{"id":"https://openalex.org/W6925739701","doi":"https://doi.org/10.21227/hhez-0r18","title":"SinOCR and SinFUND","display_name":"SinOCR and SinFUND","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W6925739701","doi":"https://doi.org/10.21227/hhez-0r18"},"language":"en","primary_location":{"id":"doi:10.21227/hhez-0r18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/hhez-0r18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/hhez-0r18","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gunathilaka, Kavishka","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Gunathilaka, Kavishka","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hewagama, Danusha","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Hewagama, Danusha","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pushpakumara, Supul","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Pushpakumara, Supul","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ambegoda, Thanuja","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Ambegoda, Thanuja","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Moratuwa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Moratuwa","institution_ids":["https://openalex.org/I195740183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I195740183"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12499","display_name":"Diphtheria, Corynebacterium, and Tetanus","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1310","display_name":"Endocrinology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12499","display_name":"Diphtheria, Corynebacterium, and Tetanus","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1310","display_name":"Endocrinology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13597","display_name":"Medicine and Dermatology Studies History","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2708","display_name":"Dermatology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11274","display_name":"Botulinum Toxin and Related Neurological Disorders","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.7204999923706055},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6317999958992004},{"id":"https://openalex.org/keywords/sri-lanka","display_name":"Sri lanka","score":0.5214999914169312},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.439300000667572},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.42410001158714294},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.40380001068115234},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.3831999897956848},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.32749998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376000285148621},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.7204999923706055},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6317999958992004},{"id":"https://openalex.org/C3017649214","wikidata":"https://www.wikidata.org/wiki/Q854","display_name":"Sri lanka","level":3,"score":0.5214999914169312},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44929999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.3831999897956848},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2784999907016754},{"id":"https://openalex.org/C2778864079","wikidata":"https://www.wikidata.org/wiki/Q173285","display_name":"Digital data","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/hhez-0r18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/hhez-0r18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/hhez-0r18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/hhez-0r18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,21,25,30,64,95,125,137,171],"SinOCR":[3],"and":[4,17,29,50,106,119,127,146,153],"SinFUND":[5],"datasets,":[6],"two":[7],"comprehensive":[8],"resources":[9],"designed":[10],"to":[11,37,115,132],"advance":[12],"Optical":[13],"Character":[14],"Recognition":[15],"(OCR)":[16],"form":[18,86,128],"understanding":[19,87,129],"for":[20,34,83,93,124],"Sinhala":[22,35,48,77],"language.":[23],"SinOCR,":[24],"first":[26,65],"publicly":[27],"available":[28],"most":[31],"extensive":[32],"dataset":[33,68],"OCR":[36,126],"date,":[38],"includes":[39],"100,000":[40],"images":[41,52],"featuring":[42],"printed":[43],"text":[44],"in":[45,101,108,150,166],"200":[46],"different":[47],"fonts":[49],"1,135":[51],"of":[53,60,69,139],"handwritten":[54],"text,":[55],"capturing":[56],"a":[57,80,167],"wide":[58],"spectrum":[59],"writing":[61],"styles.":[62],"SinFUND,":[63],"fully":[66],"annotated":[67],"its":[70],"kind,":[71],"comprises":[72],"100":[73],"diverse,":[74],"manually":[75],"filled":[76],"forms,":[78],"offering":[79],"robust":[81],"foundation":[82],"developing":[84],"template-free":[85],"models.":[88],"These":[89],"datasets":[90,113,134],"are":[91],"crucial":[92],"addressing":[94],"challenges":[96],"posed":[97],"by":[98],"paper-based":[99],"documentation":[100],"low-resource":[102],"languages,":[103],"enhancing":[104],"accuracy":[105],"efficiency":[107],"digital":[109,144],"document":[110],"processing.":[111],"Both":[112],"aim":[114],"stimulate":[116],"further":[117],"research":[118,168],"innovation,":[120],"providing":[121],"valuable":[122],"benchmarks":[123,162],"communities.":[130],"Access":[131],"these":[133],"will":[135,163],"facilitate":[136],"development":[138],"more":[140],"sophisticated":[141],"models,":[142],"promoting":[143],"transformation":[145],"improved":[147],"administrative":[148],"processes":[149],"Sri":[151],"Lanka":[152],"potentially":[154],"other":[155],"regions":[156],"with":[157,170],"similar":[158],"linguistic":[159],"challenges.":[160],"The":[161],"be":[164],"published":[165],"article":[169],"same":[172],"title.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
