A character degradation model for grayscale ancient document images
Identifieur interne : 000135 ( Hal/Corpus ); précédent : 000134; suivant : 000136A character degradation model for grayscale ancient document images
Auteurs : Van Cuong Kieu ; Jean-Philippe Domenger ; Rémy Mullot ; Nicholas Journet ; Muriel VisaniSource :
English descriptors
Abstract
Kanungo noise model is widely used to test the robustness of different binary document image analysis methods towards noise. This model only works with binary images while most document images are in grayscale. Because binarizing a document image might degrade its contents and lead to a loss of information, more and more researchers are currently focusing on segmentation-free methods (Angelika et al [2]). Thus, we propose a local noise model for grayscale images. Its main principle is to locally degrade the image in the neighbourhoods of "seed-points" selected close to the character boundary. These points define the center of "noise regions". The pixel values inside the noise region are modified by a Gaussian random distribution to make the final result more realistic. While Kanungo noise models scanning artifacts, our model simulates degradations due to the age of the document itself and printing/writing process such as ink splotches, white specks or streaks. It is very easy for users to parameterize and create a set of benchmark databases with an increasing level of noise. These databases will further be used to test the robustness of different grayscale document image analysis methods (i.e. text line segmentation, OCR, handwriting recognition).
Url:
Links to Exploration step
Hal:hal-00979057Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="fr">A character degradation model for grayscale ancient document images</title><author><name sortKey="Kieu, Van Cuong" sort="Kieu, Van Cuong" uniqKey="Kieu V" first="Van Cuong" last="Kieu">Van Cuong Kieu</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Domenger, Jean Philippe" sort="Domenger, Jean Philippe" uniqKey="Domenger J" first="Jean-Philippe" last="Domenger">Jean-Philippe Domenger</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Mullot, Remy" sort="Mullot, Remy" uniqKey="Mullot R" first="Rémy" last="Mullot">Rémy Mullot</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName><orgName type="acronym">L3I</orgName><desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lr.fr/l3i</ref></desc><listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation></listRelation><tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Journet, Nicholas" sort="Journet, Nicholas" uniqKey="Journet N" first="Nicholas" last="Journet">Nicholas Journet</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Visani, Muriel" sort="Visani, Muriel" uniqKey="Visani M" first="Muriel" last="Visani">Muriel Visani</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName><orgName type="acronym">L3I</orgName><desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lr.fr/l3i</ref></desc><listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation></listRelation><tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">HAL</idno><idno type="RBID">Hal:hal-00979057</idno><idno type="halId">hal-00979057</idno><idno type="halUri">https://hal.archives-ouvertes.fr/hal-00979057</idno><idno type="url">https://hal.archives-ouvertes.fr/hal-00979057</idno><date when="2012-11-11">2012-11-11</date><idno type="wicri:Area/Hal/Corpus">000135</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="fr">A character degradation model for grayscale ancient document images</title><author><name sortKey="Kieu, Van Cuong" sort="Kieu, Van Cuong" uniqKey="Kieu V" first="Van Cuong" last="Kieu">Van Cuong Kieu</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Domenger, Jean Philippe" sort="Domenger, Jean Philippe" uniqKey="Domenger J" first="Jean-Philippe" last="Domenger">Jean-Philippe Domenger</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Mullot, Remy" sort="Mullot, Remy" uniqKey="Mullot R" first="Rémy" last="Mullot">Rémy Mullot</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName><orgName type="acronym">L3I</orgName><desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lr.fr/l3i</ref></desc><listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation></listRelation><tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Journet, Nicholas" sort="Journet, Nicholas" uniqKey="Journet N" first="Nicholas" last="Journet">Nicholas Journet</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-3102" status="VALID"><orgName>Laboratoire Bordelais de Recherche en Informatique</orgName><orgName type="acronym">LaBRI</orgName><desc><address><addrLine>Domaine Universitaire 351, cours de la Libération 33405 Talence Cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.labri.fr</ref></desc><listRelation><relation active="#struct-91134" type="direct"></relation><relation active="#struct-92972" type="direct"></relation><relation active="#struct-300366" type="direct"></relation><relation name="UMR5800" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-91134" type="direct"><org