Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique
This paper presents a new method to restore a particular type of degradation related to ancient document images. This degradation, referred to as “bleed-through”, is due to the paper porosity, the chemical quality of the ink, or the conditions of digitalization. It appears as marks degrading the rea...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 49 |
|---|---|
| container_issue | |
| container_start_page | 38 |
| container_title | |
| container_volume | |
| creator | Fadoua, Drira Le Bourgeois, Frank Emptoz, Hubert |
| description | This paper presents a new method to restore a particular type of degradation related to ancient document images. This degradation, referred to as “bleed-through”, is due to the paper porosity, the chemical quality of the ink, or the conditions of digitalization. It appears as marks degrading the readability of the document image. Our purpose consists then in removing these marks to improve readability. The proposed method is based on a recursive unsupervised segmentation approach applied on the decorrelated data space by the principal component analysis. It generates a binary tree that only the leaves images satisfying a certain condition on their logarithmic histogram are processed. Some experiments, done on real ancient document images provided by the archives of “Chatillon-Chalaronne” illustrate the effectiveness of the suggested method. |
| doi_str_mv | 10.1007/11669487_4 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>hal_pasca</sourceid><recordid>TN_cdi_pascalfrancis_primary_19937932</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_HAL_hal_01592837v1</sourcerecordid><originalsourceid>FETCH-LOGICAL-c329t-aed3e7ae286cce213017d2f730878fb7396500c31be2241c859522fe8963f4a3</originalsourceid><addsrcrecordid>eNpFkUtP6zAQhc1Lojw2_AJvkGCRi8eTxPYSCvdSqRISKmvLdSatIU2K3VTi35OqiDuLGWnmO2cxh7ErEH9ACHUHUJYm18rmB-wMi1yghELpQzaCEiBDzM3R72Fox2wkUMjMqBxP2WVK72IoBCV1MWLNK6VNF0O74JP2gz80RFU2W8auXyz5Iy2iq6jij53vV9Ru-GTlFpT4W9oJHH8l38cUtsTf2tSvKW5DGvBx41IKdfBuE7qWz8gv2_DZ0wU7qV2T6PJnnrPZ36fZ-DmbvvybjO-nmUdpNpmjCkk5krr0niSgAFXJWqHQStdzhaYshPAIc5IyB68LU0hZkzYl1rnDc3a7t126xq5jWLn4ZTsX7PP91O52AgojNaotDOz1nl275F1TR9f6kH5VYAwqg3LgbvZcWu-eRdHOu-4jWRB2l4r9nwp-A1ifeW4</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique</title><source>Springer Books</source><creator>Fadoua, Drira ; Le Bourgeois, Frank ; Emptoz, Hubert</creator><contributor>Bunke, Horst ; Spitz, A. Lawrence</contributor><creatorcontrib>Fadoua, Drira ; Le Bourgeois, Frank ; Emptoz, Hubert ; Bunke, Horst ; Spitz, A. Lawrence</creatorcontrib><description>This paper presents a new method to restore a particular type of degradation related to ancient document images. This degradation, referred to as “bleed-through”, is due to the paper porosity, the chemical quality of the ink, or the conditions of digitalization. It appears as marks degrading the readability of the document image. Our purpose consists then in removing these marks to improve readability. The proposed method is based on a recursive unsupervised segmentation approach applied on the decorrelated data space by the principal component analysis. It generates a binary tree that only the leaves images satisfying a certain condition on their logarithmic histogram are processed. Some experiments, done on real ancient document images provided by the archives of “Chatillon-Chalaronne” illustrate the effectiveness of the suggested method.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540321403</identifier><identifier>ISBN: 9783540321408</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 3540321578</identifier><identifier>EISBN: 9783540321576</identifier><identifier>DOI: 10.1007/11669487_4</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Computer Science ; Computer science; control theory; systems ; Document Image ; Exact sciences and technology ; Handwritten Document ; Pattern recognition. Digital image processing. Computational geometry ; Recursive Approach ; Restoration Method ; Thresholding Technique</subject><ispartof>Document Analysis Systems VII, 2006, p.38-49</ispartof><rights>Springer-Verlag Berlin Heidelberg 2006</rights><rights>2008 INIST-CNRS</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c329t-aed3e7ae286cce213017d2f730878fb7396500c31be2241c859522fe8963f4a3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11669487_4$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11669487_4$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,776,777,781,786,787,790,882,27906,38236,41423,42492</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=19937932$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://hal.science/hal-01592837$$DView record in HAL$$Hfree_for_read</backlink></links><search><contributor>Bunke, Horst</contributor><contributor>Spitz, A. Lawrence</contributor><creatorcontrib>Fadoua, Drira</creatorcontrib><creatorcontrib>Le Bourgeois, Frank</creatorcontrib><creatorcontrib>Emptoz, Hubert</creatorcontrib><title>Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique</title><title>Document Analysis Systems VII</title><description>This paper presents a new method to restore a particular type of degradation related to ancient document images. This degradation, referred to as “bleed-through”, is due to the paper porosity, the chemical quality of the ink, or the conditions of digitalization. It appears as marks degrading the readability of the document image. Our purpose consists then in removing these marks to improve readability. The proposed method is based on a recursive unsupervised segmentation approach applied on the decorrelated data space by the principal component analysis. It generates a binary tree that only the leaves images satisfying a certain condition on their logarithmic histogram are processed. Some experiments, done on real ancient document images provided by the archives of “Chatillon-Chalaronne” illustrate the effectiveness of the suggested method.