{"id":"https://openalex.org/W4406871776","doi":"https://doi.org/10.3390/jimaging11020036","title":"iForal: Automated Handwritten Text Transcription for Historical Medieval Manuscripts","display_name":"iForal: Automated Handwritten Text Transcription for Historical Medieval Manuscripts","publication_year":2025,"publication_date":"2025-01-25","ids":{"openalex":"https://openalex.org/W4406871776","doi":"https://doi.org/10.3390/jimaging11020036","pmid":"https://pubmed.ncbi.nlm.nih.gov/39997538"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11020036","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jimaging11020036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100896370","display_name":"Alexandre Hil\u00e1rio Berenguer de Matos","orcid":null},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Alexandre Matos","raw_affiliation_strings":["Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100986644","display_name":"Pedro Almeida","orcid":"https://orcid.org/0009-0004-9005-6688"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro Almeida","raw_affiliation_strings":["Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019322980","display_name":"Paulo Lobato Correia","orcid":"https://orcid.org/0000-0001-6525-9572"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Paulo Correia","raw_affiliation_strings":["Instituto de Telecomunica\u00e7\u00f5es (IT), Instituto Superior Tecnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunica\u00e7\u00f5es (IT), Instituto Superior Tecnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal","institution_ids":["https://openalex.org/I4210120471","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077110373","display_name":"Osvaldo Pacheco","orcid":"https://orcid.org/0000-0002-3098-7163"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Osvaldo Pacheco","raw_affiliation_strings":["Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"Instituto de Engenharia Eletr\u00f3nica e Telem\u00e1tica de Aveiro (IEETA), Universidade de Aveiro, 3810-193 Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019322980"],"corresponding_institution_ids":["https://openalex.org/I141596103","https://openalex.org/I4210120471"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":2.7376,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87828363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"11","issue":"2","first_page":"36","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9460999965667725,"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":0.8072353601455688},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7270536422729492},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6634455919265747},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.6245140433311462},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6058056354522705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5608747005462646},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.5589564442634583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5308296084403992},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.48169928789138794},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4695245325565338},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45947733521461487},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.41763073205947876},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4149196743965149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3607885539531708},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13494035601615906},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.11448672413825989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072353601455688},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7270536422729492},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6634455919265747},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.6245140433311462},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6058056354522705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5608747005462646},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.5589564442634583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5308296084403992},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.48169928789138794},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4695245325565338},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45947733521461487},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.41763073205947876},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4149196743965149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3607885539531708},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13494035601615906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.11448672413825989},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging11020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11020036","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:39997538","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39997538","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11856379","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11856379","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"J Imaging","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:e00170c483414b86b240826144b31be3","is_oa":true,"landing_page_url":"https://doaj.org/article/e00170c483414b86b240826144b31be3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 11, Iss 2, p 36 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging11020036","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11020036","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G5188078587","display_name":null,"funder_award_id":"PTDC/HAR-HIS/5065/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2149128132","https://openalex.org/W2768926640","https://openalex.org/W2785875661","https://openalex.org/W2786974559","https://openalex.org/W2787677190","https://openalex.org/W2798826627","https://openalex.org/W2810085502","https://openalex.org/W2946759265","https://openalex.org/W2983390508","https://openalex.org/W3016645284","https://openalex.org/W3105910873","https://openalex.org/W3128300274","https://openalex.org/W3163396276","https://openalex.org/W3194824089","https://openalex.org/W4280540876","https://openalex.org/W4288043960","https://openalex.org/W4289860959","https://openalex.org/W4382202677","https://openalex.org/W4385819993","https://openalex.org/W4400740404"],"related_works":["https://openalex.org/W3003949997","https://openalex.org/W3199359807","https://openalex.org/W2110485610","https://openalex.org/W3047607512","https://openalex.org/W4390983538","https://openalex.org/W2744690920","https://openalex.org/W2107320953","https://openalex.org/W2787081548","https://openalex.org/W183832189","https://openalex.org/W2536878212"],"abstract_inverted_index":{"The":[0,51,90,130,196,221],"transcription":[1,46,217],"of":[2,48,66,73,84,127,181,240],"historical":[3,49,188],"manuscripts":[4],"aims":[5],"at":[6],"making":[7],"our":[8],"cultural":[9],"heritage":[10],"more":[11],"accessible":[12],"to":[13,17,42,162,212],"experts":[14],"and":[15,26,40,102,114,140],"also":[16],"the":[18,45,60,64,67,71,99,107,118,128,147,168,179,204,230],"larger":[19],"public,":[20],"but":[21],"it":[22],"is":[23,53,234],"a":[24,82,176,237],"challenging":[25],"time-intensive":[27],"task.":[28],"This":[29],"paper":[30],"contributes":[31],"an":[32,74],"automated":[33],"solution":[34],"for":[35,106,178,186,215,227],"text":[36,119,131],"layout":[37,108],"recognition,":[38],"segmentation,":[39],"recognition":[41,109,132],"speed":[43],"up":[44],"process":[47],"manuscripts.":[50],"focus":[52],"on":[54,146,203,229],"transcribing":[55],"Portuguese":[56,78,86],"municipal":[57],"documents":[58],"from":[59],"Middle":[61],"Ages":[62],"in":[63],"context":[65],"iForal":[68],"project,":[69],"including":[70],"contribution":[72],"annotated":[75],"dataset":[76,198],"containing":[77],"medieval":[79],"documents,":[80],"notably":[81,191],"corpus":[83],"67":[85],"royal":[87],"charter":[88],"data.":[89],"proposed":[91],"system":[92],"can":[93,152,172,224],"accurately":[94],"identify":[95],"document":[96],"layouts,":[97],"isolate":[98],"text,":[100],"segment,":[101],"transcribe":[103],"it.":[104],"Results":[105],"model":[110,121,133],"achieved":[111,122,134],"0.98":[112,115],"mAP@0.50":[113],"precision,":[116],"while":[117],"segmentation":[120,219],"0.91":[123],"mAP@0.50,":[124],"detecting":[125],"95%":[126],"lines.":[129],"8.1%":[135],"character":[136],"error":[137,143],"rate":[138,144],"(CER)":[139],"25.5%":[141],"word":[142],"(WER)":[145],"test":[148],"set.":[149],"These":[150],"results":[151],"then":[153],"be":[154,173,213,225],"validated":[155],"by":[156,236],"palaeographers":[157],"with":[158],"less":[159],"effort,":[160],"contributing":[161],"achieving":[163],"high-quality":[164],"transcriptions":[165],"faster.":[166],"Moreover,":[167],"automatic":[169,216],"models":[170,182,222],"developed":[171,223],"utilized":[174],"as":[175],"basis":[177],"creation":[180],"that":[183],"perform":[184],"well":[185],"other":[187],"handwriting":[189],"styles,":[190],"using":[192],"transfer":[193],"learning":[194],"techniques.":[195],"contributed":[197],"has":[199],"been":[200],"made":[201],"available":[202],"HTR":[205],"United":[206],"catalogue,":[207],"which":[208,233],"includes":[209],"training":[210],"datasets":[211],"used":[214,235],"or":[218],"models.":[220],"used,":[226],"instance,":[228],"eSriptorium":[231],"platform,":[232],"vast":[238],"community":[239],"experts.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}