{"id":"https://openalex.org/W1511676561","doi":"https://doi.org/10.1007/978-3-540-28640-0_20","title":"Layout and Content Extraction for PDF Documents","display_name":"Layout and Content Extraction for PDF Documents","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1511676561","doi":"https://doi.org/10.1007/978-3-540-28640-0_20","mag":"1511676561"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-28640-0_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-28640-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5010214831","display_name":"Hui Chao","orcid":"https://orcid.org/0000-0003-4153-5303"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Chao","raw_affiliation_strings":["Hewlett-Packard Laboratories, 1501 Page Mill Road, ms 1203, Palo Alto, CA, 95129, USA","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, 1501 Page Mill Road, ms 1203, Palo Alto, CA, 95129, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077871435","display_name":"Jian Fan","orcid":"https://orcid.org/0000-0001-5009-9588"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Fan","raw_affiliation_strings":["Hewlett-Packard Laboratories, 1501 Page Mill Road, ms 1203, Palo Alto, CA, 95129, USA","Hewlett-Packard Labs,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, 1501 Page Mill Road, ms 1203, Palo Alto, CA, 95129, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Labs,#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.9251,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.91332587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.875482439994812},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8027828931808472},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7488139271736145},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6867755651473999},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6580151915550232},{"id":"https://openalex.org/keywords/well-formed-document","display_name":"Well-formed document","score":0.6223232746124268},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4307381808757782},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42874884605407715},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42846623063087463},{"id":"https://openalex.org/keywords/electronic-document","display_name":"Electronic document","score":0.42222195863723755},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.42191582918167114},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41769731044769287},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.35465896129608154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1728213131427765},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07672137022018433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875482439994812},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8027828931808472},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7488139271736145},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6867755651473999},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6580151915550232},{"id":"https://openalex.org/C137441365","wikidata":"https://www.wikidata.org/wiki/Q7981054","display_name":"Well-formed document","level":5,"score":0.6223232746124268},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4307381808757782},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42874884605407715},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42846623063087463},{"id":"https://openalex.org/C2778315425","wikidata":"https://www.wikidata.org/wiki/Q694975","display_name":"Electronic document","level":2,"score":0.42222195863723755},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.42191582918167114},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41769731044769287},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.35465896129608154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1728213131427765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07672137022018433},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-28640-0_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-28640-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1488587987","https://openalex.org/W1551340397","https://openalex.org/W1557714760","https://openalex.org/W1775742847","https://openalex.org/W1801594279","https://openalex.org/W1898956034","https://openalex.org/W2011239367","https://openalex.org/W2014959772","https://openalex.org/W2083506645","https://openalex.org/W2100735443","https://openalex.org/W2116771527","https://openalex.org/W2129879687","https://openalex.org/W2133115184","https://openalex.org/W2134533274","https://openalex.org/W2135085165","https://openalex.org/W2138064184","https://openalex.org/W2144209937","https://openalex.org/W2163951260","https://openalex.org/W2982209274","https://openalex.org/W4298410530"],"related_works":["https://openalex.org/W2142128377","https://openalex.org/W2089356193","https://openalex.org/W2079569022","https://openalex.org/W3151136357","https://openalex.org/W1560643532","https://openalex.org/W1971234693","https://openalex.org/W1983284692","https://openalex.org/W2244000356","https://openalex.org/W4238415164","https://openalex.org/W2039135287"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
