Restoring warped document images through 3D shape modeling
Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence 2006-02, Vol.28 (2), p.195-208 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 208 |
|---|---|
| container_issue | 2 |
| container_start_page | 195 |
| container_title | IEEE transactions on pattern analysis and machine intelligence |
| container_volume | 28 |
| creator | Tan, Chew Lim Zhang, Li Zhang, Zheng Xia, Tao |
| description | Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly. |
| doi_str_mv | 10.1109/TPAMI.2006.40 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_16468617</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1561180</ieee_id><sourcerecordid>67643428</sourcerecordid><originalsourceid>FETCH-LOGICAL-c431t-6cce2e1a0043b50e12e3f8462940b773cc9f78679aa03966d18de9118e0f27be3</originalsourceid><addsrcrecordid>eNqF0ctrGzEQB2BRWhrH7bGnQlkKSU7rjB6rR24mb0hJKOlZyNpZe8M-HMlL6H9fbWww5NCcdNA3w8z8CPlGYUYpmNPHh_mv2xkDkDMBH8iEGm5yXnDzkUyASpZrzfQBOYzxCYCKAvhnckClkFpSNSFnvzFu-lB3y-zFhTWWWdn7ocVuk9WtW2LMNqvQD8tVxi-yuHJrzNq-xCYVfCGfKtdE_Lp7p-TP1eXj-U1-d399ez6_y73gdJNL75EhdQCCLwpAypBXWkhmBCyU4t6bSmmpjHPAjZQl1SUaSjVCxdQC-ZScbPuuQ_88pHFtW0ePTeM67IdotZGMMUibTcnxf6VUUnDB9LuQaSgYL2SCP9_Ap34IXVrXalkoLqgeUb5FPvQxBqzsOqTjhb-Wgh1Dsq8h2TEkK8Yxf-yaDosWy73epZLA0Q646F1TBdf5Ou6dGu-kiuS-b12NiPvvQqbrAf8HjiyfrA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>865734186</pqid></control><display><type>article</type><title>Restoring warped document images through 3D shape modeling</title><source>IEEE Electronic Library (IEL)</source><creator>Tan, Chew Lim ; Zhang, Li ; Zhang, Zheng ; Xia, Tao</creator><creatorcontrib>Tan, Chew Lim ; Zhang, Li ; Zhang, Zheng ; Xia, Tao</creatorcontrib><description>Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>DOI: 10.1109/TPAMI.2006.40</identifier><identifier>PMID: 16468617</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Algorithms ; Applied sciences ; Artificial Intelligence ; Automatic Data Processing - methods ; Computer Graphics ; Computer science; control theory; systems ; Computer Simulation ; Distortion ; document image analysis ; Documentation - methods ; Exact sciences and technology ; Geometrical optics ; image distortion ; Image Enhancement - methods ; Image Interpretation, Computer-Assisted - methods ; Image restoration ; image warping ; Imaging, Three-Dimensional - methods ; Index Terms- Document image restoration ; Information Storage and Retrieval - methods ; Light sources ; Mathematical models ; Models, Theoretical ; OCR improvement ; Optical character recognition ; Optical character recognition software ; Optical distortion ; Optical reflection ; Pattern Recognition, Automated - methods ; Pattern recognition. Digital image processing. Computational geometry ; Reproducibility of Results ; Restoration ; Sensitivity and Specificity ; Shading ; Shape ; shape from shading ; Solid modeling ; Surface reconstruction ; Three dimensional</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 2006-02, Vol.28 (2), p.195-208</ispartof><rights>2006 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2006</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c431t-6cce2e1a0043b50e12e3f8462940b773cc9f78679aa03966d18de9118e0f27be3</citedby><cites>FETCH-LOGICAL-c431t-6cce2e1a0043b50e12e3f8462940b773cc9f78679aa03966d18de9118e0f27be3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1561180$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1561180$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=17396675$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/16468617$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tan, Chew Lim</creatorcontrib><creatorcontrib>Zhang, Li</creatorcontrib><creatorcontrib>Zhang, Zheng</creatorcontrib><creatorcontrib>Xia, Tao</creatorcontrib><title>Restoring warped document images through 3D shape modeling</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><description>Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.</description><subject>Algorithms</subject><subject>Applied sciences</subject><subject>Artificial Intelligence</subject><subject>Automatic Data Processing - methods</subject><subject>Computer Graphics</subject><subject>Computer science; control theory; systems</subject><subject>Computer Simulation</subject><subject>Distortion</subject><subject>document image analysis</subject><subject>Documentation - methods</subject><subject>Exact sciences and technology</subject><subject>Geometrical optics</subject><subject>image distortion</subject><subject>Image Enhancement - methods</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>Image restoration</subject><subject>image warping</subject><subject>Imaging, Three-Dimensional - methods</subject><subject>Index Terms- Document image restoration</subject><subject>Information Storage and Retrieval - methods</subject><subject>Light sources</subject><subject>Mathematical models</subject><subject>Models, Theoretical</subject><subject>OCR improvement</subject><subject>Optical character recognition</subject><subject>Optical character recognition software</subject><subject>Optical distortion</subject><subject>Optical reflection</subject><subject>Pattern Recognition, Automated - methods</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Reproducibility of Results</subject><subject>Restoration</subject><subject>Sensitivity and Specificity</subject><subject>Shading</subject><subject>Shape</subject><subject>shape from