{"id":"https://openalex.org/W4415969858","doi":"https://doi.org/10.1109/cist65886.2025.11224240","title":"Transforming Text into Discovery: OCR Enrichment of Digital Collections in the University of Galway Library","display_name":"Transforming Text into Discovery: OCR Enrichment of Digital Collections in the University of Galway Library","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4415969858","doi":"https://doi.org/10.1109/cist65886.2025.11224240"},"language":"en","primary_location":{"id":"doi:10.1109/cist65886.2025.11224240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist65886.2025.11224240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th Congress on Information Science and Technology (CiSt)","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/A5024903445","display_name":"Oksana Dereza","orcid":"https://orcid.org/0000-0003-2896-6037"},"institutions":[{"id":"https://openalex.org/I4210142142","display_name":"COPE Galway","ror":"https://ror.org/04ehmzv20","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210142142"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Oksana Dereza","raw_affiliation_strings":["Library University of Galway,Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"Library University of Galway,Galway,Ireland","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I4210142142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120283936","display_name":"Marie-Louise Rouget","orcid":null},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]},{"id":"https://openalex.org/I4210142142","display_name":"COPE Galway","ror":"https://ror.org/04ehmzv20","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210142142"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Marie-Louise Rouget","raw_affiliation_strings":["Library University of Galway,Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"Library University of Galway,Galway,Ireland","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I4210142142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120283937","display_name":"Chidi Egwu","orcid":null},"institutions":[{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Chidi Egwu","raw_affiliation_strings":["University of Galway,School of Medicine,Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"University of Galway,School of Medicine,Galway,Ireland","institution_ids":["https://openalex.org/I188760350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062811565","display_name":"Cillian Joy","orcid":"https://orcid.org/0000-0003-2470-0995"},"institutions":[{"id":"https://openalex.org/I4210142142","display_name":"COPE Galway","ror":"https://ror.org/04ehmzv20","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210142142"]},{"id":"https://openalex.org/I188760350","display_name":"Ollscoil na Gaillimhe \u2013 University of Galway","ror":"https://ror.org/03bea9k73","country_code":"IE","type":"education","lineage":["https://openalex.org/I188760350"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Cillian Joy","raw_affiliation_strings":["Library University of Galway,Galway,Ireland"],"affiliations":[{"raw_affiliation_string":"Library University of Galway,Galway,Ireland","institution_ids":["https://openalex.org/I188760350","https://openalex.org/I4210142142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024903445"],"corresponding_institution_ids":["https://openalex.org/I188760350","https://openalex.org/I4210142142"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35377529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6068999767303467,"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":0.6068999767303467,"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":0.11860000342130661,"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.04809999838471413,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7527999877929688},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.7465000152587891},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6891000270843506},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.5299999713897705},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4553999900817871},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.4537999927997589},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44830000400543213},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7527999877929688},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.7465000152587891},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6891000270843506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989999771118164},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4027999937534332},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2988765800","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital collections","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C18599908","wikidata":"https://www.wikidata.org/wiki/Q1196904","display_name":"Electronic publishing","level":3,"score":0.2883000075817108},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cist65886.2025.11224240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cist65886.2025.11224240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 8th Congress on Information Science and Technology (CiSt)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://researchrepository.universityofgalway.ie:10379/19264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/CiSt65886.2025.11224240","pdf_url":null,"source":{"id":"https://openalex.org/S4377196322","display_name":"ARAN (University of Galway Research Repository) (Ollscoil na Gaillimhe \u2013 University of Galway)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I188760350","host_organization_name":"Ollscoil na Gaillimhe \u2013 University of Galway","host_organization_lineage":["https://openalex.org/I188760350"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1879810414","https://openalex.org/W1993557076","https://openalex.org/W2001642682","https://openalex.org/W2056397490","https://openalex.org/W2443396451","https://openalex.org/W2476822088","https://openalex.org/W2786345741","https://openalex.org/W2787677190","https://openalex.org/W2949780281","https://openalex.org/W2973047034","https://openalex.org/W2980523701","https://openalex.org/W2981597140","https://openalex.org/W2984055017","https://openalex.org/W2986829274","https://openalex.org/W3011228495","https://openalex.org/W3013597222","https://openalex.org/W3208193076","https://openalex.org/W3211052011","https://openalex.org/W3216666189","https://openalex.org/W4200356778","https://openalex.org/W4285124838","https://openalex.org/W4288043960","https://openalex.org/W4308111020","https://openalex.org/W4311363515","https://openalex.org/W4367853079","https://openalex.org/W4386649947","https://openalex.org/W4387673211","https://openalex.org/W4389762644","https://openalex.org/W4391529321","https://openalex.org/W4392952747","https://openalex.org/W4402343056","https://openalex.org/W4402683023","https://openalex.org/W4403672681","https://openalex.org/W4405849824","https://openalex.org/W4406871776","https://openalex.org/W4408403671","https://openalex.org/W4409591086","https://openalex.org/W4410281696"],"related_works":[],"abstract_inverted_index":{"The":[0,90],"University":[1],"of":[2,32,41,56,64,72,102],"Galway":[3],"Library":[4],"has":[5],"been":[6],"working":[7],"on":[8,68],"an":[9,58],"Optical":[10],"Character":[11],"Recognition":[12],"(OCR)":[13],"pipeline":[14,91],"to":[15],"transform":[16],"scanned":[17],"archival":[18],"materials":[19],"into":[20,125],"machine-readable":[21],"text":[22,123],"at":[23,93],"scale.":[24],"This":[25],"significantly":[26],"enhances":[27],"the":[28,33,49,62,79],"accessibility":[29],"and":[30,44,77,86,105],"searchability":[31],"University\u2019s":[34],"digitised":[35,73],"heritage":[36,69],"collections,":[37],"supporting":[38],"diverse":[39],"areas":[40],"research":[42],"interest":[43],"fostering":[45],"deeper":[46],"engagement":[47],"with":[48,96],"Library\u2019s":[50],"holdings.The":[51],"paper":[52],"discusses":[53],"key":[54],"aspects":[55],"building":[57],"OCR":[59,66,80],"pipeline,":[60],"including":[61],"performance":[63],"available":[65],"software":[67],"data,":[70],"pre-processing":[71],"images,":[74],"quality":[75,97],"assurance,":[76],"converting":[78],"engine":[81],"outputs":[82],"for":[83,99],"DAMS":[84],"upload":[85],"seamless":[87],"IIIF":[88],"integration.":[89],"aims":[92],"balancing":[94],"automation":[95],"control":[98],"successful":[100],"extraction":[101,124],"printed,":[103],"typewritten":[104],"handwritten":[106],"text.":[107],"We":[108],"believe":[109],"that":[110,118],"our":[111],"experience":[112],"may":[113],"help":[114],"other":[115],"GLAM":[116],"institutions":[117],"are":[119],"considering":[120],"incorporating":[121],"automatic":[122],"their":[126],"digital":[127],"collections":[128],"workflow.":[129]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-06T00:00:00"}