type="institution" xml:id="struct-91134" status="OLD"><orgName>Université Bordeaux Segalen - Bordeaux 2</orgName><desc><address><addrLine>146 rue Léo Saignat - 33076 Bordeaux cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-bordeauxsegalen.fr/</ref></desc></org></tutelle><tutelle active="#struct-92972" type="direct"><org type="institution" xml:id="struct-92972" status="OLD"><orgName>Université Sciences et Technologies - Bordeaux 1</orgName><desc><address><addrLine>351 cours de la Libération - 33405 Talence cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bordeaux1.fr</ref></desc></org></tutelle><tutelle active="#struct-300366" type="direct"><org type="institution" xml:id="struct-300366" status="VALID"><orgName>École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="UMR5800" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="IdRef">02636817X</idno><idno type="ISNI">0000000122597504</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author><author><name sortKey="Visani, Muriel" sort="Visani, Muriel" uniqKey="Visani M" first="Muriel" last="Visani">Muriel Visani</name><affiliation><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName><orgName type="acronym">L3I</orgName><desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-lr.fr/l3i</ref></desc><listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation></listRelation><tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>document degradation model</term><term>performance evaluation</term><term>synthetic image generation</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Kanungo noise model is widely used to test the robustness of different binary document image analysis methods towards noise. This model only works with binary images while most document images are in grayscale. Because binarizing a document image might degrade its contents and lead to a loss of information, more and more researchers are currently focusing on segmentation-free methods (Angelika et al [2]). Thus, we propose a local noise model for grayscale images. Its main principle is to locally degrade the image in the neighbourhoods of "seed-points" selected close to the character boundary. These points define the center of "noise regions". The pixel values inside the noise region are modified by a Gaussian random distribution to make the final result more realistic. While Kanungo noise models scanning artifacts, our model simulates degradations due to the age of the document itself and printing/writing process such as ink splotches, white specks or streaks. It is very easy for users to parameterize and create a set of benchmark databases with an increasing level of noise. These databases will further be used to test the robustness of different grayscale document image analysis methods (i.e. text line segmentation, OCR, handwriting recognition).</div></front></TEI><hal api="V3"><titleStmt><title xml:lang="fr">A character degradation model for grayscale ancient document images</title><author role="aut"><persName><forename type="first">Van Cuong</forename><surname>Kieu</surname></persName><email>vkieu@univ-lr.fr</email><idno type="halauthor">1013436</idno><affiliation ref="#struct-3102"></affiliation><affiliation ref="#struct-40831"></affiliation></author><author role="aut"><persName><forename type="first">Jean-Philippe</forename><surname>Domenger</surname></persName><email>domenger@labri.fr</email><idno type="halauthor">315378</idno><affiliation ref="#struct-3102"></affiliation></author><author role="aut"><persName><forename type="first">Rémy</forename><surname>Mullot</surname></persName><email>remy.mullot@univ-lr.fr</email><idno type="halauthor">455566</idno><affiliation ref="#struct-40831"></affiliation></author><author role="aut"><persName><forename type="first">Nicholas</forename><surname>Journet</surname></persName><email>journet@labri.fr</email><idno type="halauthor">498093</idno><affiliation ref="#struct-3102"></affiliation></author><author role="aut"><persName><forename type="first">Muriel</forename><surname>Visani</surname></persName><email>muriel.visani@univ-lr.fr</email><idno type="halauthor">449621</idno><affiliation ref="#struct-40831"></affiliation></author><editor role="depositor"><persName><forename>Van Cuong</forename><surname>Kieu</surname></persName><email>vkieu@univ-lr.fr</email></editor><funder>ANR</funder></titleStmt><editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2014-04-21 14:25:21</date><date type="whenWritten">2012-07-13</date><date type="whenModified">2014-06-13 16:38:33</date><date type="whenReleased">2014-06-13 16:38:33</date><date type="whenProduced">2012-11-11</date><date type="whenEndEmbargoed">2014-04-21</date><ref type="file" target="https://hal.archives-ouvertes.fr/hal-00979057/document"><date notBefore="2014-04-21"></date></ref><ref type="file" subtype="author" n="1" target="https://hal.archives-ouvertes.fr/hal-00979057/file/cifed.pdf"><date notBefore="2014-04-21"></date></ref></edition><respStmt><resp>contributor</resp><name key="193931"><persName><forename>Van