shading</subject><subject>Solid modeling</subject><subject>Surface reconstruction</subject><subject>Three dimensional</subject><issn>0162-8828</issn><issn>1939-3539</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2006</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNqF0ctrGzEQB2BRWhrH7bGnQlkKSU7rjB6rR24mb0hJKOlZyNpZe8M-HMlL6H9fbWww5NCcdNA3w8z8CPlGYUYpmNPHh_mv2xkDkDMBH8iEGm5yXnDzkUyASpZrzfQBOYzxCYCKAvhnckClkFpSNSFnvzFu-lB3y-zFhTWWWdn7ocVuk9WtW2LMNqvQD8tVxi-yuHJrzNq-xCYVfCGfKtdE_Lp7p-TP1eXj-U1-d399ez6_y73gdJNL75EhdQCCLwpAypBXWkhmBCyU4t6bSmmpjHPAjZQl1SUaSjVCxdQC-ZScbPuuQ_88pHFtW0ePTeM67IdotZGMMUibTcnxf6VUUnDB9LuQaSgYL2SCP9_Ap34IXVrXalkoLqgeUb5FPvQxBqzsOqTjhb-Wgh1Dsq8h2TEkK8Yxf-yaDosWy73epZLA0Q646F1TBdf5Ou6dGu-kiuS-b12NiPvvQqbrAf8HjiyfrA</recordid><startdate>20060201</startdate><enddate>20060201</enddate><creator>Tan, Chew Lim</creator><creator>Zhang, Li</creator><creator>Zhang, Zheng</creator><creator>Xia, Tao</creator><general>IEEE</general><general>IEEE Computer Society</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20060201</creationdate><title>Restoring warped document images through 3D shape modeling</title><author>Tan, Chew Lim ; Zhang, Li ; Zhang, Zheng ; Xia, Tao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c431t-6cce2e1a0043b50e12e3f8462940b773cc9f78679aa03966d18de9118e0f27be3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Algorithms</topic><topic>Applied sciences</topic><topic>Artificial Intelligence</topic><topic>Automatic Data Processing - methods</topic><topic>Computer Graphics</topic><topic>Computer science; control theory; systems</topic><topic>Computer Simulation</topic><topic>Distortion</topic><topic>document image analysis</topic><topic>Documentation - methods</topic><topic>Exact sciences and technology</topic><topic>Geometrical optics</topic><topic>image distortion</topic><topic>Image Enhancement - methods</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>Image restoration</topic><topic>image warping</topic><topic>Imaging, Three-Dimensional - methods</topic><topic>Index Terms- Document image restoration</topic><topic>Information Storage and Retrieval - methods</topic><topic>Light sources</topic><topic>Mathematical models</topic><topic>Models, Theoretical</topic><topic>OCR improvement</topic><topic>Optical character recognition</topic><topic>Optical character recognition software</topic><topic>Optical distortion</topic><topic>Optical reflection</topic><topic>Pattern Recognition, Automated - methods</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Reproducibility of Results</topic><topic>Restoration</topic><topic>Sensitivity and Specificity</topic><topic>Shading</topic><topic>Shape</topic><topic>shape from shading</topic><topic>Solid modeling</topic><topic>Surface reconstruction</topic><topic>Three dimensional</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tan, Chew Lim</creatorcontrib><creatorcontrib>Zhang, Li</creatorcontrib><creatorcontrib>Zhang, Zheng</creatorcontrib><creatorcontrib>Xia, Tao</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tan, Chew Lim</au><au>Zhang, Li</au><au>Zhang, Zheng</au><au>Xia, Tao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Restoring warped document images through 3D shape modeling</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><date>2006-02-01</date><risdate>2006</risdate><volume>28</volume><issue>2</issue><spage>195</spage><epage>208</epage><pages>195-208</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><coden>ITPIDJ</coden><abstract>Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><pmid>16468617</pmid><doi>10.1109/TPAMI.2006.40</doi><tpages>14</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0162-8828 |
| ispartof | IEEE transactions on pattern analysis and machine intelligence, 2006-02, Vol.28 (2), p.195-208 |
| issn | 0162-8828 1939-3539 |
| language | eng |
| recordid | cdi_pubmed_primary_16468617 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Applied sciences Artificial Intelligence Automatic Data Processing - methods Computer Graphics Computer science control theory systems Computer Simulation Distortion document image analysis Documentation - methods Exact sciences and technology Geometrical optics image distortion Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Image restoration image warping Imaging, Three-Dimensional - methods Index Terms- Document image restoration Information Storage and Retrieval - methods Light sources Mathematical models Models, Theoretical OCR improvement Optical character recognition Optical character recognition software Optical distortion Optical reflection Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Reproducibility of Results Restoration Sensitivity and Specificity Shading Shape shape from shading Solid modeling Surface reconstruction Three dimensional |
| title | Restoring warped document images through 3D shape modeling |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T18%3A17%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Restoring%20warped%20document%20images%20through%203D%20shape%20modeling&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Tan,%20Chew%20Lim&rft.date=2006-02-01&rft.volume=28&rft.issue=2&rft.spage=195&rft.epage=208&rft.pages=195-208&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/TPAMI.2006.40&rft_dat=%3Cproquest_RIE%3E67643428%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=865734186&rft_id=info:pmid/16468617&rft_ieee_id=1561180&rfr_iscdi=true |