Graph cut-based binarisation of noisy check images
Identifieur interne : 000314 ( Main/Exploration ); précédent : 000313; suivant : 000315Graph cut-based binarisation of noisy check images
Auteurs : A. Dawoud [États-Unis] ; A. Netchaev [États-Unis]Source :
- IET image processing : (Print) [ 1751-9659 ] ; 2012.
Descripteurs français
- Pascal (Inist)
- Coupe graphe, Image bruitée, Traitement image document, Contraste image, Méthode variable complexe, Echelle gris, Histogramme, Algorithme, Caractère manuscrit, Détection seuil, Squelette, Extraction caractéristique, Evaluation performance, Reconnaissance optique caractère, Segmentation, Traitement signal, Reconnaissance forme, Arrière plan.
English descriptors
- KwdEn :
- Algorithm, Background, Complex variable method, Document image processing, Feature extraction, Graph cut, Gray scale, Histogram, Image contrast, Manuscript character, Noisy image, Optical character recognition, Pattern recognition, Performance evaluation, Segmentation, Signal processing, Skeleton, Threshold detection.
Abstract
Binarisation of document images with poor contrast, strong noise, complex patterns and variable modalities in the greyscale histograms is a challenging problem. This study proposes an algorithm for the binarisation of noisy check images to extract handwriting text using normalised graph cuts (GCs). The proposed algorithm uses a normalised GC measure as a thresholding principle to distinguish the handwriting characters from the noisy background. The authors propose a factor to penalise extracting objects that do not have the elongated shape of the characters. Improving the structural quality of the characters' skeleton facilitates better feature extraction and classification, which improves the overall performance of optical character recognition (OCR). Experimental results performed on 560 check images showed significant improvements in OCR recognition rates compared to other well-established segmentation algorithms.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000070
- to stream PascalFrancis, to step Curation: 000698
- to stream PascalFrancis, to step Checkpoint: 000076
- to stream Main, to step Merge: 000317
- to stream Main, to step Curation: 000314
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Graph cut-based binarisation of noisy check images</title><author><name sortKey="Dawoud, A" sort="Dawoud, A" uniqKey="Dawoud A" first="A." last="Dawoud">A. Dawoud</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>School of Computing, University of Southern Mississippi</s1><s2>Hattiesburg, MS 39406</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">État du Mississippi</region></placeName></affiliation></author><author><name sortKey="Netchaev, A" sort="Netchaev, A" uniqKey="Netchaev A" first="A." last="Netchaev">A. Netchaev</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>School of Computing, University of Southern Mississippi</s1><s2>Hattiesburg, MS 39406</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">État du Mississippi</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">13-0017543</idno><date when="2012">2012</date><idno type="stanalyst">PASCAL 13-0017543 INIST</idno><idno type="RBID">Pascal:13-0017543</idno><idno type="wicri:Area/PascalFrancis/Corpus">000070</idno><idno type="wicri:Area/PascalFrancis/Curation">000698</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000076</idno><idno type="wicri:doubleKey">1751-9659:2012:Dawoud A:graph:cut:based</idno><idno type="wicri:Area/Main/Merge">000317</idno><idno type="wicri:Area/Main/Curation">000314</idno><idno type="wicri:Area/Main/Exploration">000314</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Graph cut-based binarisation of noisy check images</title><author><name sortKey="Dawoud, A" sort="Dawoud, A" uniqKey="Dawoud A" first="A." last="Dawoud">A. Dawoud</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>School of Computing, University of Southern Mississippi</s1><s2>Hattiesburg, MS 39406</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">État du Mississippi</region></placeName></affiliation></author><author><name sortKey="Netchaev, A" sort="Netchaev, A" uniqKey="Netchaev A" first="A." last="Netchaev">A. Netchaev</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>School of Computing, University of Southern Mississippi</s1><s2>Hattiesburg, MS 39406</s2><s3>USA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>États-Unis</country><placeName><region type="state">État du Mississippi</region></placeName></affiliation></author></analytic><series><title level="j" type="main">IET image processing : (Print)</title><title level="j" type="abbreviated">IET image process. : (Print)</title><idno type="ISSN">1751-9659</idno><imprint><date when="2012">2012</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">IET image processing : (Print)</title><title level="j" type="abbreviated">IET image process. : (Print)</title><idno type="ISSN">1751-9659</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithm</term><term>Background</term><term>Complex variable method</term><term>Document image processing</term><term>Feature extraction</term><term>Graph cut</term><term>Gray scale</term><term>Histogram</term><term>Image contrast</term><term>Manuscript character</term><term>Noisy image</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Performance evaluation</term><term>Segmentation</term><term>Signal processing</term><term>Skeleton</term><term>Threshold detection</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Coupe graphe</term><term>Image bruitée</term><term>Traitement image document</term><term>Contraste image</term><term>Méthode variable complexe</term><term>Echelle gris</term><term>Histogramme</term><term>Algorithme</term><term>Caractère manuscrit</term><term>Détection seuil</term><term>Squelette</term><term>Extraction caractéristique</term><term>Evaluation performance</term><term>Reconnaissance optique caractère</term><term>Segmentation</term><term>Traitement signal</term><term>Reconnaissance forme</term><term>Arrière plan</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Binarisation of document images with poor contrast, strong noise, complex patterns and variable modalities in the greyscale histograms is a challenging problem. This study proposes an algorithm for the binarisation of noisy check images to extract handwriting text using normalised graph cuts (GCs). The proposed algorithm uses a normalised GC measure as a thresholding principle to distinguish the handwriting characters from the noisy background. The authors propose a factor to penalise extracting objects that do not have the elongated shape of the characters. Improving the structural quality of the characters' skeleton facilitates better feature extraction and classification, which improves the overall performance of optical character recognition (OCR). Experimental results performed on 560 check images showed significant improvements in OCR recognition rates compared to other well-established segmentation algorithms.</div></front></TEI><affiliations><list><country><li>États-Unis</li></country><region><li>État du Mississippi</li></region></list><tree><country name="États-Unis"><region name="État du Mississippi"><name sortKey="Dawoud, A" sort="Dawoud, A" uniqKey="Dawoud A" first="A." last="Dawoud">A. Dawoud</name></region><name sortKey="Netchaev, A" sort="Netchaev, A" uniqKey="Netchaev A" first="A." last="Netchaev">A. Netchaev</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 000314 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000314 | 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= Pascal:13-0017543
|texte= Graph cut-based binarisation of noisy check images
}}
| This area was generated with Dilib version V0.6.32. |  |