Segmentation and Recognition of Dimensioning Text from Engineering Drawings
Identifieur interne : 002194 ( Main/Exploration ); précédent : 002193; suivant : 002195Segmentation and Recognition of Dimensioning Text from Engineering Drawings
Auteurs : Dov Dori [Israël] ; Yelena Velkovitch [Israël]Source :
- Computer Vision and Image Understanding [ 1077-3142 ] ; 1996.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
- Algorithm, Algorithm performance, CAD conversion, Computer aided design, Experimental study, Image interpretation, Image processing, Neural network, Optical character recognition, Pattern extraction, Pattern recognition, Segmentation, Word processing, engineering drawing understanding, optical character recognition., text segmentation, text-graphics association, text-graphics separation.
Abstract
Recognition of dimensioning text in engineering drawings is an essential part of the drawing understanding process, as this text provides the exact dimensions and tolerances of the object described in the drawing. We consider engineering drawings produced according to either ISO or ANSI drafting standards. Text segmentation and recognition are preceded by orthogonal zig-zag vectorization, arc segmentation, and arrowhead pair recognition. Initial textbox extraction is done by a region growing process, performed on text-wire candidates. On the basis of textbox context (neighboring annotation wires) the drafting standard is detected. Raw textboxes are divided into logical textboxes, which are further decomposed into basic textboxes. A neural network based OCR algorithm is applied to each basic textbox. Finally, the OCR recognition results are verified by using contextual information and comparing the results with the measurements made directly on the drawing.
Url:
DOI: 10.1006/cviu.1997.0585
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000A11
- to stream Istex, to step Curation: 000999
- to stream Istex, to step Checkpoint: 001698
- to stream Main, to step Merge: 002311
- to stream PascalFrancis, to step Corpus: 000898
- to stream PascalFrancis, to step Curation: 000A99
- to stream PascalFrancis, to step Checkpoint: 000815
- to stream Main, to step Merge: 002409
- to stream Main, to step Curation: 002194
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Segmentation and Recognition of Dimensioning Text from Engineering Drawings</title><author><name sortKey="Dori, Dov" sort="Dori, Dov" uniqKey="Dori D" first="Dov" last="Dori">Dov Dori</name></author><author><name sortKey="Velkovitch, Yelena" sort="Velkovitch, Yelena" uniqKey="Velkovitch Y" first="Yelena" last="Velkovitch">Yelena Velkovitch</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D065735D1B124DCE455FF2DCA70AFA35A39F50A4</idno><date when="1998" year="1998">1998</date><idno type="doi">10.1006/cviu.1997.0585</idno><idno type="url">https://api.istex.fr/document/D065735D1B124DCE455FF2DCA70AFA35A39F50A4/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000A11</idno><idno type="wicri:Area/Istex/Curation">000999</idno><idno type="wicri:Area/Istex/Checkpoint">001698</idno><idno type="wicri:doubleKey">1077-3142:1998:Dori D:segmentation:and:recognition</idno><idno type="wicri:Area/Main/Merge">002311</idno><idno type="wicri:source">INIST</idno><idno type="RBID">Pascal:98-0189160</idno><idno type="wicri:Area/PascalFrancis/Corpus">000898</idno><idno type="wicri:Area/PascalFrancis/Curation">000A99</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000815</idno><idno type="wicri:doubleKey">1077-3142:1998:Dori D:segmentation:and:recognition</idno><idno type="wicri:Area/Main/Merge">002409</idno><idno type="wicri:Area/Main/Curation">002194</idno><idno type="wicri:Area/Main/Exploration">002194</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Segmentation and Recognition of Dimensioning Text from Engineering Drawings</title><author><name sortKey="Dori, Dov" sort="Dori, Dov" uniqKey="Dori D" first="Dov" last="Dori">Dov Dori</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Information Systems Engineering, Faculty of Industrial Engineering and Management, Technion, Israel Institute of Technology, Haifa, 32000</wicri:regionArea><wicri:noRegion>32000</wicri:noRegion></affiliation></author><author><name sortKey="Velkovitch, Yelena" sort="Velkovitch, Yelena" uniqKey="Velkovitch Y" first="Yelena" last="Velkovitch">Yelena Velkovitch</name><affiliation wicri:level="1"><country xml:lang="fr">Israël</country><wicri:regionArea>Information Systems Engineering, Faculty of Industrial Engineering and Management, Technion, Israel Institute of Technology, Haifa, 32000</wicri:regionArea><wicri:noRegion>32000</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Computer Vision and Image Understanding</title><title level="j" type="abbrev">YCVIU</title><idno type="ISSN">1077-3142</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1996">1996</date><biblScope unit="volume">69</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="196">196</biblScope><biblScope unit="page" to="201">201</biblScope></imprint><idno type="ISSN">1077-3142</idno></series><idno type="istex">D065735D1B124DCE455FF2DCA70AFA35A39F50A4</idno><idno type="DOI">10.1006/cviu.1997.0585</idno><idno type="PII">S1077-3142(97)90585-3</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1077-3142</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term><term>Algorithm performance</term><term>CAD conversion</term><term>Computer aided design</term><term>Experimental study</term><term>Image interpretation</term><term>Image processing</term><term>Neural network</term><term>Optical character recognition</term><term>Pattern extraction</term><term>Pattern recognition</term><term>Segmentation</term><term>Word processing</term><term>engineering drawing understanding</term><term>optical character recognition.</term><term>text segmentation</term><term>text-graphics association</term><term>text-graphics separation</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Algorithme</term><term>Conception assistée</term><term>Etude expérimentale</term><term>Extraction forme</term><term>Interprétation image</term><term>Performance algorithme</term><term>Reconnaissance forme</term><term>Reconnaissance optique caractère</term><term>Réseau neuronal</term><term>Segmentation</term><term>Traitement image</term><term>Traitement texte</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Recognition of dimensioning text in engineering drawings is an essential part of the drawing understanding process, as this text provides the exact dimensions and tolerances of the object described in the drawing. We consider engineering drawings produced according to either ISO or ANSI drafting standards. Text segmentation and recognition are preceded by orthogonal zig-zag vectorization, arc segmentation, and arrowhead pair recognition. Initial textbox extraction is done by a region growing process, performed on text-wire candidates. On the basis of textbox context (neighboring annotation wires) the drafting standard is detected. Raw textboxes are divided into logical textboxes, which are further decomposed into basic textboxes. A neural network based OCR algorithm is applied to each basic textbox. Finally, the OCR recognition results are verified by using contextual information and comparing the results with the measurements made directly on the drawing.</div></front></TEI><affiliations><list><country><li>Israël</li></country></list><tree><country name="Israël"><noRegion><name sortKey="Dori, Dov" sort="Dori, Dov" uniqKey="Dori D" first="Dov" last="Dori">Dov Dori</name></noRegion><name sortKey="Velkovitch, Yelena" sort="Velkovitch, Yelena" uniqKey="Velkovitch Y" first="Yelena" last="Velkovitch">Yelena Velkovitch</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002194 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002194 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:D065735D1B124DCE455FF2DCA70AFA35A39F50A4
|texte= Segmentation and Recognition of Dimensioning Text from Engineering Drawings
}}
| This area was generated with Dilib version V0.6.32. |  |