OcrV1, Main, Exploration, bibRecord, 001395

Historical document image segmentation using background light intensity normalization

Identifieur interne : 001395 ( Main/Exploration ); précédent : 001394; suivant : 001396

Historical document image segmentation using background light intensity normalization

Auteurs : ZHIXIN SHI [États-Unis] ; Venugopal Govindaraju [États-Unis]

Source :

SPIE proceedings series [ 1017-2653 ] ; 2005.

RBID : Pascal:05-0360928

Descripteurs français

Pascal (Inist)
- Traitement image document, Segmentation image, Algorithme adaptatif, Fonction non linéaire, Meilleure approximation, Détection seuil, Echelle gris, Image niveau gris, Caractère manuscrit, Reconnaissance optique caractère, Traitement image.

English descriptors

KwdEn :
- Adaptive algorithm, Best approximation, Document image processing, Gray scale, Grey level image, Image processing, Image segmentation, Manuscript character, Non linear function, Optical character recognition, Threshold detection.

Abstract

This paper presents a new document binarization algorithm for camera images of historical documents, which are especially found in The Library of Congress of the Unite States. The algorithm uses a background light intensity normalization algorithm to enhance an image before a local adaptive binarization algorithm is applied. The image normalization algorithm uses an adaptive linear or non-linear function to approximate the uneven background of the image due to the uneven surface of the document paper, aged color or uneven light source of the cameras for image lifting. Our algorithm adaptively captures the background of a document image with a "best fit" approximation. The document image is then normalized with respect to the approximation before a thresholding algorithm is applied. The technique works for both gray scale and color historical handwritten document images with significant improvement in readability for both human and OCR.

Affiliations:

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: 000458
to stream PascalFrancis, to step Curation: 000330
to stream PascalFrancis, to step Checkpoint: 000404
to stream Main, to step Merge: 001434
to stream Main, to step Curation: 001395

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Historical document image segmentation using background light intensity normalization</title>
<author><name sortKey="Zhixin Shi" sort="Zhixin Shi" uniqKey="Zhixin Shi" last="Zhixin Shi">ZHIXIN SHI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition (CEDAR), State University of New York at Buffalo</s1>
<s2>Amherst</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Amherst</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition (CEDAR), State University of New York at Buffalo</s1>
<s2>Amherst</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Amherst</wicri:noRegion>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">05-0360928</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 05-0360928 INIST</idno>
<idno type="RBID">Pascal:05-0360928</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000458</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000330</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000404</idno>
<idno type="wicri:doubleKey">1017-2653:2005:Zhixin Shi:historical:document:image</idno>
<idno type="wicri:Area/Main/Merge">001434</idno>
<idno type="wicri:Area/Main/Curation">001395</idno>
<idno type="wicri:Area/Main/Exploration">001395</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Historical document image segmentation using background light intensity normalization</title>
<author><name sortKey="Zhixin Shi" sort="Zhixin Shi" uniqKey="Zhixin Shi" last="Zhixin Shi">ZHIXIN SHI</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition (CEDAR), State University of New York at Buffalo</s1>
<s2>Amherst</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Amherst</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Center of Excellence for Document Analysis and Recognition (CEDAR), State University of New York at Buffalo</s1>
<s2>Amherst</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<wicri:noRegion>Amherst</wicri:noRegion>
<placeName><settlement type="city">Buffalo (New York)</settlement>
<region type="state">État de New York</region>
</placeName>
<orgName type="university" n="3">Université d'État de New York à Buffalo</orgName>
<orgName type="institution">Université d'État de New York</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="2005">2005</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive algorithm</term>
<term>Best approximation</term>
<term>Document image processing</term>
<term>Gray scale</term>
<term>Grey level image</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Manuscript character</term>
<term>Non linear function</term>
<term>Optical character recognition</term>
<term>Threshold detection</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Traitement image document</term>
<term>Segmentation image</term>
<term>Algorithme adaptatif</term>
<term>Fonction non linéaire</term>
<term>Meilleure approximation</term>
<term>Détection seuil</term>
<term>Echelle gris</term>
<term>Image niveau gris</term>
<term>Caractère manuscrit</term>
<term>Reconnaissance optique caractère</term>
<term>Traitement image</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents a new document binarization algorithm for camera images of historical documents, which are especially found in The Library of Congress of the Unite States. The algorithm uses a background light intensity normalization algorithm to enhance an image before a local adaptive binarization algorithm is applied. The image normalization algorithm uses an adaptive linear or non-linear function to approximate the uneven background of the image due to the uneven surface of the document paper, aged color or uneven light source of the cameras for image lifting. Our algorithm adaptively captures the background of a document image with a "best fit" approximation. The document image is then normalized with respect to the approximation before a thresholding algorithm is applied. The technique works for both gray scale and color historical handwritten document images with significant improvement in readability for both human and OCR.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>État de New York</li>
</region>
<settlement><li>Buffalo (New York)</li>
</settlement>
<orgName><li>Université d'État de New York</li>
<li>Université d'État de New York à Buffalo</li>
</orgName>
</list>
<tree><country name="États-Unis"><noRegion><name sortKey="Zhixin Shi" sort="Zhixin Shi" uniqKey="Zhixin Shi" last="Zhixin Shi">ZHIXIN SHI</name>
</noRegion>
<name sortKey="Govindaraju, Venu" sort="Govindaraju, Venu" uniqKey="Govindaraju V" first="Venu" last="Govindaraju">Venugopal Govindaraju</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 001395 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001395 | 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:05-0360928
   |texte=   Historical document image segmentation using background light intensity normalization
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

Historical document image segmentation using background light intensity normalization

Historical document image segmentation using background light intensity normalization

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri