PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS

PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS

The invention relates to a method for automatically classifying objects in two dimensions which are present in an image by using a neural network to recognise the objects. The method consists in recognising the objects with the aid of a neural network which is fed with indicators of the angular conf...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: POTTIER ISABELLE, BUREL GILLES
Format: Patent
Sprache:fre
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 POTTIER ISABELLE
BUREL GILLES
description The invention relates to a method for automatically classifying objects in two dimensions which are present in an image by using a neural network to recognise the objects. The method consists in recognising the objects with the aid of a neural network which is fed with indicators of the angular configurations relating to the polygonal approximation of an outline of the object in question; the class of the object being obtained by interpretation of the states obtained at the output of the neural network. Application to the field of robotics, in particular to robot sight (vision) systems.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_FR2667255B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>FR2667255B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_FR2667255B13</originalsourceid><addsrcrecordid>eNrjZHAICPJ3dnVxVQAiZx_H4GBPN09nxxBPfz8Fx9AQf18gMzAUKKvu7-TlGhKs4AhUGBqh4OLp6-oXDFQVzMPAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4t2CjMzMzI1MTZ0MjYlQAgBPFypB</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS</title><source>esp@cenet</source><creator>POTTIER ISABELLE ; BUREL GILLES</creator><creatorcontrib>POTTIER ISABELLE ; BUREL GILLES</creatorcontrib><description>The invention relates to a method for automatically classifying objects in two dimensions which are present in an image by using a neural network to recognise the objects. The method consists in recognising the objects with the aid of a neural network which is fed with indicators of the angular configurations relating to the polygonal approximation of an outline of the object in question; the class of the object being obtained by interpretation of the states obtained at the output of the neural network. Application to the field of robotics, in particular to robot sight (vision) systems.</description><edition>5</edition><language>fre</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>1994</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=19940909&amp;DB=EPODOC&amp;CC=FR&amp;NR=2667255B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=19940909&amp;DB=EPODOC&amp;CC=FR&amp;NR=2667255B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>POTTIER ISABELLE</creatorcontrib><creatorcontrib>BUREL GILLES</creatorcontrib><title>PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS</title><description>The invention relates to a method for automatically classifying objects in two dimensions which are present in an image by using a neural network to recognise the objects. The method consists in recognising the objects with the aid of a neural network which is fed with indicators of the angular configurations relating to the polygonal approximation of an outline of the object in question; the class of the object being obtained by interpretation of the states obtained at the output of the neural network. Application to the field of robotics, in particular to robot sight (vision) systems.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>1994</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHAICPJ3dnVxVQAiZx_H4GBPN09nxxBPfz8Fx9AQf18gMzAUKKvu7-TlGhKs4AhUGBqh4OLp6-oXDFQVzMPAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4t2CjMzMzI1MTZ0MjYlQAgBPFypB</recordid><startdate>19940909</startdate><enddate>19940909</enddate><creator>POTTIER ISABELLE</creator><creator>BUREL GILLES</creator><scope>EVB</scope></search><sort><creationdate>19940909</creationdate><title>PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS</title><author>POTTIER ISABELLE ; BUREL GILLES</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_FR2667255B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>fre</language><creationdate>1994</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>POTTIER ISABELLE</creatorcontrib><creatorcontrib>BUREL GILLES</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>POTTIER ISABELLE</au><au>BUREL GILLES</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS</title><date>1994-09-09</date><risdate>1994</risdate><abstract>The invention relates to a method for automatically classifying objects in two dimensions which are present in an image by using a neural network to recognise the objects. The method consists in recognising the objects with the aid of a neural network which is fed with indicators of the angular configurations relating to the polygonal approximation of an outline of the object in question; the class of the object being obtained by interpretation of the states obtained at the output of the neural network. Application to the field of robotics, in particular to robot sight (vision) systems.</abstract><edition>5</edition><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language fre
recordid cdi_epo_espacenet_FR2667255B1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title PROCEDE DE CLASSIFICATION AUTOMATIQUE D'OBJETS A DEUX DIMENSIONS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T13%3A06%3A11IST&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=POTTIER%20ISABELLE&rft.date=1994-09-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EFR2667255B1%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