{"id":"https://openalex.org/W2142809404","doi":"https://doi.org/10.1109/icdar.2007.4377094","title":"Table Recognition and Understanding from PDF Files","display_name":"Table Recognition and Understanding from PDF Files","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2142809404","doi":"https://doi.org/10.1109/icdar.2007.4377094","mag":"2142809404"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4377094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377094","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","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/A5102884920","display_name":"Tarek M. Hassan","orcid":"https://orcid.org/0000-0003-0278-3937"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"T. Hassan","raw_affiliation_strings":["Institute of Information Systems, University of Technology, Vienna, Wien, Austria","Vienna University of Technology, Vienna#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, University of Technology, Vienna, Wien, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of Technology, Vienna#TAB#","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055923468","display_name":"Robert Baumgartner","orcid":"https://orcid.org/0000-0003-0899-4903"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"R. Baumgartner","raw_affiliation_strings":["Institute of Information Systems, University of Technology, Vienna, Wien, Austria","Vienna University of Technology, Vienna#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Information Systems, University of Technology, Vienna, Wien, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of Technology, Vienna#TAB#","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102884920"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":7.2266,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97688647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1143","last_page":"1147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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/T12357","display_name":"Digital Media Forensic Detection","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"}}],"keywords":[{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.9047499895095825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.815488338470459},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7672879099845886},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6517666578292847},{"id":"https://openalex.org/keywords/row-and-column-spaces","display_name":"Row and column spaces","score":0.6166446208953857},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.5770990252494812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49196216464042664},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4811759889125824},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.426650732755661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.414674311876297},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40170934796333313},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38105714321136475},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17984163761138916}],"concepts":[{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.9047499895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815488338470459},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7672879099845886},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6517666578292847},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.6166446208953857},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.5770990252494812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49196216464042664},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4811759889125824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.426650732755661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414674311876297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40170934796333313},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38105714321136475},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17984163761138916},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4377094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4377094","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W141724566","https://openalex.org/W2106110775","https://openalex.org/W2121061496","https://openalex.org/W2149546672","https://openalex.org/W2165382068","https://openalex.org/W3023264106","https://openalex.org/W6605756948"],"related_works":["https://openalex.org/W3123744736","https://openalex.org/W3121299875","https://openalex.org/W1566754092","https://openalex.org/W4281971614","https://openalex.org/W1992086467","https://openalex.org/W2005695153","https://openalex.org/W2011918259","https://openalex.org/W2741429854","https://openalex.org/W4214886263","https://openalex.org/W3007479582"],"abstract_inverted_index":{"We":[0,40,60,83],"propose":[1,61],"a":[2,34,58,106],"flexible":[3],"method":[4],"for":[5,23,65,114],"detecting":[6],"and":[7,29,55,68,75,81,91,93],"understanding":[8],"tables":[9,74],"in":[10,45,104],"PDF":[11,49],"files,":[12],"which":[13],"is":[14,30,102],"not":[15],"reliant":[16],"upon":[17],"one":[18],"particular":[19],"feature":[20],"being":[21],"present,":[22],"example":[24],"ruling":[25],"lines":[26,54],"or":[27],"indentations,":[28],"therefore":[31],"applicable":[32],"to":[33,71,87],"wide":[35,107],"variety":[36,108],"of":[37,109],"visual":[38],"presentations.":[39],"describe":[41],"the":[42,47],"steps":[43],"required":[44],"transforming":[46],"low-level":[48],"instructions":[50],"into":[51,112],"text":[52],"segments,":[53],"boxes":[56],"on":[57],"page.":[59],"three":[62],"different":[63],"classifications":[64],"published":[66],"tables,":[67],"develop":[69],"methods":[70],"detect":[72],"these":[73],"correctly":[76],"identify":[77],"their":[78],"respective":[79],"rows":[80,90],"columns.":[82],"also":[84],"explain":[85],"how":[86],"recognize":[88],"spanning":[89],"columns,":[92],"multi-line":[94],"rows.":[95],"Experimental":[96],"results":[97],"show":[98],"that":[99],"our":[100],"algorithm":[101],"effective":[103],"converting":[105],"tabular":[110],"presentations":[111],"HTML":[113],"information":[115],"extraction":[116],"purposes.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}