{"id":"https://openalex.org/W2608505037","doi":"https://doi.org/10.1109/icpr.2016.7900272","title":"Historical document digitization through layout analysis and deep content classification","display_name":"Historical document digitization through layout analysis and deep content classification","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2608505037","doi":"https://doi.org/10.1109/icpr.2016.7900272","mag":"2608505037"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7900272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11380/1103792","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018805832","display_name":"Andrea Corbelli","orcid":null},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]},{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Andrea Corbelli","raw_affiliation_strings":["Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]},{"raw_affiliation_string":"Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048928616","display_name":"Lorenzo Baraldi","orcid":"https://orcid.org/0000-0001-5125-4957"},"institutions":[{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]},{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Baraldi","raw_affiliation_strings":["Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]},{"raw_affiliation_string":"Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003393933","display_name":"Costantino Grana","orcid":"https://orcid.org/0000-0002-4792-2358"},"institutions":[{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]},{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Costantino Grana","raw_affiliation_strings":["Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]},{"raw_affiliation_string":"Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030948871","display_name":"Rita Cucchiara","orcid":"https://orcid.org/0000-0002-2239-283X"},"institutions":[{"id":"https://openalex.org/I4210161797","display_name":"Ferrari (Italy)","ror":"https://ror.org/05p859a12","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210161797"]},{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Rita Cucchiara","raw_affiliation_strings":["Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy"],"affiliations":[{"raw_affiliation_string":"Dipartimento di Ingegneria \u201cEnzo Ferrari\u201d, Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]},{"raw_affiliation_string":"Dipartimento di Ingegneria \"Enzo Ferrari\", Universit\u00e0 degli Studi di Modena e Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018805832"],"corresponding_institution_ids":["https://openalex.org/I122346577","https://openalex.org/I4210161797"],"apc_list":null,"apc_paid":null,"fwci":0.835,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.81793009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4077","last_page":"4082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987999796867371,"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":0.9962999820709229,"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":0.8384667634963989},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.8246533274650574},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.8242079615592957},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.7444531917572021},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.7030288577079773},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6421530842781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613810420036316},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5560961365699768},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5359374284744263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5152990818023682},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4568711817264557},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.4443415403366089},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.41133347153663635},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4013364911079407},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39873769879341125},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16665709018707275},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.1386413872241974},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11708155274391174},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08730649948120117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384667634963989},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.8246533274650574},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.8242079615592957},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.7444531917572021},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.7030288577079773},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6421530842781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613810420036316},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5560961365699768},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5359374284744263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5152990818023682},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4568711817264557},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.4443415403366089},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.41133347153663635},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4013364911079407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39873769879341125},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16665709018707275},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.1386413872241974},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11708155274391174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08730649948120117},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr.2016.7900272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7900272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unimore.it:11380/1103792","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1103792","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1103792","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1103792","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.550000011920929,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1971336721","https://openalex.org/W1982746261","https://openalex.org/W1997214623","https://openalex.org/W2001642682","https://openalex.org/W2003299073","https://openalex.org/W2024581784","https://openalex.org/W2042106258","https://openalex.org/W2055408294","https://openalex.org/W2069551827","https://openalex.org/W2098345386","https://openalex.org/W2108959246","https://openalex.org/W2115512125","https://openalex.org/W2118020653","https://openalex.org/W2120522996","https://openalex.org/W2121906002","https://openalex.org/W2122237496","https://openalex.org/W2125962095","https://openalex.org/W2130746998","https://openalex.org/W2133308113","https://openalex.org/W2144209937","https://openalex.org/W2158619747","https://openalex.org/W2161846515","https://openalex.org/W2163534337","https://openalex.org/W2165992492","https://openalex.org/W2170570264","https://openalex.org/W4255372243","https://openalex.org/W6650820226","https://openalex.org/W6678214219","https://openalex.org/W6679799793","https://openalex.org/W6683992317"],"related_works":["https://openalex.org/W564581980","https://openalex.org/W2964383635","https://openalex.org/W2995914718","https://openalex.org/W2897195263","https://openalex.org/W2114366712","https://openalex.org/W2067985181","https://openalex.org/W1984241378","https://openalex.org/W2105504191","https://openalex.org/W2168372885","https://openalex.org/W2149128132"],"abstract_inverted_index":{"Document":[0],"layout":[1,29,53],"segmentation":[2,30],"and":[3,61],"recognition":[4],"is":[5,41],"an":[6,25,49],"important":[7],"task":[8],"in":[9,86],"the":[10,44,95,99,111],"creation":[11],"of":[12,46,48,77,98],"digitized":[13],"documents":[14],"collections,":[15],"especially":[16],"when":[17],"dealing":[18],"with":[19],"historical":[20,50,112],"documents.":[21],"This":[22],"paper":[23],"presents":[24],"hybrid":[26],"approach":[27,60],"to":[28,36,43],"as":[31,33],"well":[32],"a":[34,57,62,81,87,102],"strategy":[35],"classify":[37],"document":[38],"regions,":[39],"which":[40],"applied":[42],"process":[45,65],"digitization":[47],"encyclopedia.":[51,114],"Our":[52],"analysis":[54],"method":[55],"merges":[56],"classic":[58],"top-down":[59],"bottom-up":[63],"classification":[64],"based":[66],"on":[67,94],"local":[68],"geometrical":[69],"features,":[70],"while":[71],"regions":[72],"are":[73,92],"classified":[74],"by":[75],"means":[76],"features":[78],"extracted":[79],"from":[80,110],"Convolutional":[82],"Neural":[83],"Network":[84],"merged":[85],"Random":[88],"Forest":[89],"classifier.":[90],"Experiments":[91],"conducted":[93],"first":[96],"volume":[97],"\u201cEnciclopedia":[100],"Treccani\u201d,":[101],"large":[103],"dataset":[104],"containing":[105],"999":[106],"manually":[107],"annotated":[108],"pages":[109],"Italian":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}