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer Science</subject><subject>Computer science; control theory; systems</subject><subject>Document Image</subject><subject>Exact sciences and technology</subject><subject>Handwritten Document</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Recursive Approach</subject><subject>Restoration Method</subject><subject>Thresholding Technique</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540321403</isbn><isbn>9783540321408</isbn><isbn>3540321578</isbn><isbn>9783540321576</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpFkUtP6zAQhc1Lojw2_AJvkGCRi8eTxPYSCvdSqRISKmvLdSatIU2K3VTi35OqiDuLGWnmO2cxh7ErEH9ACHUHUJYm18rmB-wMi1yghELpQzaCEiBDzM3R72Fox2wkUMjMqBxP2WVK72IoBCV1MWLNK6VNF0O74JP2gz80RFU2W8auXyz5Iy2iq6jij53vV9Ru-GTlFpT4W9oJHH8l38cUtsTf2tSvKW5DGvBx41IKdfBuE7qWz8gv2_DZ0wU7qV2T6PJnnrPZ36fZ-DmbvvybjO-nmUdpNpmjCkk5krr0niSgAFXJWqHQStdzhaYshPAIc5IyB68LU0hZkzYl1rnDc3a7t126xq5jWLn4ZTsX7PP91O52AgojNaotDOz1nl275F1TR9f6kH5VYAwqg3LgbvZcWu-eRdHOu-4jWRB2l4r9nwp-A1ifeW4</recordid><startdate>20060101</startdate><enddate>20060101</enddate><creator>Fadoua, Drira</creator><creator>Le Bourgeois, Frank</creator><creator>Emptoz, Hubert</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope><scope>1XC</scope></search><sort><creationdate>20060101</creationdate><title>Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique</title><author>Fadoua, Drira ; Le Bourgeois, Frank ; Emptoz, Hubert</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c329t-aed3e7ae286cce213017d2f730878fb7396500c31be2241c859522fe8963f4a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer Science</topic><topic>Computer science; control theory; systems</topic><topic>Document Image</topic><topic>Exact sciences and technology</topic><topic>Handwritten Document</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Recursive Approach</topic><topic>Restoration Method</topic><topic>Thresholding Technique</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fadoua, Drira</creatorcontrib><creatorcontrib>Le Bourgeois, Frank</creatorcontrib><creatorcontrib>Emptoz, Hubert</creatorcontrib><collection>Pascal-Francis</collection><collection>Hyper Article en Ligne (HAL)</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fadoua, Drira</au><au>Le Bourgeois, Frank</au><au>Emptoz, Hubert</au><au>Bunke, Horst</au><au>Spitz, A. Lawrence</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique</atitle><btitle>Document Analysis Systems VII</btitle><date>2006-01-01</date><risdate>2006</risdate><spage>38</spage><epage>49</epage><pages>38-49</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540321403</isbn><isbn>9783540321408</isbn><eisbn>3540321578</eisbn><eisbn>9783540321576</eisbn><abstract>This paper presents a new method to restore a particular type of degradation related to ancient document images. This degradation, referred to as “bleed-through”, is due to the paper porosity, the chemical quality of the ink, or the conditions of digitalization. It appears as marks degrading the readability of the document image. Our purpose consists then in removing these marks to improve readability. The proposed method is based on a recursive unsupervised segmentation approach applied on the decorrelated data space by the principal component analysis. It generates a binary tree that only the leaves images satisfying a certain condition on their logarithmic histogram are processed. Some experiments, done on real ancient document images provided by the archives of “Chatillon-Chalaronne” illustrate the effectiveness of the suggested method.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11669487_4</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Document Analysis Systems VII, 2006, p.38-49 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_19937932 |
| source | Springer Books |
| subjects | Applied sciences Artificial intelligence Computer Science Computer science control theory systems Document Image Exact sciences and technology Handwritten Document Pattern recognition. Digital image processing. Computational geometry Recursive Approach Restoration Method Thresholding Technique |
| title | Restoring Ink Bleed-Through Degraded Document Images Using a Recursive Unsupervised Classification Technique |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T06%3A32%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-hal_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Restoring%20Ink%20Bleed-Through%20Degraded%20Document%20Images%20Using%20a%20Recursive%20Unsupervised%20Classification%20Technique&rft.btitle=Document%20Analysis%20Systems%20VII&rft.au=Fadoua,%20Drira&rft.date=2006-01-01&rft.spage=38&rft.epage=49&rft.pages=38-49&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540321403&rft.isbn_list=9783540321408&rft_id=info:doi/10.1007/11669487_4&rft_dat=%3Chal_pasca%3Eoai_HAL_hal_01592837v1%3C/hal_pasca%3E%3Curl%3E%3C/url%3E&rft.eisbn=3540321578&rft.eisbn_list=9783540321576&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |