{"id":"https://openalex.org/W2154032543","doi":"https://doi.org/10.1145/2361354.2361383","title":"Logical segmentation for article extraction in digitized old newspapers","display_name":"Logical segmentation for article extraction in digitized old newspapers","publication_year":2012,"publication_date":"2012-09-04","ids":{"openalex":"https://openalex.org/W2154032543","doi":"https://doi.org/10.1145/2361354.2361383","mag":"2154032543"},"language":"en","primary_location":{"id":"doi:10.1145/2361354.2361383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1210.0999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041298953","display_name":"Thomas Palfray","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thomas Palfray","raw_affiliation_strings":["LITIS, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075258341","display_name":"David G. Hebert","orcid":"https://orcid.org/0000-0003-3926-5228"},"institutions":[{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]},{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Hebert","raw_affiliation_strings":["LITIS, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059213449","display_name":"St\u00e9phane Nicolas","orcid":"https://orcid.org/0000-0003-0758-9930"},"institutions":[{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]},{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Nicolas","raw_affiliation_strings":["LITIS, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112340423","display_name":"Pierrick Tranouez","orcid":"https://orcid.org/0000-0002-1962-0782"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierrick Tranouez","raw_affiliation_strings":["LITIS, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022490769","display_name":"Thierry Paquet","orcid":"https://orcid.org/0000-0002-2044-7542"},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thierry Paquet","raw_affiliation_strings":["LITIS, University of Rouen, Rouen, France"],"affiliations":[{"raw_affiliation_string":"LITIS, University of Rouen, Rouen, France","institution_ids":["https://openalex.org/I62396329","https://openalex.org/I4210108118"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041298953"],"corresponding_institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"],"apc_list":null,"apc_paid":null,"fwci":0.2777,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.61429508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.998199999332428,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.998199999332428,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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/T12923","display_name":"Digital Image Processing Techniques","score":0.9940000176429749,"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/newspaper","display_name":"Newspaper","score":0.8699784278869629},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7935826778411865},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7664251327514648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7652757167816162},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7102518081665039},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.49848175048828125},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4940341114997864},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3653249144554138},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19646775722503662},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13192638754844666}],"concepts":[{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.8699784278869629},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7935826778411865},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7664251327514648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652757167816162},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7102518081665039},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.49848175048828125},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4940341114997864},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3653249144554138},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19646775722503662},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13192638754844666},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2361354.2361383","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM symposium on Document engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1210.0999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1210.0999","pdf_url":"https://arxiv.org/pdf/1210.0999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:HAL:hal-00737859v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00737859","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Document Engineering, Sep 2012, France. pp.NA","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1210.0999","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1210.0999","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1210.0999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1210.0999","pdf_url":"https://arxiv.org/pdf/1210.0999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1491852184","https://openalex.org/W2025384595","https://openalex.org/W2030393865","https://openalex.org/W2052301383","https://openalex.org/W2090985514","https://openalex.org/W2096210305","https://openalex.org/W2162031011","https://openalex.org/W2734798343","https://openalex.org/W6629356302"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2359544913","https://openalex.org/W2471217682"],"abstract_inverted_index":{"Newspapers":[0],"are":[1,11,191],"documents":[2],"made":[3],"of":[4,68,81,118,162,199,205,213,220],"news":[5],"item":[6],"and":[7,66,124,128,166,170,225],"informative":[8,87],"articles.":[9,90],"They":[10],"not":[12],"meant":[13],"to":[14,47,84,141,216],"be":[15,179,232],"read":[16],"iteratively:":[17],"the":[18,71,78,82,86,89,96,106,116,142,147,150,173,197,200],"reader":[19],"can":[20,178,231],"pick":[21],"his":[22],"items":[23],"in":[24,136],"any":[25],"order":[26],"he":[27],"fancies.":[28],"Ignoring":[29],"this":[30],"structural":[31],"property,":[32],"most":[33],"digitized":[34],"newspaper":[35,59],"archives":[36,198],"only":[37],"offer":[38],"access":[39],"by":[40,45,115,146],"issue":[41],"or":[42],"at":[43,70,95,172,234],"best":[44],"page":[46,83,107],"their":[48],"content.":[49],"We":[50,190],"have":[51],"built":[52],"a":[53,100,137,157,184],"digitization":[54],"workflow":[55],"that":[56],"automatically":[57],"extracts":[58,77],"articles":[60],"from":[61,113],"images,":[62,163],"which":[63,182],"allows":[64,186],"indexing":[65,165],"retrieval":[67,167],"information":[69],"article":[72,174],"level.":[73,175],"Our":[74,153],"back-end":[75],"system":[76,148,155,195],"logical":[79,108,132],"structure":[80,109,133],"produce":[85],"units:":[88],"Each":[91],"image":[92,223],"is":[93,110,134],"labelled":[94],"pixel":[97],"level,":[98],"through":[99],"machine":[101],"learning":[102],"based":[103],"method,":[104],"then":[105],"constructed":[111],"up":[112],"there":[114],"detection":[117],"structuring":[119],"entities":[120],"such":[121],"as":[122,183],"horizontal":[123],"vertical":[125],"separators,":[126],"titles":[127],"text":[129],"lines.":[130],"This":[131],"stored":[135],"METS":[138],"wrapper":[139],"associated":[140],"ALTO":[143],"file":[144],"produced":[145],"including":[149],"OCRed":[151],"text.":[152],"front-end":[154],"provides":[156],"web":[158],"high":[159],"definition":[160],"visualisation":[161],"textual":[164],"facilities,":[168],"searching":[169],"reading":[171],"Articles":[176],"transcriptions":[177],"collaboratively":[180],"corrected,":[181],"consequence":[185],"for":[187],"better":[188],"indexing.":[189],"currently":[192],"testing":[193],"our":[194],"on":[196],"Journal":[201],"de":[202],"Rouen,":[203],"one":[204],"France":[206],"eldest":[207],"local":[208],"newspaper.":[209],"These":[210],"250":[211],"years":[212],"publication":[214],"amount":[215],"300":[217],"000":[218],"pages":[219],"very":[221],"variable":[222],"quality":[224],"layout":[226],"complexity.":[227],"Test":[228],"year":[229],"1808":[230],"consulted":[233],"plair.univ-rouen.fr.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2022-08-21T00:00:00"}
