{"id":"https://openalex.org/W7166581099","doi":"https://doi.org/10.1145/3805689.3806442","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","display_name":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166581099","doi":"https://doi.org/10.1145/3805689.3806442"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3806442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3806442","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063383646","display_name":"F. Beyene","orcid":"https://orcid.org/0000-0002-6108-3319"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fitsum Sileshi Beyene","raw_affiliation_strings":["Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0009-0009-2006-7580","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065588624","display_name":"Christopher L. Dancy","orcid":"https://orcid.org/0000-0003-2119-496X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher L. Dancy","raw_affiliation_strings":["Department of Industrial and Manufacturing Engineering & Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0003-2119-496X","affiliations":[{"raw_affiliation_string":"Department of Industrial and Manufacturing Engineering & Computer Science and Engineering, Pennsylvania State University, State college, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8282659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7675","last_page":"7691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.34929999709129333,"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":0.34929999709129333,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.16619999706745148,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/invisibility","display_name":"Invisibility","score":0.7889999747276306},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.44909998774528503},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.33469998836517334},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2761000096797943}],"concepts":[{"id":"https://openalex.org/C50962388","wikidata":"https://www.wikidata.org/wiki/Q762018","display_name":"Invisibility","level":2,"score":0.7889999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169000267982483},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805689.3806442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.25761","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2603.25761","pdf_url":"https://arxiv.org/pdf/2603.25761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805689.3806442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3806442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W2001642682","https://openalex.org/W2099984129","https://openalex.org/W2973047034","https://openalex.org/W2997154779","https://openalex.org/W3003711898","https://openalex.org/W3093938929","https://openalex.org/W3106274667","https://openalex.org/W3113753692","https://openalex.org/W3118615836","https://openalex.org/W3120043490","https://openalex.org/W3174220540","https://openalex.org/W3176851559","https://openalex.org/W3178709966","https://openalex.org/W3208962647","https://openalex.org/W3214680719","https://openalex.org/W4225605585","https://openalex.org/W4234153941","https://openalex.org/W4280595958","https://openalex.org/W4281820857","https://openalex.org/W4290927927","https://openalex.org/W4304013646","https://openalex.org/W4312233877","https://openalex.org/W4365388135","https://openalex.org/W4365510854","https://openalex.org/W4382202677","https://openalex.org/W4387606456","https://openalex.org/W4390873989","https://openalex.org/W4405399726","https://openalex.org/W4411550066","https://openalex.org/W4412887686","https://openalex.org/W4413145313","https://openalex.org/W4417132706"],"related_works":[],"abstract_inverted_index":{"Optical":[0],"character":[1,131],"recognition":[2],"(OCR)":[3],"and":[4,13,23,33,39,49,65,79,96,102,114,133,153,167,184,197,201,207],"document":[5,50,66],"understanding":[6,51,67],"systems":[7,52],"increasingly":[8],"rely":[9],"on":[10,20,136],"large":[11],"vision":[12,100],"vision-language":[14],"models,":[15],"yet":[16],"evaluation":[17,97,126,178],"remains":[18],"centered":[19],"modern,":[21],"Western,":[22],"institutional":[24,198],"documents.":[25],"This":[26,44],"emphasis":[27],"masks":[28],"system":[29],"behavior":[30],"in":[31,121,145],"historical":[32,60,117,146],"marginalized":[34],"archives,":[35],"where":[36],"layout,":[37],"typography,":[38],"material":[40],"degradation":[41],"shape":[42],"interpretation.":[43],"study":[45],"examines":[46],"how":[47,88,177],"OCR":[48,64,104],"are":[53,75],"evaluated,":[54],"with":[55],"particular":[56],"attention":[57],"to":[58,175,181,194],"Black":[59,112,172],"newspapers.":[61],"We":[62,85,187],"review":[63],"papers,":[68],"as":[69,71],"well":[70],"benchmark":[72,94,205],"datasets,":[73],"which":[74],"published":[76],"between":[77],"2006":[78],"2025":[80],"using":[81],"the":[82,89,107],"PRISMA":[83],"framework.":[84],"look":[86],"into":[87,160],"studies":[90,166],"report":[91],"training":[92,123],"data,":[93],"design,":[95],"metrics":[98],"for":[99],"transformer":[101],"multimodal":[103],"systems.":[105],"During":[106],"review,":[108],"we":[109,162],"found":[110],"that":[111,189],"newspapers":[113],"other":[115],"community-produced":[116],"documents":[118],"rarely":[119,140],"appear":[120],"reported":[122],"data":[124,208],"or":[125],"benchmarks.":[127],"Most":[128],"evaluations":[129],"emphasize":[130],"accuracy":[132],"task":[134],"success":[135],"modern":[137],"layouts.":[138],"They":[139],"capture":[141],"structural":[142,182],"failures":[143],"common":[144],"newspapers,":[147],"including":[148],"column":[149],"collapse,":[150],"typographic":[151],"errors,":[152],"hallucinated":[154],"text.":[155],"To":[156],"put":[157],"these":[158,190],"findings":[159],"perspective,":[161],"use":[163],"previous":[164],"empirical":[165],"archival":[168],"statistics":[169],"from":[170],"significant":[171],"press":[173],"collections":[174],"show":[176],"gaps":[179,191],"lead":[180],"invisibility":[183],"representational":[185],"harm.":[186],"propose":[188],"occur":[192],"due":[193],"organizational":[195],"(meso)":[196],"(macro)":[199],"behaviors":[200],"structure,":[202],"shaped":[203],"by":[204],"incentives":[206],"governance":[209],"decisions.":[210]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-06-30T00:00:00"}