Cuong</forename><surname>Kieu</surname></persName><email>vkieu@univ-lr.fr</email></name></respStmt></editionStmt><publicationStmt><distributor>CCSD</distributor><idno type="halId">hal-00979057</idno><idno type="halUri">https://hal.archives-ouvertes.fr/hal-00979057</idno><idno type="halBibtex">kieu:hal-00979057</idno><idno type="halRefHtml">21st International Conference on Pattern Recognition (ICPR), Nov 2012, France</idno><idno type="halRef">21st International Conference on Pattern Recognition (ICPR), Nov 2012, France</idno></publicationStmt><seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno><idno type="stamp" n="UNIV-BORDEAUX1">Université Bordeaux I - Sciences Technologies</idno><idno type="stamp" n="UNIV-BORDEAUX2">Université Victor Segalen - Bordeaux II</idno><idno type="stamp" n="UNIV-ROCHELLE">Université de la Rochelle</idno><idno type="stamp" n="LABRI">Laboratoire Bordelais de Recherche en Informatique</idno><idno type="stamp" n="UNIV-BORDEAUX">Université de Bordeaux</idno></seriesStmt><notesStmt><note type="audience" n="1">Not set</note><note type="invited" n="1">Yes</note><note type="popular" n="0">No</note><note type="peer" n="1">Yes</note><note type="proceedings" n="1">Yes</note></notesStmt><sourceDesc><biblStruct><analytic><title xml:lang="fr">A character degradation model for grayscale ancient document images</title><author role="aut"><persName><forename type="first">Van Cuong</forename><surname>Kieu</surname></persName><email>vkieu@univ-lr.fr</email><idno type="halAuthorId">1013436</idno><affiliation ref="#struct-3102"></affiliation><affiliation ref="#struct-40831"></affiliation></author><author role="aut"><persName><forename type="first">Jean-Philippe</forename><surname>Domenger</surname></persName><email>domenger@labri.fr</email><idno type="halAuthorId">315378</idno><affiliation ref="#struct-3102"></affiliation></author><author role="aut"><persName><forename type="first">Rémy</forename><surname>Mullot</surname></persName><email>remy.mullot@univ-lr.fr</email><idno type="halAuthorId">455566</idno><affiliation ref="#struct-40831"></affiliation></author><author role="aut"><persName><forename type="first">Nicholas</forename><surname>Journet</surname></persName><email>journet@labri.fr</email><idno type="halAuthorId">498093</idno><affiliation ref="#struct-3102"></affiliation></author><author role="aut"><persName><forename type="first">Muriel</forename><surname>Visani</surname></persName><email>muriel.visani@univ-lr.fr</email><idno type="halAuthorId">449621</idno><affiliation ref="#struct-40831"></affiliation></author></analytic><monogr><meeting><title>21st International Conference on Pattern Recognition (ICPR)</title><date type="start">2012-11-11</date><date type="end">2012-11-15</date><country key="FR">France</country></meeting><imprint></imprint></monogr></biblStruct></sourceDesc><profileDesc><langUsage><language ident="en">English</language></langUsage><textClass><keywords scheme="author"><term xml:lang="en">document degradation model</term><term xml:lang="en">synthetic image generation</term><term xml:lang="en">performance evaluation</term></keywords><classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</classCode><classCode scheme="halDomain" n="info.info-gr">Computer Science [cs]/Graphics [cs.GR]</classCode><classCode scheme="halTypology" n="COMM">Conference papers</classCode></textClass><abstract xml:lang="en">Kanungo noise model is widely used to test the robustness of different binary document image analysis methods towards noise. This model only works with binary images while most document images are in grayscale. Because binarizing a document image might degrade its contents and lead to a loss of information, more and more researchers are currently focusing on segmentation-free methods (Angelika et al [2]). Thus, we propose a local noise model for grayscale images. Its main principle is to locally degrade the image in the neighbourhoods of "seed-points" selected close to the character boundary. These points define the center of "noise regions". The pixel values inside the noise region are modified by a Gaussian random distribution to make the final result more realistic. While Kanungo noise models scanning artifacts, our model simulates degradations due to the age of the document itself and printing/writing process such as ink splotches, white specks or streaks. It is very easy for users to parameterize and create a set of benchmark databases with an increasing level of noise. These databases will further be used to test the robustness of different grayscale document image analysis methods (i.e. text line segmentation, OCR, handwriting recognition).</abstract><particDesc><org type="consortium">DIGIDOC</org></particDesc></profileDesc></hal></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Hal/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000135 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Corpus/biblio.hfd -nk 000135 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Hal
|étape= Corpus
|type= RBID
|clé= Hal:hal-00979057
|texte= A character degradation model for grayscale ancient document images
}}
| This area was generated with Dilib version V0.6.32. |  |