{"id":"https://openalex.org/W4411902268","doi":"https://doi.org/10.1007/s10032-025-00543-9","title":"Tabular context-aware optical character recognition and tabular data reconstruction for historical records","display_name":"Tabular context-aware optical character recognition and tabular data reconstruction for historical records","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4411902268","doi":"https://doi.org/10.1007/s10032-025-00543-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/40985006"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-025-00543-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00543-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00543-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00543-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056117065","display_name":"Loitongbam Gyanendro Singh","orcid":"https://orcid.org/0000-0002-7594-6146"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Loitongbam Gyanendro Singh","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088719080","display_name":"Stuart E. Middleton","orcid":"https://orcid.org/0000-0001-8305-8176"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stuart E. Middleton","raw_affiliation_strings":["School of Electronics and Computer Science, University of Southampton, Southampton, UK"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056117065"],"corresponding_institution_ids":["https://openalex.org/I43439940"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13315932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":"3","first_page":"357","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9958000183105469,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861999750137329,"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/character","display_name":"Character (mathematics)","score":0.831849217414856},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6523848176002502},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5830881595611572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5560636520385742},{"id":"https://openalex.org/keywords/historical-record","display_name":"Historical record","score":0.5165859460830688},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4502406418323517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3994588255882263},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.331760048866272},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3232344686985016},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.19851461052894592},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.18888354301452637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0875386893749237},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08425045013427734},{"id":"https://openalex.org/keywords/biography","display_name":"Biography","score":0.05530652403831482}],"concepts":[{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.831849217414856},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6523848176002502},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5830881595611572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5560636520385742},{"id":"https://openalex.org/C2992790187","wikidata":"https://www.wikidata.org/wiki/Q1145106","display_name":"Historical record","level":3,"score":0.5165859460830688},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4502406418323517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3994588255882263},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.331760048866272},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3232344686985016},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.19851461052894592},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.18888354301452637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0875386893749237},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08425045013427734},{"id":"https://openalex.org/C520712124","wikidata":"https://www.wikidata.org/wiki/Q36279","display_name":"Biography","level":2,"score":0.05530652403831482},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10032-025-00543-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00543-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00543-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},{"id":"pmid:40985006","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40985006","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":"International journal on document analysis and recognition (Online)","raw_type":null},{"id":"pmh:oai:eprints.soton.ac.uk:502849","is_oa":false,"landing_page_url":"http://doi.org/10.1007/s10032-025-00543-9>).","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:europepmc.org:11259549","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12450121","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12450121/pdf/10032_2025_Article_543.pdf","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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"},{"id":"pmh:oai:pubmedcentral.nih.gov:12450121","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12450121/","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":"Int J Doc Anal Recognit","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10032-025-00543-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-025-00543-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-025-00543-9.