Morphological preprocessing method to thresholding degraded word images
Identifieur interne : 000A76 ( Main/Exploration ); précédent : 000A75; suivant : 000A77Morphological preprocessing method to thresholding degraded word images
Auteurs : Shigueo Nomura [Japon] ; Keiji Yamanaka [Brésil] ; Takayuki Shiose [Japon] ; Hiroshi Kawakami [Japon] ; Osamu Katai [Japon]Source :
- Pattern recognition letters [ 0167-8655 ] ; 2009.
Descripteurs français
- Pascal (Inist)
- Détection seuil, Morphologie mathématique, Ombre, Bruit fond, Image binaire, Segmentation, Localisation, Méthode adaptative, Image niveau gris, Filtre morphologique, Reconnaissance optique caractère, Complexité calcul, Appareillage essai, Imageur, Analyse qualitative, Evaluation performance, Reconnaissance forme.
- Wicri :
- topic : Analyse qualitative.
English descriptors
- KwdEn :
- Adaptive method, Background noise, Binary image, Computational complexity, Grey level image, Imager, Localization, Mathematical morphology, Morphological filter, Optical character recognition, Pattern recognition, Performance evaluation, Qualitative analysis, Segmentation, Shadow, Testing equipment, Threshold detection.
Abstract
This paper presents a novel preprocessing method based on mathematical morphology techniques to improve the subsequent thresholding quality of raw degraded word images. The raw degraded word images contain undesirable shapes called critical shadows on the background that cause noise in binary images. This noise constitutes obstacles to posterior segmentation of characters. Direct application of a thresholding method produces inadequate binary versions of these degraded word images. Our preprocessing method called Shadow Location and Lightening (SL*L) adaptively, accurately and without manual fine-tuning of parameters locates these critical shadows on grayscale degraded images using morphological operations, and lightens them before applying eventual thresholding process. In this way, enhanced binary images without unpredictable and inappropriate noise can be provided to subsequent segmentation of characters. Then, adequate binary characters can be segmented and extracted as input data to optical character recognition (OCR) applications saving computational effort and increasing recognition rate. The proposed method is experimentally tested with a set of several raw degraded images extracted from real photos acquired by unsophisticated imaging systems. A qualitative analysis of experimental results led to conclusions that the thresholding result quality was significantly improved with the proposed preprocessing method. Also, a quantitative evaluation using a testing data of 1194 degraded word images showed the essentiality and effectiveness of the proposed preprocessing method to increase segmentation and recognition rates of their characters. Furthermore, an advantage of the proposed method is that Otsu's method as a simple and easily implementable global thresholding technique can be sufficient to reducing computational load.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000225
- to stream PascalFrancis, to step Curation: 000555
- to stream PascalFrancis, to step Checkpoint: 000191
- to stream Main, to step Merge: 000A85
- to stream Main, to step Curation: 000A76
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Morphological preprocessing method to thresholding degraded word images</title>
<author><name sortKey="Nomura, Shigueo" sort="Nomura, Shigueo" uniqKey="Nomura S" first="Shigueo" last="Nomura">Shigueo Nomura</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Yamanaka, Keiji" sort="Yamanaka, Keiji" uniqKey="Yamanaka K" first="Keiji" last="Yamanaka">Keiji Yamanaka</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Faculty of Electrical Engineering, Federal University of Uberlândia</s1>
<s2>Uberlândia 38400-902</s2>
<s3>BRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Brésil</country>
<wicri:noRegion>Uberlândia 38400-902</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Shiose, Takayuki" sort="Shiose, Takayuki" uniqKey="Shiose T" first="Takayuki" last="Shiose">Takayuki Shiose</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Kawakami, Hiroshi" sort="Kawakami, Hiroshi" uniqKey="Kawakami H" first="Hiroshi" last="Kawakami">Hiroshi Kawakami</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Katai, Osamu" sort="Katai, Osamu" uniqKey="Katai O" first="Osamu" last="Katai">Osamu Katai</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">09-0265418</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 09-0265418 INIST</idno>
<idno type="RBID">Pascal:09-0265418</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000225</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000555</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000191</idno>
<idno type="wicri:doubleKey">0167-8655:2009:Nomura S:morphological:preprocessing:method</idno>
<idno type="wicri:Area/Main/Merge">000A85</idno>
<idno type="wicri:Area/Main/Curation">000A76</idno>
<idno type="wicri:Area/Main/Exploration">000A76</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Morphological preprocessing method to thresholding degraded word images</title>
<author><name sortKey="Nomura, Shigueo" sort="Nomura, Shigueo" uniqKey="Nomura S" first="Shigueo" last="Nomura">Shigueo Nomura</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Yamanaka, Keiji" sort="Yamanaka, Keiji" uniqKey="Yamanaka K" first="Keiji" last="Yamanaka">Keiji Yamanaka</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Faculty of Electrical Engineering, Federal University of Uberlândia</s1>
<s2>Uberlândia 38400-902</s2>
