{"id":"https://openalex.org/W4220988041","doi":"https://doi.org/10.1145/3485845","title":"Augmentation-based Pseudo-Ground truth Generation for Deep Learning in Historical Document Segmentation for Greater Levels of Archival Description and Access","display_name":"Augmentation-based Pseudo-Ground truth Generation for Deep Learning in Historical Document Segmentation for Greater Levels of Archival Description and Access","publication_year":2022,"publication_date":"2022-03-07","ids":{"openalex":"https://openalex.org/W4220988041","doi":"https://doi.org/10.1145/3485845"},"language":"en","primary_location":{"id":"doi:10.1145/3485845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485845","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-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/A5061711551","display_name":"Chulwoo Pack","orcid":"https://orcid.org/0000-0002-9876-4388"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chulwoo Pack","raw_affiliation_strings":["Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"],"raw_orcid":"https://orcid.org/0000-0002-9876-4388","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056614770","display_name":"Y. F. Liu","orcid":"https://orcid.org/0000-0002-0879-0487"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089919340","display_name":"Leen\u2010Kiat Soh","orcid":"https://orcid.org/0000-0002-6094-4666"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leen-Kiat Soh","raw_affiliation_strings":["Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045354577","display_name":"Elizabeth Lorang","orcid":"https://orcid.org/0000-0002-0003-6789"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Lorang","raw_affiliation_strings":["University Libraries, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Libraries, University of Nebraska-Lincoln, Lincoln, Nebraska, United States","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":null,"apc_paid":null,"fwci":0.2936,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5059577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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":0.9835000038146973,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9767000079154968,"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/ground-truth","display_name":"Ground truth","score":0.8954291343688965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242833375930786},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7220491170883179},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6364762187004089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655356645584106},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.436554491519928},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4351470470428467},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3500973582267761}],"concepts":[{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.8954291343688965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242833375930786},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7220491170883179},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6364762187004089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655356645584106},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.436554491519928},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4351470470428467},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3500973582267761},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485845","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485845","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306100","display_name":"National Endowment for the Humanities","ror":"https://ror.org/02vdm1p28"},{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W58456790","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1964101267","https://openalex.org/W1965285802","https://openalex.org/W1989496235","https://openalex.org/W2005173844","https://openalex.org/W2008420823","https://openalex.org/W2031489346","https://openalex.org/W2036145013","https://openalex.org/W2085082924","https://openalex.org/W2088326204","https://openalex.org/W2106311500","https://openalex.org/W2157769407","https://openalex.org/W2157880897","https://openalex.org/W2169786363","https://openalex.org/W2180404376","https://openalex.org/W2215544391","https://openalex.org/W2527268310","https://openalex.org/W2533973874","https://openalex.org/W2555182955","https://openalex.org/W2576852589","https://openalex.org/W2612452126","https://openalex.org/W2769041395","https://openalex.org/W2771490691","https://openalex.org/W2777421064","https://openalex.org/W2798826627","https://openalex.org/W2886527657","https://openalex.org/W2914424171","https://openalex.org/W2919115771","https://openalex.org/W2923274354","https://openalex.org/W2941697737","https://openalex.org/W2954996726","https://openalex.org/W2959716049","https://openalex.org/W2962903028","https://openalex.org/W2963545917","https://openalex.org/W2964217532","https://openalex.org/W2964346820","https://openalex.org/W2992511782","https://openalex.org/W3004124585","https://openalex.org/W3025418895","https://openalex.org/W3104784423","https://openalex.org/W4288620865","https://openalex.org/W6684862263"],"related_works":["https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W1997160662","https://openalex.org/W2088281698","https://openalex.org/W2099262596","https://openalex.org/W2021525266","https://openalex.org/W4220988041","https://openalex.org/W92754040","https://openalex.org/W2079504722"],"abstract_inverted_index":{"The":[0,120],"successful":[1,43],"use":[2,82,139,238,265,289],"of":[3,17,45,60,74,83,89,112,130,144,172,181,220,228,239,242,250,283,290,299],"deep":[4,46,230],"learning":[5,47,231],"solutions":[6,48],"for":[7,28,49,150],"document":[8,30,50,117],"image":[9,51],"segmentation":[10,52,118,285,325],"typically":[11],"relies":[12],"on":[13,196,258,328],"a":[14,109,116,170,178,259,324],"large":[15],"number":[16,111,180],"manually":[18],"labeled":[19,113,182],"ground":[20,132],"truth":[21,104,133,168,223,279,330],"examples,":[22],"which":[23],"is":[24,122,281,313],"expensive":[25],"to":[26,56,78,101,200,205,216,269,315],"obtain":[27],"historical":[29,151],"images":[31,114,164,203],"that":[32,123,276,306,323],"have":[33,53,270],"significant":[34,271],"noise":[35,272],"effects":[36],"and":[37,67,81,147,153,165,234,295],"variation.":[38],"At":[39],"the":[40,69,128,145,191,209,218,226,229,237,248,251,255,288,291,300],"same":[41],"time,":[42],"applications":[44],"rich":[54],"potential":[55],"facilitate":[57],"greater":[58,72],"levels":[59,73],"description":[61,75,146],"in":[62,115,208,225],"archival":[63,84,154],"collections":[64,85],"(e.g.,":[65],"at":[66],"below":[68],"item-level).":[70],"These":[71],"are":[76],"critical":[77],"increasing":[79],"access":[80,148],"across":[86],"an":[87,98],"array":[88],"research":[90],"domains.":[91],"In":[92,156],"response,":[93],"this":[94,157],"article":[95],"investigates":[96],"whether":[97],"augmentation-based":[99,135,277],"approach":[100,252],"generating":[102,131,186,202],"pseudo-ground":[103,167,222,278,329],"can":[105,126,138],"be":[106,206],"effective":[107],"with":[108,287],"limited":[110],"application.":[119],"rationale":[121],"if":[124],"we":[125,137,160,189,212,321],"decrease":[127],"cost":[129],"through":[134],"approaches,":[136],"these":[140],"approaches":[141],"as":[142],"part":[143],"pipelines":[149],"library":[152],"collections.":[155],"initial":[158],"exploration,":[159],"first":[161],"generate":[162],"synthetic":[163,187],"corresponding":[166],"using":[169,307],"set":[171],"existing":[173],"degradation-based":[174],"augmentation":[175],"models":[176,312],"from":[177],"small":[179],"actual":[183],"images.":[184],"When":[185],"images,":[188],"control":[190],"visual":[192],"quality":[193],"distortion":[194],"based":[195],"OCR":[197],"word-level":[198],"confidence":[199],"avoid":[201],"unlikely":[204],"present":[207],"dataset.":[210,261,302],"Then,":[211],"perform":[213],"several":[214],"investigations":[215,263],"examine":[217],"impact":[219],"incorporating":[221],"data":[224,331],"training":[227],"network":[232,257,326],"dhSegment":[233],"further":[235],"evaluate":[236],"multiple":[240],"combinations":[241],"degradation":[243,311],"models.":[244],"We":[245],"also":[246,304],"assess":[247],"generalizability":[249],"by":[253],"applying":[254],"trained":[256,327],"larger":[260],"Our":[262],"primarily":[264],"real-world":[266],"datasets":[267],"known":[268],"effects.":[273],"Results":[274,303],"show":[275,305,322],"generation":[280],"capable":[282],"improving":[284],"performance":[286],"full":[292],"original":[293,301],"dataset":[294],"requires":[296],"only":[297],"30%":[298],"more":[308],"than":[309],"three":[310],"likely":[314],"cause":[316],"overfitting":[317],"during":[318],"training.":[319],"Furthermore,":[320],"has":[332],"generalization":[333],"capability.":[334]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}