljbCl4JATfrdOi2EcbHnAbSy6lnLJzbusGBvdAglN2gDbgaPsajCMIfSi1xwpsp2uEgdwVvf_EegRDukMgPaIHZ0BwuOWvOZsY3XpcfHXG4mN2SfNVaN_7xhkkNVC4o6dy2qofu0JVKCFjmSTyz9kb2chLmw</addsrcrecordid><sourcetype>Institutional Repository</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>High power LED lighting for CNN based image processing at frame rates of 10 kHz</title><source>Fraunhofer-ePrints</source><creator>Blug, A ; Jetter, V ; Strohm, P ; Carl, D ; Höfler, H</creator><creatorcontrib>Blug, A ; Jetter, V ; Strohm, P ; Carl, D ; Höfler, H</creatorcontrib><description>CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the inspection of cylindrical metallic surfaces on aluminum wires. Frame rates of 10 kHz and exposure times of 20 µs have been achieved so far.</description><identifier>DOI: 10.1109/CNNA.2010.5430333</identifier><language>eng</language><subject>cellular neural network (CNN) ; CNN ; image processing ; light-emitting diode ; machine vision</subject><creationdate>2010</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,315,780,4050,27860</link.rule.ids><linktorsrc>$$Uhttp://publica.fraunhofer.de/documents/N-134388.html$$EView_record_in_Fraunhofer-Gesellschaft$$FView_record_in_$$GFraunhofer-Gesellschaft$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Blug, A</creatorcontrib><creatorcontrib>Jetter, V</creatorcontrib><creatorcontrib>Strohm, P</creatorcontrib><creatorcontrib>Carl, D</creatorcontrib><creatorcontrib>Höfler, H</creatorcontrib><title>High power LED lighting for CNN based image processing at frame rates of 10 kHz</title><description>CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the inspection of cylindrical metallic surfaces on aluminum wires. Frame rates of 10 kHz and exposure times of 20 µs have been achieved so far.</description><subject>cellular neural network (CNN)</subject><subject>CNN</subject><subject>image processing</subject><subject>light-emitting diode</subject><subject>machine vision</subject><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>AFSUM</sourceid><sourceid>E3A</sourceid><recordid>eNqdjL0OgjAUhbs4GPUB3O4LiK3FBEeDGAaDi3tT5BYagZJbjNGntyYOzk4n3_ljbCl4JATfrdOi2EcbHnAbSy6lnLJzbusGBvdAglN2gDbgaPsajCMIfSi1xwpsp2uEgdwVvf_EegRDukMgPaIHZ0BwuOWvOZsY3XpcfHXG4mN2SfNVaN_7xhkkNVC4o6dy2qofu0JVKCFjmSTyz9kb2chLmw</recordid><startdate>2010</startdate><enddate>2010</enddate><creator>Blug, A</creator><creator>Jetter, V</creator><creator>Strohm, P</creator><creator>Carl, D</creator><creator>Höfler, H</creator><scope>AFSUM</scope><scope>E3A</scope></search><sort><creationdate>2010</creationdate><title>High power LED lighting for CNN based image processing at frame rates of 10 kHz</title><author>Blug, A ; Jetter, V ; Strohm, P ; Carl, D ; Höfler, H</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-fraunhofer_primary_oai_fraunhofer_de_N_1343883</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>cellular neural network (CNN)</topic><topic>CNN</topic><topic>image processing</topic><topic>light-emitting diode</topic><topic>machine vision</topic><toplevel>online_resources</toplevel><creatorcontrib>Blug, A</creatorcontrib><creatorcontrib>Jetter, V</creatorcontrib><creatorcontrib>Strohm, P</creatorcontrib><creatorcontrib>Carl, D</creatorcontrib><creatorcontrib>Höfler, H</creatorcontrib><collection>Fraunhofer-ePrints - FT</collection><collection>Fraunhofer-ePrints</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Blug, A</au><au>Jetter, V</au><au>Strohm, P</au><au>Carl, D</au><au>Höfler, H</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>High power LED lighting for CNN based image processing at frame rates of 10 kHz</atitle><date>2010</date><risdate>2010</risdate><abstract>CNN based cameras are able to process images in the kHz range in machine vision systems, as demonstrated for the closed loop control of laser welding processes. Other applications do not benefit from a comparable light source. This paper reports the current state of a LED based lighting for the inspection of cylindrical metallic surfaces on aluminum wires. Frame rates of 10 kHz and exposure times of 20 µs have been achieved so far.</abstract><doi>10.1109/CNNA.2010.5430333</doi><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	DOI: 10.1109/CNNA.2010.5430333
ispartof
issn
language	eng
recordid	cdi_fraunhofer_primary_oai_fraunhofer_de_N_134388
source	Fraunhofer-ePrints
subjects	cellular neural network (CNN) CNN image processing light-emitting diode machine vision
title	High power LED lighting for CNN based image processing at frame rates of 10 kHz
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T03%3A04%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-fraunhofer_E3A&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=High%20power%20LED%20lighting%20for%20CNN%20based%20image%20processing%20at%20frame%20rates%20of%2010%20kHz&rft.au=Blug,%20A&rft.date=2010&rft_id=info:doi/10.1109/CNNA.2010.5430333&rft_dat=%3Cfraunhofer_E3A%3Eoai_fraunhofer_de_N_134388%3C/fraunhofer_E3A%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