{"id":"https://openalex.org/W2771175171","doi":"https://doi.org/10.1145/3075645","title":"Mass Digitization of Early Modern Texts With Optical Character Recognition","display_name":"Mass Digitization of Early Modern Texts With Optical Character Recognition","publication_year":2017,"publication_date":"2017-12-07","ids":{"openalex":"https://openalex.org/W2771175171","doi":"https://doi.org/10.1145/3075645","mag":"2771175171"},"language":"en","primary_location":{"id":"doi:10.1145/3075645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075645","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/A5061106701","display_name":"Matthew Christy","orcid":"https://orcid.org/0000-0002-8076-5112"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Christy","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620143","display_name":"Anshul Gupta","orcid":"https://orcid.org/0000-0003-0408-4072"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshul Gupta","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017494581","display_name":"Elizabeth Grumbach","orcid":"https://orcid.org/0000-0001-5622-0967"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Grumbach","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083909674","display_name":"Laura Mandell","orcid":"https://orcid.org/0000-0002-4013-114X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Mandell","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065474822","display_name":"Richard Furuta","orcid":"https://orcid.org/0000-0002-7349-4203"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Furuta","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062423099","display_name":"Ricardo Guti\u00e9rrez\u2010Osuna","orcid":"https://orcid.org/0000-0003-2817-2085"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricardo Gutierrez-Osuna","raw_affiliation_strings":["Texas A8M University, College Station, TX"],"affiliations":[{"raw_affiliation_string":"Texas A8M University, College Station, TX","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5061106701"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.37,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.70322052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9957000017166138,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9937999844551086,"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/digitization","display_name":"Digitization","score":0.9143214225769043},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8626279830932617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7238488793373108},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.6425433158874512},{"id":"https://openalex.org/keywords/microform","display_name":"Microform","score":0.5847197771072388},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5799973011016846},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4839337468147278},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4825989007949829},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4695699214935303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4434584975242615},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3837619721889496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23491820693016052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22869837284088135},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.13104292750358582},{"id":"https://openalex.org/keywords/library-science","display_name":"Library science","score":0.12881112098693848},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11817583441734314}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.9143214225769043},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8626279830932617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7238488793373108},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.6425433158874512},{"id":"https://openalex.org/C8184842","wikidata":"https://www.wikidata.org/wiki/Q830450","display_name":"Microform","level":2,"score":0.5847197771072388},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5799973011016846},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4839337468147278},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4825989007949829},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4695699214935303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4434584975242615},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3837619721889496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23491820693016052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22869837284088135},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13104292750358582},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.12881112098693848},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11817583441734314},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3075645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3075645","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G8451567539","display_name":null,"funder_award_id":"31200645","funder_id":"https://openalex.org/F4320306146","funder_display_name":"Andrew W. Mellon Foundation"}],"funders":[{"id":"https://openalex.org/F4320306146","display_name":"Andrew W. Mellon Foundation","ror":"https://ror.org/04jsh2530"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1514940655","https://openalex.org/W1699166917","https://openalex.org/W1973924286","https://openalex.org/W1990797646","https://openalex.org/W1995376165","https://openalex.org/W2001642682","https://openalex.org/W2007489617","https://openalex.org/W2021732807","https://openalex.org/W2022710553","https://openalex.org/W2035683813","https://openalex.org/W2055783626","https://openalex.org/W2056471870","https://openalex.org/W2061688106","https://openalex.org/W2075484307","https://openalex.org/W2088326204","https://openalex.org/W2090855106","https://openalex.org/W2092449865","https://openalex.org/W2093129597","https://openalex.org/W2098470001","https://openalex.org/W2107756083","https://openalex.org/W2109305763","https://openalex.org/W2118376687","https://openalex.org/W2131846894","https://openalex.org/W2143842970","https://openalex.org/W2155381731","https://openalex.org/W2241862190","https://openalex.org/W2251507498","https://openalex.org/W2258158787","https://openalex.org/W2283184170","https://openalex.org/W2295218488","https://openalex.org/W4298132949","https://openalex.org/W4299710100"],"related_works":["https://openalex.org/W4205520559","https://openalex.org/W2344247273","https://openalex.org/W2780279436","https://openalex.org/W2786752243","https://openalex.org/W1512334992","https://openalex.org/W4290785358","https://openalex.org/W907309559","https://openalex.org/W2387970992","https://openalex.org/W2724898345","https://openalex.org/W2566805851"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2],"(OCR)":[3],"engines":[4,184],"work":[5,180],"poorly":[6],"on":[7,144],"texts":[8,62],"published":[9],"with":[10],"premodern":[11],"printing":[12],"technologies.":[13],"Engaging":[14],"the":[15,20,29,38,50,64,88,92,133,141,151,154,161],"key":[16],"technological":[17],"contributors":[18],"from":[19,49,63,118],"IMPACT":[21],"project,":[22],"an":[23],"earlier":[24],"project":[25,142],"attempting":[26],"to":[27,55,84,106,113,120],"solve":[28],"OCR":[30,41,57,114,183],"problem":[31],"for":[32,59,126,158,178,185],"early":[33,60],"modern":[34,36,61],"and":[35,70,104,128,153,166,171],"texts,":[37],"Early":[39,71],"Modern":[40],"Project":[42],"(eMOP)":[43],"of":[44,91],"Texas":[45],"A8M":[46],"received":[47],"funding":[48],"Andrew":[51],"W.":[52],"Mellon":[53],"Foundation":[54],"improve":[56],"outputs":[58],"Eighteenth":[65],"Century":[66],"Collections":[67],"Online":[68,74],"(ECCO)":[69],"English":[72],"Books":[73],"(EEBO)":[75],"proprietary":[76],"database":[77],"products\u2014or":[78],"some":[79],"45":[80],"million":[81],"pages.":[82],"Added":[83],"print":[85],"problems":[86],"are":[87],"poor":[89],"quality":[90],"page":[93],"images":[94],"in":[95,181],"these":[96],"collections,":[97],"which":[98],"would":[99],"be":[100,176],"too":[101],"time":[102],"consuming":[103],"expensive":[105],"reimage.":[107],"This":[108],"article":[109],"describes":[110],"eMOP's":[111],"attempts":[112],"307,000":[115],"documents":[116],"digitized":[117],"microfilm":[119],"make":[121],"our":[122,136],"cultural":[123,186],"heritage":[124,187],"available":[125],"current":[127],"future":[129,172],"researchers.":[130],"We":[131],"describe":[132],"reasoning":[134],"behind":[135],"choices":[137],"as":[138],"we":[139,149,156,169],"undertook":[140],"based":[143],"other":[145],"relevant":[146],"studies;":[147],"discoveries":[148],"made;":[150],"data":[152],"system":[155],"developed":[157],"processing":[159],"it;":[160],"software,":[162],"algorithms,":[163],"training":[164],"procedures,":[165],"tools":[167],"that":[168,174],"developed;":[170],"directions":[173],"should":[175],"taken":[177],"further":[179],"developing":[182],"materials.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
