Image Segmentation Using Connected Components for Document Analysis
Identifieur interne : 000778 ( Crin/Corpus ); précédent : 000777; suivant : 000779Image Segmentation Using Connected Components for Document Analysis
Auteurs : S. Collin ; K. TombreSource :
English descriptors
- KwdEn :
Abstract
This paper presents the use of analysing the connected components extracted from the binary image of a document. Such an analysis provides a lot of useful information, and can lead to simple solutions to problems such as the location of the address zone on an envelope or of the bar code on a parcel. The connected components can also be used for segmenting an image into text and graphics parts and extracting graphical primitives from it. We also show that a good structure describing an image as a set of connected components and of relations between then can be a good basis for performing high-level interpretation of a technical document.
Links to Exploration step
CRIN:collin89aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="568">Image Segmentation Using Connected Components for Document Analysis</title></titleStmt><publicationStmt><idno type="RBID">CRIN:collin89a</idno><date when="1989" year="1989">1989</date><idno type="wicri:Area/Crin/Corpus">000778</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Image Segmentation Using Connected Components for Document Analysis</title><author><name sortKey="Collin, S" sort="Collin, S" uniqKey="Collin S" first="S." last="Collin">S. Collin</name></author><author><name sortKey="Tombre, K" sort="Tombre, K" uniqKey="Tombre K" first="K." last="Tombre">K. Tombre</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>connected components</term><term>document processing</term><term>image analysis</term><term>pattern recognition</term><term>segmentation</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2745">This paper presents the use of analysing the connected components extracted from the binary image of a document. Such an analysis provides a lot of useful information, and can lead to simple solutions to problems such as the location of the address zone on an envelope or of the bar code on a parcel. The connected components can also be used for segmenting an image into text and graphics parts and extracting graphical primitives from it. We also show that a good structure describing an image as a set of connected components and of relations between then can be a good basis for performing high-level interpretation of a technical document.</div></front></TEI><BibTex type="inproceedings"><ref>collin89a</ref><crinnumber>89-R-064</crinnumber><category>3</category><equipe>VISION</equipe><author><e>Collin, S.</e><e>Tombre, K.</e></author><title>Image Segmentation Using Connected Components for Document Analysis</title><booktitle>{Proceedings International Symposium {AIPAC}'89 (Advanced Information Processing in Automatic Control), Nancy}</booktitle><year>1989</year><editor>R. Husson</editor><volume>2</volume><pages>166-170</pages><month>jul</month><keywords><e>pattern recognition</e><e>document processing</e><e>image analysis</e><e>connected components</e><e>segmentation</e></keywords><abstract>This paper presents the use of analysing the connected components extracted from the binary image of a document. Such an analysis provides a lot of useful information, and can lead to simple solutions to problems such as the location of the address zone on an envelope or of the bar code on a parcel. The connected components can also be used for segmenting an image into text and graphics parts and extracting graphical primitives from it. We also show that a good structure describing an image as a set of connected components and of relations between then can be a good basis for performing high-level interpretation of a technical document.</abstract></BibTex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000778 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 000778 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Crin
|étape= Corpus
|type= RBID
|clé= CRIN:collin89a
|texte= Image Segmentation Using Connected Components for Document Analysis
}}
| This area was generated with Dilib version V0.6.33. |  |