<s3>BRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Brésil</country>
<wicri:noRegion>Uberlândia 38400-902</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Shiose, Takayuki" sort="Shiose, Takayuki" uniqKey="Shiose T" first="Takayuki" last="Shiose">Takayuki Shiose</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Kawakami, Hiroshi" sort="Kawakami, Hiroshi" uniqKey="Kawakami H" first="Hiroshi" last="Kawakami">Hiroshi Kawakami</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Katai, Osamu" sort="Katai, Osamu" uniqKey="Katai O" first="Osamu" last="Katai">Osamu Katai</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Department of Systems Science, Graduate School of Informatics, Kyoto University, Yoshida Honmachi</s1>
<s2>Sakyo-ku, Kyoto 606-8501</s2>
<s3>JPN</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>Japon</country>
<wicri:noRegion>Sakyo-ku, Kyoto 606-8501</wicri:noRegion>
<orgName type="university">Université de Kyoto</orgName>
<placeName><settlement type="city">Kyoto</settlement>
<region type="prefecture">Région du Kansai</region>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition letters</title>
<title level="j" type="abbreviated">Pattern recogn. lett.</title>
<idno type="ISSN">0167-8655</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive method</term>
<term>Background noise</term>
<term>Binary image</term>
<term>Computational complexity</term>
<term>Grey level image</term>
<term>Imager</term>
<term>Localization</term>
<term>Mathematical morphology</term>
<term>Morphological filter</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Performance evaluation</term>
<term>Qualitative analysis</term>
<term>Segmentation</term>
<term>Shadow</term>
<term>Testing equipment</term>
<term>Threshold detection</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Détection seuil</term>
<term>Morphologie mathématique</term>
<term>Ombre</term>
<term>Bruit fond</term>
<term>Image binaire</term>
<term>Segmentation</term>
<term>Localisation</term>
<term>Méthode adaptative</term>
<term>Image niveau gris</term>
<term>Filtre morphologique</term>
<term>Reconnaissance optique caractère</term>
<term>Complexité calcul</term>
<term>Appareillage essai</term>
<term>Imageur</term>
<term>Analyse qualitative</term>
<term>Evaluation performance</term>
<term>Reconnaissance forme</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Analyse qualitative</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents a novel preprocessing method based on mathematical morphology techniques to improve the subsequent thresholding quality of raw degraded word images. The raw degraded word images contain undesirable shapes called critical shadows on the background that cause noise in binary images. This noise constitutes obstacles to posterior segmentation of characters. Direct application of a thresholding method produces inadequate binary versions of these degraded word images. Our preprocessing method called Shadow Location and Lightening (SL<sup>*</sup>
L) adaptively, accurately and without manual fine-tuning of parameters locates these critical shadows on grayscale degraded images using morphological operations, and lightens them before applying eventual thresholding process. In this way, enhanced binary images without unpredictable and inappropriate noise can be provided to subsequent segmentation of characters. Then, adequate binary characters can be segmented and extracted as input data to optical character recognition (OCR) applications saving computational effort and increasing recognition rate. The proposed method is experimentally tested with a set of several raw degraded images extracted from real photos acquired by unsophisticated imaging systems. A qualitative analysis of experimental results led to conclusions that the thresholding result quality was significantly improved with the proposed preprocessing method. Also, a quantitative evaluation using a testing data of 1194 degraded word images showed the essentiality and effectiveness of the proposed preprocessing method to increase segmentation and recognition rates of their characters. Furthermore, an advantage of the proposed method is that Otsu's method as a simple and easily implementable global thresholding technique can be sufficient to reducing computational load.</div>
</front>
</TEI>
<affiliations><list><country><li>Brésil</li>
<li>Japon</li>
</country>
<region><li>Région du Kansai</li>
</region>
<settlement><li>Kyoto</li>
</settlement>
<orgName><li>Université de Kyoto</li>
</orgName>
</list>
<tree><country name="Japon"><region name="Région du Kansai"><name sortKey="Nomura, Shigueo" sort="Nomura, Shigueo" uniqKey="Nomura S" first="Shigueo" last="Nomura">Shigueo Nomura</name>
</region>
<name sortKey="Katai, Osamu" sort="Katai, Osamu" uniqKey="Katai O" first="Osamu" last="Katai">Osamu Katai</name>
<name sortKey="Kawakami, Hiroshi" sort="Kawakami, Hiroshi" uniqKey="Kawakami H" first="Hiroshi" last="Kawakami">Hiroshi Kawakami</name>
<name sortKey="Shiose, Takayuki" sort="Shiose, Takayuki" uniqKey="Shiose T" first="Takayuki" last="Shiose">Takayuki Shiose</name>
</country>
<country name="Brésil"><noRegion><name sortKey="Yamanaka, Keiji" sort="Yamanaka, Keiji" uniqKey="Yamanaka K" first="Keiji" last="Yamanaka">Keiji Yamanaka</name>
</noRegion>
</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 000A76 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A76 | 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:09-0265418 |texte= Morphological preprocessing method to thresholding degraded word images }}
![]() | This area was generated with Dilib version V0.6.32. | ![]() |