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2831640940","display_name":"Global Surface Air Temperature (GloSAT)","funder_award_id":"NE/S015604/1","funder_id":"https://openalex.org/F4320334631","funder_display_name":"Natural Environment Research Council"}],"funders":[{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320320331","display_name":"Met Office","ror":"https://ror.org/01ch2yn61"},{"id":"https://openalex.org/F4320334631","display_name":"Natural Environment Research Council","ror":"https://ror.org/02b5d8509"},{"id":"https://openalex.org/F7705544900","display_name":"Department for Science, Innovation and Technology","ror":"https://ror.org/028z36n30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411902268.pdf","grobid_xml":"https://content.openalex.org/works/W4411902268.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W30902120","https://openalex.org/W1981276685","https://openalex.org/W1987932675","https://openalex.org/W2022351003","https://openalex.org/W2097117768","https://openalex.org/W2137998699","https://openalex.org/W2139893662","https://openalex.org/W2144554289","https://openalex.org/W2769316437","https://openalex.org/W2786162033","https://openalex.org/W2963748441","https://openalex.org/W2964241181","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3003496674","https://openalex.org/W3004042913","https://openalex.org/W3014641072","https://openalex.org/W3033331029","https://openalex.org/W3034997246","https://openalex.org/W3034999214","https://openalex.org/W3049072356","https://openalex.org/W3095771422","https://openalex.org/W3096609285","https://openalex.org/W3104953317","https://openalex.org/W3107064625","https://openalex.org/W3118722740","https://openalex.org/W3164045210","https://openalex.org/W3181186176","https://openalex.org/W3181895085","https://openalex.org/W3184971748","https://openalex.org/W3217518891","https://openalex.org/W4288046074","https://openalex.org/W4304013646","https://openalex.org/W4312233877","https://openalex.org/W4312554912","https://openalex.org/W4382202677","https://openalex.org/W4385079034","https://openalex.org/W4385819984","https://openalex.org/W4385991037","https://openalex.org/W4386576653","https://openalex.org/W4387925380","https://openalex.org/W4390190120","https://openalex.org/W4398164033","https://openalex.org/W4402396664"],"related_works":["https://openalex.org/W1991513203","https://openalex.org/W2892704491","https://openalex.org/W3178467699","https://openalex.org/W4312612713","https://openalex.org/W4408696804","https://openalex.org/W2106936331","https://openalex.org/W1985626581","https://openalex.org/W2042634493","https://openalex.org/W2100798736","https://openalex.org/W2728450881"],"abstract_inverted_index":{"Digitizing":[0],"historical":[1,53],"tabular":[2,191],"records":[3,198],"is":[4],"essential":[5],"for":[6,138,187],"preserving":[7],"and":[8,26,71,106,126,140,159,175,208],"analyzing":[9],"valuable":[10],"data":[11],"across":[12],"various":[13],"fields,":[14],"but":[15],"it":[16,45,75,92],"presents":[17,46],"challenges":[18],"due":[19],"to":[20,36,62,84,119,170,199],"complex":[21,144],"layouts,":[22],"mixed":[23],"text":[24,59,80],"types,":[25],"degraded":[27,141],"document":[28,204],"quality.":[29],"This":[30,114,181],"paper":[31],"introduces":[32],"a":[33,48,77,110,127,131,154,160,184],"comprehensive":[34],"framework":[35,115,182],"address":[37],"these":[38],"issues":[39],"through":[40],"three":[41],"key":[42],"contributions.":[43],"First,":[44],"UoS_Data_Rescue,":[47],"novel":[49,78],"dataset":[50,207],"of":[51,66,190],"1,113":[52],"logbooks":[54],"with":[55,102,153],"over":[56],"594,000":[57],"annotated":[58],"cells,":[60],"designed":[61],"handle":[63],"the":[64,117,122],"complexities":[65],"handwritten":[67],"entries,":[68],"aging":[69],"artifacts,":[70],"intricate":[72],"layouts.":[73],"Second,":[74],"proposes":[76,93],"context-aware":[79],"extraction":[81],"approach":[82],"(TrOCR-ctx)":[83],"reduce":[85],"cascading":[86],"errors":[87],"during":[88],"table":[89,145,178],"digitization.":[90],"Third,":[91],"an":[94],"enhanced":[95],"end-to-end":[96],"OCR":[97,105,124,173],"pipeline":[98],"that":[99],"integrates":[100],"TrOCR-ctx":[101],"ByT5,":[103],"combining":[104],"post-OCR":[107],"correction":[108],"in":[109,130,172,177],"unified":[111],"training":[112],"framework.":[113],"enables":[116],"system":[118],"produce":[120],"both":[121],"raw":[123],"output":[125],"corrected":[128],"version":[129],"single":[132],"pass,":[133],"improving":[134],"recognition":[135],"accuracy,":[136],"particularly":[137],"multilingual":[139],"text,":[142],"within":[143],"digitization":[146,189],"tasks.":[147,180],"The":[148,206],"model":[149],"achieves":[150],"superior":[151],"performance":[152],"0.049":[155],"word":[156],"error":[157,163],"rate":[158],"0.035":[161],"character":[162],"rate,":[164],"outperforming":[165],"existing":[166],"methods":[167],"by":[168],"up":[169],"41%":[171],"tasks":[174],"10.74%":[176],"reconstruction":[179],"offers":[183],"robust":[185],"solution":[186],"large-scale":[188],"documents,":[192],"extending":[193],"its":[194],"applications":[195],"beyond":[196],"climate":[197],"other":[200],"domains":[201],"requiring":[202],"structured":[203],"preservation.":[205],"implementation":[209],"are":[210],"available":[211],"as":[212],"open-source":[213],"resources.":[214]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
