{"id":"https://openalex.org/W2331964305","doi":"https://doi.org/10.1145/2809544.2809558","title":"Clustering Historical Documents Based on the Reconstruction Error of Autoencoders","display_name":"Clustering Historical Documents Based on the Reconstruction Error of Autoencoders","publication_year":2015,"publication_date":"2015-08-22","ids":{"openalex":"https://openalex.org/W2331964305","doi":"https://doi.org/10.1145/2809544.2809558","mag":"2331964305"},"language":"en","primary_location":{"id":"doi:10.1145/2809544.2809558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2809544.2809558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","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/A5066134818","display_name":"Mathias Seuret","orcid":"https://orcid.org/0000-0001-9153-1031"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Mathias Seuret","raw_affiliation_strings":["Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019597653","display_name":"Andreas Fischer","orcid":"https://orcid.org/0000-0003-0069-3436"},"institutions":[{"id":"https://openalex.org/I173439891","display_name":"HES-SO University of Applied Sciences and Arts Western Switzerland","ror":"https://ror.org/01xkakk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I173439891"]},{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Fischer","raw_affiliation_strings":["Department of Informatics, University of Fribourg and iCoSys Institute HES-SO"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Fribourg and iCoSys Institute HES-SO","institution_ids":["https://openalex.org/I173439891","https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048355704","display_name":"Angelika Garz","orcid":null},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Angelika Garz","raw_affiliation_strings":["Department of Informatics, University of Fribourg, DIVA, 1700 Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Fribourg, DIVA, 1700 Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073619925","display_name":"Marcus Liwicki","orcid":"https://orcid.org/0000-0003-4029-6574"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marcus Liwicki","raw_affiliation_strings":["Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018014670","display_name":"Rolf Ingold","orcid":"https://orcid.org/0000-0001-7738-133X"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rolf Ingold","raw_affiliation_strings":["Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Fribourg, 1700 Fribourg, Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066134818"],"corresponding_institution_ids":["https://openalex.org/I154338468"],"apc_list":null,"apc_paid":null,"fwci":0.9205,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83204918,"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":"85","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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":0.9966999888420105,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9958000183105469,"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":0.9936000108718872,"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":0.7707909941673279},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6982743740081787},{"id":"https://openalex.org/keywords/cursive","display_name":"Cursive","score":0.6755616664886475},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.66874760389328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6619188189506531},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6480374932289124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4942457973957062},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4626643657684326},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4490514397621155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3526708483695984},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18256840109825134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707909941673279},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6982743740081787},{"id":"https://openalex.org/C2778943297","wikidata":"https://www.wikidata.org/wiki/Q1079418","display_name":"Cursive","level":2,"score":0.6755616664886475},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.66874760389328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6619188189506531},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6480374932289124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4942457973957062},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4626643657684326},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4490514397621155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3526708483695984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18256840109825134},{"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:10.1145/2809544.2809558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2809544.2809558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:hesso.tind.io:10894","is_oa":false,"landing_page_url":"http://arodes.hes-so.ch/record/10894","pdf_url":null,"source":{"id":"https://openalex.org/S4306402432","display_name":"ArODES (HES-SO (https://www.hes-so.ch/))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210088449","host_organization_name":"HES-SO Gen\u00e8ve","host_organization_lineage":["https://openalex.org/I4210088449"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arodes.hes-so.ch/record/10894","raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1826790618","https://openalex.org/W1970088388","https://openalex.org/W1985602840","https://openalex.org/W2002629090","https://openalex.org/W2043329917","https://openalex.org/W2045806863","https://openalex.org/W2093275091","https://openalex.org/W2099937879","https://openalex.org/W2126925189","https://openalex.org/W2130608499","https://openalex.org/W2133262956","https://openalex.org/W2142127980","https://openalex.org/W2145094598","https://openalex.org/W2152736061","https://openalex.org/W2396976214","https://openalex.org/W2997574889"],"related_works":["https://openalex.org/W2373698219","https://openalex.org/W2035729865","https://openalex.org/W4253008392","https://openalex.org/W3092020155","https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W1985694112"],"abstract_inverted_index":{"The":[0],"term":[1],"\"historical":[2],"documents\"":[3],"encompasses":[4],"an":[5,104],"enormous":[6],"variety":[7],"of":[8,65,74,122],"document":[9,54],"types":[10],"considering":[11],"different":[12,112],"scripts,":[13],"languages,":[14],"writing":[15,129],"supports,":[16],"and":[17,26,39,93,135],"degradation":[18],"degrees.":[19],"For":[20,131],"automatic":[21],"processing":[22],"with":[23,71,115],"machine":[24],"learning":[25,37],"pattern":[27],"recognition":[28],"methods,":[29],"it":[30],"would":[31],"be":[32],"ideal":[33],"to":[34,67,78,126],"share":[35],"labeled":[36],"samples":[38],"trained":[40,102],"statistical":[41],"models":[42],"across":[43],"similar":[44,128],"documents,":[45],"avoiding":[46],"a":[47,90,94],"retraining":[48],"from":[49],"scratch":[50],"for":[51,97],"every":[52],"historical":[53,69],"anew.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"using":[61],"the":[62,72,99,120,123],"reconstruction":[63,84,124],"error":[64,85,125],"autoencoders":[66],"compare":[68],"manuscripts":[70,113],"goal":[73],"clustering":[75],"them":[76],"according":[77],"their":[79],"visual":[80,87],"appearance.":[81],"A":[82],"low":[83],"suggests":[86],"similarity":[88],"between":[89,133],"new":[91],"manuscript":[92],"known":[95],"manuscript,":[96],"which":[98],"autoencoder":[100],"was":[101],"in":[103,138],"unsupervised":[105],"fashion.":[106],"Preliminary":[107],"experiments":[108],"conducted":[109],"on":[110,117],"10":[111],"written":[114],"ink":[116],"parchment":[118],"demonstrate":[119],"ability":[121],"group":[127],"styles.":[130],"discriminating":[132],"Carolingian":[134],"cursive":[136],"script,":[137],"particular,":[139],"near-perfect":[140],"results":[141],"are":[142],"reported.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}