Vector-based segmentation of text connected to graphics in engineering drawings
Identifieur interne : 002A07 ( Main/Merge ); précédent : 002A06; suivant : 002A08Vector-based segmentation of text connected to graphics in engineering drawings
Auteurs : D. Dori [Israël] ; L. Wenyin [Israël]Source :
- Lecture notes in computer science [ 0302-9743 ] ; 1996.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
A method for segmentation of text that may be connected to graphics in engineering drawings is presented. It consists of three steps : growing individual characterbox regions, using a recursive merging scheme by stroke linking ; merging the detected characterboxes into a textbox and determining its orientation ; and re-segmenting the textbox back into the refined characterbox that can be input to an OCR subsystem. The method can segment dimensioning text as well as other classes of text. It handles both isolated and touching characters, aligned at any slant. The capability of segmenting characters that touch either themselves or graphics, which is an important feature in handling real life drawings, is obtained by focusing on intermediate vector information rather that on the raw pixel data. We present the details of the algorithm and show both successful and unsuccessful examples from an experimental set of 36 dimensioning textboxes, in which 94% segmentation rate was achieved with 3% false alarm rate.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000973
- to stream PascalFrancis, to step Curation: 000A25
- to stream PascalFrancis, to step Checkpoint: 000920
Links to Exploration step
Pascal:97-0020290Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Vector-based segmentation of text connected to graphics in engineering drawings</title>
<author><name sortKey="Dori, D" sort="Dori, D" uniqKey="Dori D" first="D." last="Dori">D. Dori</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</s1>
<s2>Haifa 32000</s2>
<s3>ISR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Israël</country>
<wicri:noRegion>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Wenyin, L" sort="Wenyin, L" uniqKey="Wenyin L" first="L." last="Wenyin">L. Wenyin</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</s1>
<s2>Haifa 32000</s2>
<s3>ISR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Israël</country>
<wicri:noRegion>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">97-0020290</idno>
<date when="1996">1996</date>
<idno type="stanalyst">PASCAL 97-0020290 INIST</idno>
<idno type="RBID">Pascal:97-0020290</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000973</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000A25</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000920</idno>
<idno type="wicri:doubleKey">0302-9743:1996:Dori D:vector:based:segmentation</idno>
<idno type="wicri:Area/Main/Merge">002A07</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Vector-based segmentation of text connected to graphics in engineering drawings</title>
<author><name sortKey="Dori, D" sort="Dori, D" uniqKey="Dori D" first="D." last="Dori">D. Dori</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</s1>
<s2>Haifa 32000</s2>
<s3>ISR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Israël</country>
<wicri:noRegion>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Wenyin, L" sort="Wenyin, L" uniqKey="Wenyin L" first="L." last="Wenyin">L. Wenyin</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</s1>
<s2>Haifa 32000</s2>
<s3>ISR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Israël</country>
<wicri:noRegion>Faculty of Industrial Engineering and Management Technion-Israel Institute of Technology</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="1996">1996</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term>
<term>Computer aided design</term>
<term>Engineering</term>
<term>Graphics</term>
<term>Industrial drawing</term>
<term>Segmentation</term>
<term>Text</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance caractère</term>
<term>Représentation graphique</term>
<term>Segmentation</term>
<term>Texte</term>
<term>Ingénierie</term>
<term>Conception assistée</term>
<term>Dessin industriel</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">A method for segmentation of text that may be connected to graphics in engineering drawings is presented. It consists of three steps : growing individual characterbox regions, using a recursive merging scheme by stroke linking ; merging the detected characterboxes into a textbox and determining its orientation ; and re-segmenting the textbox back into the refined characterbox that can be input to an OCR subsystem. The method can segment dimensioning text as well as other classes of text. It handles both isolated and touching characters, aligned at any slant. The capability of segmenting characters that touch either themselves or graphics, which is an important feature in handling real life drawings, is obtained by focusing on intermediate vector information rather that on the raw pixel data. We present the details of the algorithm and show both successful and unsuccessful examples from an experimental set of 36 dimensioning textboxes, in which 94% segmentation rate was achieved with 3% false alarm rate.</div>
</front>
</TEI>
<affiliations><list><country><li>Israël</li>
</country>
</list>
<tree><country name="Israël"><noRegion><name sortKey="Dori, D" sort="Dori, D" uniqKey="Dori D" first="D." last="Dori">D. Dori</name>
</noRegion>
<name sortKey="Wenyin, L" sort="Wenyin, L" uniqKey="Wenyin L" first="L." last="Wenyin">L. Wenyin</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002A07 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 002A07 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= Pascal:97-0020290 |texte= Vector-based segmentation of text connected to graphics in engineering drawings }}
This area was generated with Dilib version V0.6.32. |