{"id":"https://openalex.org/W2120147695","doi":"https://doi.org/10.1109/icdar.2003.1227635","title":"Correcting the document layout: a machine learning approach","display_name":"Correcting the document layout: a machine learning approach","publication_year":2004,"publication_date":"2004-02-03","ids":{"openalex":"https://openalex.org/W2120147695","doi":"https://doi.org/10.1109/icdar.2003.1227635","mag":"2120147695"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},"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/A5035789137","display_name":"Donato Malerba","orcid":"https://orcid.org/0000-0001-8432-4608"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"D. Malerba","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","Dipt. di Informatica, Universita degli Studi di Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipt. di Informatica, Universita degli Studi di Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035635558","display_name":"Floriana Esposito","orcid":"https://orcid.org/0000-0002-1075-3239"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"F. Esposito","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","Dipt. di Informatica, Universita degli Studi di Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipt. di Informatica, Universita degli Studi di Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030643448","display_name":"O. Altamura","orcid":null},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"O. Altamura","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","Dipt. di Informatica, Universita degli Studi di Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipt. di Informatica, Universita degli Studi di Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073750332","display_name":"Michelangelo Ceci","orcid":"https://orcid.org/0000-0002-6690-7583"},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Ceci","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","Dipt. di Informatica, Universita degli Studi di Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari, Italy","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipt. di Informatica, Universita degli Studi di Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041745569","display_name":"Margherita Berardi","orcid":null},"institutions":[{"id":"https://openalex.org/I5561750","display_name":"University of Bari Aldo Moro","ror":"https://ror.org/027ynra39","country_code":"IT","type":"education","lineage":["https://openalex.org/I5561750"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"M. Berardi","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari","Dipt. di Informatica, Universita degli Studi di Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Bari, Bari","institution_ids":["https://openalex.org/I5561750"]},{"raw_affiliation_string":"Dipt. di Informatica, Universita degli Studi di Bari, Italy","institution_ids":["https://openalex.org/I5561750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5561750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983000159263611,"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":0.9983000159263611,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9972000122070312,"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":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8064544200897217},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.6911043524742126},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6377938389778137},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5757869482040405},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5739083290100098},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45346394181251526},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4464070498943329},{"id":"https://openalex.org/keywords/page-layout","display_name":"Page layout","score":0.43442896008491516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4036116302013397},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.3296869397163391},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32087159156799316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13171467185020447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11447694897651672},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11236587166786194}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064544200897217},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.6911043524742126},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6377938389778137},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5757869482040405},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5739083290100098},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45346394181251526},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4464070498943329},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.43442896008491516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4036116302013397},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3296869397163391},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32087159156799316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13171467185020447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11447694897651672},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11236587166786194},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdar.2003.1227635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.1952","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.1952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csc.liv.ac.uk/~prima/ICDAR2003/Papers/0017_625_malerba_d.pdf","raw_type":"text"},{"id":"pmh:oai:ricerca.uniba.it:11586/136441","is_oa":false,"landing_page_url":"http://hdl.handle.net/11586/136441","pdf_url":null,"source":{"id":"https://openalex.org/S4377196296","display_name":"CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5561750","host_organization_name":"University of Bari Aldo Moro","host_organization_lineage":["https://openalex.org/I5561750"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W111063460","https://openalex.org/W1573167079","https://openalex.org/W1801594279","https://openalex.org/W1898956034","https://openalex.org/W1983284692","https://openalex.org/W2126727781","https://openalex.org/W2131715999","https://openalex.org/W2134533274","https://openalex.org/W2138064184","https://openalex.org/W2153554054","https://openalex.org/W6604505951","https://openalex.org/W6992286974"],"related_works":["https://openalex.org/W4385629018","https://openalex.org/W4308237185","https://openalex.org/W2382002934","https://openalex.org/W2506450476","https://openalex.org/W3185650400","https://openalex.org/W2098418896","https://openalex.org/W4231519550","https://openalex.org/W2064780770","https://openalex.org/W2156021548","https://openalex.org/W4390873583"],"abstract_inverted_index":{"In":[0,36],"this":[1],"paper,":[2],"a":[3,27,34,145],"machine":[4],"learning":[5,131],"approach":[6],"to":[7,120],"support":[8],"the":[9,12,15,23,31,39,48,63,73,79,86,89,92,97,101,104,107,110,118,122,125,137],"user":[10,102,119,140],"during":[11,103],"correction":[13,105,135],"of":[14,25,33,78,88,91,99,106,109,124,139,147],"layout":[16,32,40,134],"analysis":[17,21,41,50,65,81,127],"is":[18,22,42,114],"proposed.":[19],"Layout":[20],"process":[24,82],"extracting":[26],"hierarchical":[28],"structure":[29],"describing":[30],"page.":[35],"our":[37],"approach,":[38],"performed":[43],"in":[44],"two":[45],"steps:":[46],"firstly,":[47],"global":[49,111,126],"determines":[51],"possible":[52],"areas":[53],"containing":[54],"paragraphs,":[55],"sections,":[56],"columns,":[57],"figures":[58],"and":[59,61,128,152],"tables,":[60],"secondly,":[62],"local":[64,80],"groups":[66],"together":[67],"blocks":[68],"that":[69],"possibly":[70],"fall":[71],"within":[72],"same":[74],"area.":[75],"The":[76],"result":[77],"strongly":[83],"depends":[84],"on":[85,144],"quality":[87],"results":[90,108,123,143],"first":[93],"step.":[94],"We":[95],"investigate":[96],"possibility":[98],"supporting":[100],"analysis.":[112],"This":[113],"done":[115],"by":[116,130],"allowing":[117],"correct":[121],"then":[129],"rules":[132],"for":[133],"from":[136],"sequence":[138],"actions.":[141],"Experimental":[142],"set":[146],"multi-page":[148],"documents":[149],"are":[150],"reported":[151],"commented.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
