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.

Intelligent region-based thresholding for color document images with highlighted regions

Identifieur interne : 000099 ( PascalFrancis/Corpus ); précédent : 000098; suivant : 000100

Intelligent region-based thresholding for color document images with highlighted regions

Auteurs : Chun-Ming Tsai

Source :

RBID : Pascal:12-0135276

Descripteurs français

English descriptors

Abstract

The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

pA  
A01 01  1    @0 0031-3203
A02 01      @0 PTNRA8
A03   1    @0 Pattern recogn.
A05       @2 45
A06       @2 4
A08 01  1  ENG  @1 Intelligent region-based thresholding for color document images with highlighted regions
A11 01  1    @1 TSAI (Chun-Ming)
A14 01      @1 Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road @2 Taipei 100 @3 TWN @Z 1 aut.
A20       @1 1341-1362
A21       @1 2012
A23 01      @0 ENG
A43 01      @1 INIST @2 15220 @5 354000502889930110
A44       @0 0000 @1 © 2012 INIST-CNRS. All rights reserved.
A45       @0 23 ref.
A47 01  1    @0 12-0135276
A60       @1 P
A61       @0 A
A64 01  1    @0 Pattern recognition
A66 01      @0 GBR
C01 01    ENG  @0 The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.
C02 01  X    @0 001D04A05C
C02 02  X    @0 001D04A05A
C02 03  X    @0 001D04A04A2
C03 01  X  FRE  @0 Détection seuil @5 01
C03 01  X  ENG  @0 Threshold detection @5 01
C03 01  X  SPA  @0 Detección umbral @5 01
C03 02  X  FRE  @0 Image couleur @5 02
C03 02  X  ENG  @0 Color image @5 02
C03 02  X  SPA  @0 Imagen color @5 02
C03 03  3  FRE  @0 Traitement image document @5 03
C03 03  3  ENG  @0 Document image processing @5 03
C03 04  X  FRE  @0 Evaluation performance @5 04
C03 04  X  ENG  @0 Performance evaluation @5 04
C03 04  X  SPA  @0 Evaluación prestación @5 04
C03 05  X  FRE  @0 Diminution coût @5 05
C03 05  X  ENG  @0 Cost lowering @5 05
C03 05  X  SPA  @0 Reducción costes @5 05
C03 06  X  FRE  @0 Complexité calcul @5 06
C03 06  X  ENG  @0 Computational complexity @5 06
C03 06  X  SPA  @0 Complejidad computación @5 06
C03 07  X  FRE  @0 Reconnaissance optique caractère @5 07
C03 07  X  ENG  @0 Optical character recognition @5 07
C03 07  X  SPA  @0 Reconocimento óptico de caracteres @5 07
C03 08  X  FRE  @0 Eclairement @5 08
C03 08  X  ENG  @0 Illumination @5 08
C03 08  X  SPA  @0 Alumbrado @5 08
C03 09  X  FRE  @0 Qualité image @5 09
C03 09  X  ENG  @0 Image quality @5 09
C03 09  X  SPA  @0 Calidad imagen @5 09
C03 10  X  FRE  @0 Algorithme @5 10
C03 10  X  ENG  @0 Algorithm @5 10
C03 10  X  SPA  @0 Algoritmo @5 10
C03 11  3  FRE  @0 Système embarqué @5 11
C03 11  3  ENG  @0 Embedded systems @5 11
C03 12  X  FRE  @0 Reconnaissance forme @5 46
C03 12  X  ENG  @0 Pattern recognition @5 46
C03 12  X  SPA  @0 Reconocimiento patrón @5 46
C03 13  X  FRE  @0 Arrière plan @4 CD @5 96
C03 13  X  ENG  @0 Background @4 CD @5 96
C03 14  X  FRE  @0 Avant plan @4 CD @5 97
C03 14  X  ENG  @0 Foreground @4 CD @5 97
C07 01  X  FRE  @0 Traitement image @5 12
C07 01  X  ENG  @0 Image processing @5 12
C07 01  X  SPA  @0 Procesamiento imagen @5 12
N21       @1 100
N44 01      @1 OTO
N82       @1 OTO

Format Inist (serveur)

NO : PASCAL 12-0135276 INIST
ET : Intelligent region-based thresholding for color document images with highlighted regions
AU : TSAI (Chun-Ming)
AF : Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road/Taipei 100/Taïwan (1 aut.)
DT : Publication en série; Niveau analytique
SO : Pattern recognition; ISSN 0031-3203; Coden PTNRA8; Royaume-Uni; Da. 2012; Vol. 45; No. 4; Pp. 1341-1362; Bibl. 23 ref.
LA : Anglais
EA : The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.
CC : 001D04A05C; 001D04A05A; 001D04A04A2
FD : Détection seuil; Image couleur; Traitement image document; Evaluation performance; Diminution coût; Complexité calcul; Reconnaissance optique caractère; Eclairement; Qualité image; Algorithme; Système embarqué; Reconnaissance forme; Arrière plan; Avant plan
FG : Traitement image
ED : Threshold detection; Color image; Document image processing; Performance evaluation; Cost lowering; Computational complexity; Optical character recognition; Illumination; Image quality; Algorithm; Embedded systems; Pattern recognition; Background; Foreground
EG : Image processing
SD : Detección umbral; Imagen color; Evaluación prestación; Reducción costes; Complejidad computación; Reconocimento óptico de caracteres; Alumbrado; Calidad imagen; Algoritmo; Reconocimiento patrón
LO : INIST-15220.354000502889930110
ID : 12-0135276

