{"id":"https://openalex.org/W1990899722","doi":"https://doi.org/10.1145/1815330.1815339","title":"Table detection in heterogeneous documents","display_name":"Table detection in heterogeneous documents","publication_year":2010,"publication_date":"2010-06-09","ids":{"openalex":"https://openalex.org/W1990899722","doi":"https://doi.org/10.1145/1815330.1815339","mag":"1990899722"},"language":"en","primary_location":{"id":"doi:10.1145/1815330.1815339","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003304863","display_name":"Faisal Shafait","orcid":"https://orcid.org/0000-0002-0922-0566"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Faisal Shafait","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI GmbH), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI GmbH), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110962620","display_name":"Ray Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ray Smith","raw_affiliation_strings":["Google Inc., CA","Google, Inc., CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc., CA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003304863"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":4.5255,"has_fulltext":false,"cited_by_count":110,"citation_normalized_percentile":{"value":0.94980261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8313990831375122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8192323446273804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6619400978088379},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.5974920392036438},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5954863429069519},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.54442298412323},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5364310145378113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4485361874103546},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.44642093777656555},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.4281400144100189},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39842450618743896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2728309631347656},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.22705134749412537},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19534558057785034}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8313990831375122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192323446273804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6619400978088379},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.5974920392036438},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5954863429069519},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.54442298412323},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5364310145378113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4485361874103546},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.44642093777656555},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.4281400144100189},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39842450618743896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2728309631347656},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.22705134749412537},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19534558057785034},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1815330.1815339","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/c5b1d3fa-0025-495f-a42c-ef8cf89636aa","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/c5b1d3fa-0025-495f-a42c-ef8cf89636aa","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shafait , F & Smith , R 2010 , Table detection in heterogeneous documents . in Proceedings of the 9th IAPR International Workshop on Document Analysis Systems . vol. 1 , Association for Computing Machinery (ACM) , USA , pp. 65-72 , 9th IAPR International Workshop on Document Analysis Systems , Boston , United States , 9/06/10 . https://doi.org/10.1145/1815330.1815339","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.7400","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.7400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csse.uwa.edu.au/~shafait/papers/Shafait-Table-Detection-DAS10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W56465887","https://openalex.org/W171088530","https://openalex.org/W779888475","https://openalex.org/W1612759903","https://openalex.org/W1970549718","https://openalex.org/W1971336721","https://openalex.org/W1980609290","https://openalex.org/W2001642682","https://openalex.org/W2056797079","https://openalex.org/W2098218583","https://openalex.org/W2117462434","https://openalex.org/W2119476919","https://openalex.org/W2125962095","https://openalex.org/W2129265797","https://openalex.org/W2143633261","https://openalex.org/W2158295445","https://openalex.org/W2166323498","https://openalex.org/W2168459394","https://openalex.org/W6602320115"],"related_works":["https://openalex.org/W2131730163","https://openalex.org/W4223967348","https://openalex.org/W2079703172","https://openalex.org/W2038329042","https://openalex.org/W1988371238","https://openalex.org/W2573990671","https://openalex.org/W182542749","https://openalex.org/W2000372441","https://openalex.org/W2051072213","https://openalex.org/W1950646998"],"abstract_inverted_index":{"Detecting":[0],"tables":[1,11,28,42],"in":[2,24,29,43,116],"document":[3,31,106],"images":[4,107],"is":[5,92],"important":[6,13],"since":[7],"not":[8,50],"only":[9],"do":[10,49],"contain":[12],"information,":[14],"but":[15],"also":[16],"most":[17],"of":[18,27,46,89,96,102,123],"the":[19,25,30,90,97,103,119],"layout":[20],"analysis":[21],"methods":[22],"fail":[23],"presence":[26],"image.":[32],"Existing":[33],"approaches":[34],"for":[35,64],"table":[36,65,120],"detection":[37,66,121],"mainly":[38],"focus":[39],"on":[40,53,73,105],"detecting":[41],"single":[44],"columns":[45],"text":[47],"and":[48],"work":[51],"reliably":[52],"documents":[54,74],"with":[55,69,75],"varying":[56,76],"layouts.":[57],"This":[58],"paper":[59],"presents":[60],"a":[61,70,124],"practical":[62],"algorithm":[63,91,104],"that":[67],"works":[68],"high":[71],"accuracy":[72],"layouts":[77],"(company":[78],"reports,":[79],"newspaper":[80],"articles,":[81],"magazine":[82],"pages,":[83],"...).":[84],"An":[85],"open":[86],"source":[87],"implementation":[88],"provided":[93],"as":[94],"part":[95],"Tesseract":[98],"OCR":[99,126],"engine.":[100],"Evaluation":[101],"from":[108],"publicly":[109],"available":[110],"UNLV":[111],"dataset":[112],"shows":[113],"competitive":[114],"performance":[115],"comparison":[117],"to":[118],"module":[122],"commercial":[125],"system.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}