Links to Exploration step

Pascal:12-0135276

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" level="a">Intelligent region-based thresholding for color document images with highlighted regions</title>
<author>
<name sortKey="Tsai, Chun Ming" sort="Tsai, Chun Ming" uniqKey="Tsai C" first="Chun-Ming" last="Tsai">Chun-Ming Tsai</name>
<affiliation>
<inist:fA14 i1="01">
<s1>Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road</s1>
<s2>Taipei 100</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">INIST</idno>
<idno type="inist">12-0135276</idno>
<date when="2012">2012</date>
<idno type="stanalyst">PASCAL 12-0135276 INIST</idno>
<idno type="RBID">Pascal:12-0135276</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000099</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en" level="a">Intelligent region-based thresholding for color document images with highlighted regions</title>
<author>
<name sortKey="Tsai, Chun Ming" sort="Tsai, Chun Ming" uniqKey="Tsai C" first="Chun-Ming" last="Tsai">Chun-Ming Tsai</name>
<affiliation>
<inist:fA14 i1="01">
<s1>Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road</s1>
<s2>Taipei 100</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series>
<title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
<imprint>
<date when="2012">2012</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Algorithm</term>
<term>Background</term>
<term>Color image</term>
<term>Computational complexity</term>
<term>Cost lowering</term>
<term>Document image processing</term>
<term>Embedded systems</term>
<term>Foreground</term>
<term>Illumination</term>
<term>Image quality</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Performance evaluation</term>
<term>Threshold detection</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Détection seuil</term>
<term>Image couleur</term>
<term>Traitement image document</term>
<term>Evaluation performance</term>
<term>Diminution coût</term>
<term>Complexité calcul</term>
<term>Reconnaissance optique caractère</term>
<term>Eclairement</term>
<term>Qualité image</term>
<term>Algorithme</term>
<term>Système embarqué</term>
<term>Reconnaissance forme</term>
<term>Arrière plan</term>
<term>Avant plan</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.</div>
</front>
</TEI>
<inist>
<standard h6="B">
<pA>
<fA01 i1="01" i2="1">
<s0>0031-3203</s0>
</fA01>
<fA02 i1="01">
<s0>PTNRA8</s0>
</fA02>
<fA03 i2="1">
<s0>Pattern recogn.</s0>
</fA03>
<fA05>
<s2>45</s2>
</fA05>
<fA06>
<s2>4</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG">
<s1>Intelligent region-based thresholding for color document images with highlighted regions</s1>
</fA08>
<fA11 i1="01" i2="1">
<s1>TSAI (Chun-Ming)</s1>
</fA11>
<fA14 i1="01">
<s1>Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road</s1>
<s2>Taipei 100</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20>
<s1>1341-1362</s1>
</fA20>
<fA21>
<s1>2012</s1>
</fA21>
<fA23 i1="01">
<s0>ENG</s0>
</fA23>
<fA43 i1="01">
<s1>INIST</s1>
<s2>15220</s2>
<s5>354000502889930110</s5>
</fA43>
<fA44>
<s0>0000</s0>
<s1>© 2012 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45>
<s0>23 ref.</s0>
</fA45>
<fA47 i1="01" i2="1">
<s0>12-0135276</s0>
</fA47>
<fA60>
<s1>P</s1>
</fA60>
<fA61>
<s0>A</s0>
</fA61>
<fA64 i1="01" i2="1">
<s0>Pattern recognition</s0>
</fA64>
<fA66 i1="01">
<s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG">
<s0>The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.</s0>
</fC01>
<fC02 i1="01" i2="X">
<s0>001D04A05C</s0>
</fC02>
<fC02 i1="02" i2="X">
<s0>001D04A05A</s0>
</fC02>
<fC02 i1="03" i2="X">
<s0>001D04A04A2</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE">
<s0>Détection seuil</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG">
<s0>Threshold detection</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA">
<s0>Detección umbral</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE">
<s0>Image couleur</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG">
<s0>Color image</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA">
<s0>Imagen color</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="3" l="FRE">
<s0>Traitement image document</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="3" l="ENG">
<s0>Document image processing</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE">
<s0>Evaluation performance</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG">
<s0>Performance evaluation</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA">
<s0>Evaluación prestación</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE">
<s0>Diminution coût</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG">
<s0>Cost lowering</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA">
<s0>Reducción costes</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE">
<s0>Complexité calcul</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG">
<s0>Computational complexity</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA">
<s0>Complejidad computación</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE">
<s0>Reconnaissance optique caractère</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG">
<s0>Optical character recognition</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA">
<s0>Reconocimento óptico de caracteres</s0>
<s5>07</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE">
<s0>Eclairement</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG">
<s0>Illumination</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA">
<s0>Alumbrado</s0>
<s5>08</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE">
<s0>Qualité image</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG">
<s0>Image quality</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA">
<s0>Calidad imagen</s0>
<s5>09</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE">
<s0>Algorithme</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG">
<s0>Algorithm</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA">
<s0>Algoritmo</s0>
<s5>10</s5>
</fC03>
<fC03 i1="11" i2="3" l="FRE">
<s0>Système embarqué</s0>
<s5>11</s5>
</fC03>
<fC03 i1="11" i2="3" l="ENG">
<s0>Embedded systems</s0>
<s5>11</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE">
<s0>Reconnaissance forme</s0>
<s5>46</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG">
<s0>Pattern recognition</s0>
<s5>46</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA">
<s0>Reconocimiento patrón</s0>
<s5>46</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE">
<s0>Arrière plan</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG">
<s0>Background</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE">
<s0>Avant plan</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG">
<s0>Foreground</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC07 i1="01" i2="X" l="FRE">
<s0>Traitement image</s0>
<s5>12</s5>
</fC07>
<fC07 i1="01" i2="X" l="ENG">
<s0>Image processing</s0>
<s5>12</s5>
</fC07>
<fC07 i1="01" i2="X" l="SPA">
<s0>Procesamiento imagen</s0>
<s5>12</s5>
</fC07>
<fN21>
<s1>100</s1>
</fN21>
<fN44 i1="01">
<s1>OTO</s1>
</fN44>
<fN82>
<s1>OTO</s1>
</fN82>
</pA>
</standard>
<server>
<NO>PASCAL 12-0135276 INIST</NO>
<ET>Intelligent region-based thresholding for color document images with highlighted regions</ET>
<AU>TSAI (Chun-Ming)</AU>
<AF>Department of Computer Science, Taipei Municipal University of Education, No. 1, Ai-Kuo W. Road/Taipei 100/Taïwan (1 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>Pattern recognition; ISSN 0031-3203; Coden PTNRA8; Royaume-Uni; Da. 2012; Vol. 45; No. 4; Pp. 1341-1362; Bibl. 23 ref.</SO>
<LA>Anglais</LA>
<EA>The study applies an intelligent region-based thresholding method for the binarization of color document images with highlighted regions. The results also indicate that the proposed method can threshold simultaneously when the background is gradually changing, reversed, or inseparable from the foreground, with efficient binarization results. Rather than the traditional method of scanning the entire document at least once, this method intelligently divides a document image into several foreground regions and decides the background range for each foreground region, in order to effectively process the detected document regions. Experimental results demonstrate the high effectiveness of the proposed method in providing promising binarization results with low computational cost. Furthermore, the results of the proposed method are more accurate than global, region-based, local, and hybrid methods. Images were analyzed using MODI OCR measurement data such as recall rate and precision rate. In particular, when test images produced under inadequate illumination are processed using the proposed method, the binarization results of this method have better visual quality and better measurable OCR performance than compared global, region-based, local, and hybrid methods. Moreover, the proposed algorithm can be run in an embedded system due to its simplicity and efficiency.</EA>
<CC>001D04A05C; 001D04A05A; 001D04A04A2</CC>
<FD>Détection seuil; Image couleur; Traitement image document; Evaluation performance; Diminution coût; Complexité calcul; Reconnaissance optique caractère; Eclairement; Qualité image; Algorithme; Système embarqué; Reconnaissance forme; Arrière plan; Avant plan</FD>
<FG>Traitement image</FG>
<ED>Threshold detection; Color image; Document image processing; Performance evaluation; Cost lowering; Computational complexity; Optical character recognition; Illumination; Image quality; Algorithm; Embedded systems; Pattern recognition; Background; Foreground</ED>
<EG>Image processing</EG>
<SD>Detección umbral; Imagen color; Evaluación prestación; Reducción costes; Complejidad computación; Reconocimento óptico de caracteres; Alumbrado; Calidad imagen; Algoritmo; Reconocimiento patrón</SD>
<LO>INIST-15220.354000502889930110</LO>
<ID>12-0135276</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000099 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000099 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:12-0135276
   |texte=   Intelligent region-based thresholding for color document images with highlighted regions
}}

Wicri

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