{"id":"https://openalex.org/W7127639802","doi":"https://doi.org/10.48550/arxiv.2602.03693","title":"OCRTurk: A Comprehensive OCR Benchmark for Turkish","display_name":"OCRTurk: A Comprehensive OCR Benchmark for Turkish","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127639802","doi":"https://doi.org/10.48550/arxiv.2602.03693"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.03693","doi":"https://doi.org/10.48550/arxiv.2602.03693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.03693","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102025505","display_name":"Deniz Y\u0131lmaz","orcid":"https://orcid.org/0000-0003-4570-9067","observed_orcids":["https://orcid.org/0000-0003-4570-9067"]},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Y\u0131lmaz, Deniz","raw_affiliation_strings":["Middle East Technical University , Computer Engineering Department , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Middle East Technical University , Computer Engineering Department , Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124978936","display_name":"Evren Ayberk Munis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Munis, Evren Ayberk","raw_affiliation_strings":["Politecnico di Torino , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino , Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040060728","display_name":"\u00c7a\u011fr\u0131 Toraman","orcid":"https://orcid.org/0000-0001-6976-3258","observed_orcids":["https://orcid.org/0000-0001-6976-3258"]},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Toraman, \u00c7a\u011fr\u0131","raw_affiliation_strings":["Middle East Technical University , Computer Engineering Department , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Middle East Technical University , Computer Engineering Department , Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134381451","display_name":"S\u00fcha Kagan K\u00f6se","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260380","display_name":"Roketsan","ror":"https://ror.org/03nt0pm37","country_code":"TR","type":"company","lineage":["https://openalex.org/I4405260380"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"K\u00f6se, S\u00fcha Ka\u011fan","raw_affiliation_strings":["Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey","institution_ids":["https://openalex.org/I4405260380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146824299","display_name":"Burak Akta\u015f","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260380","display_name":"Roketsan","ror":"https://ror.org/03nt0pm37","country_code":"TR","type":"company","lineage":["https://openalex.org/I4405260380"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Akta\u015f, Burak","raw_affiliation_strings":["Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey","institution_ids":["https://openalex.org/I4405260380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092706481","display_name":"Mehmet Can Baytekin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260380","display_name":"Roketsan","ror":"https://ror.org/03nt0pm37","country_code":"TR","type":"company","lineage":["https://openalex.org/I4405260380"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Baytekin, Mehmet Can","raw_affiliation_strings":["Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey","institution_ids":["https://openalex.org/I4405260380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082988235","display_name":"Bilge Kaan G\u00f6r\u00fcr","orcid":"https://orcid.org/0000-0001-9595-0997","observed_orcids":["https://orcid.org/0000-0001-9595-0997"]},"institutions":[{"id":"https://openalex.org/I4405260380","display_name":"Roketsan","ror":"https://ror.org/03nt0pm37","country_code":"TR","type":"company","lineage":["https://openalex.org/I4405260380"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"G\u00f6r\u00fcr, Bilge Kaan","raw_affiliation_strings":["Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Roketsan Inc. , Artificial Intelligence Technologies Unit , Turkey","institution_ids":["https://openalex.org/I4405260380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/optical-character-recognition","display_name":"optical character recognition","score":0.9240000247955322},{"id":"https://openalex.org/keywords/turkish-language","display_name":"Turkish language","score":0.8259999752044678},{"id":"https://openalex.org/keywords/document-parsing","display_name":"document parsing","score":0.7379999756813049},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7400000095367432},{"id":"https://openalex.org/keywords/paddleocr","display_name":"PaddleOCR","score":0.652999997138977},{"id":"https://openalex.org/keywords/academic-documents","display_name":"academic documents","score":0.625},{"id":"https://openalex.org/keywords/slide-decks","display_name":"slide decks","score":0.8230000138282776}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8058000206947327},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8023999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906000018119812},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.7447999715805054},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5692999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644000172615051},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4138999879360199},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.03693","doi":"https://doi.org/10.48550/arxiv.2602.03693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.03693","doi":"https://doi.org/10.48550/arxiv.2602.03693","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03693","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.6077346205711365,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Document":[0],"parsing":[1,56,78],"is":[2,25],"now":[3],"widely":[4],"used":[5],"in":[6,18,139],"applications,":[7],"such":[8,47],"as":[9,48],"large-scale":[10],"document":[11,55,66,77,85,151],"digitization,":[12],"retrieval-augmented":[13],"generation,":[14],"and":[15,20,31,40,65,84,104,132,142],"domain-specific":[16],"pipelines":[17],"healthcare":[19],"education.":[21],"Benchmarking":[22],"these":[23],"models":[24,111],"crucial":[26],"for":[27,44],"assessing":[28],"their":[29],"reliability":[30],"practical":[32],"robustness.":[33],"Existing":[34],"benchmarks":[35],"mostly":[36],"target":[37],"high-resource":[38],"languages":[39],"provide":[41],"limited":[42],"coverage":[43],"low-resource":[45],"settings,":[46],"Turkish.":[49],"Moreover,":[50],"existing":[51],"studies":[52],"on":[53,112,156],"Turkish":[54,76,95],"lack":[57],"a":[58,75],"standardized":[59],"benchmark":[60,79],"that":[61],"reflects":[62],"real-world":[63],"scenarios":[64],"diversity.":[67],"To":[68],"address":[69],"this":[70],"gap,":[71],"we":[72],"introduce":[73],"OCRTurk,":[74],"covering":[80],"multiple":[81],"layout":[82],"elements":[83],"categories":[86],"at":[87],"three":[88],"difficulty":[89,118],"levels.":[90],"OCRTurk":[91,113],"consists":[92],"of":[93],"180":[94],"documents":[96],"drawn":[97],"from":[98],"academic":[99],"articles,":[100],"theses,":[101],"slide":[102],"decks,":[103],"non-academic":[105,157],"articles.":[106],"We":[107,145],"evaluate":[108],"seven":[109],"OCR":[110],"using":[114],"element-wise":[115,128],"metrics.":[116],"Across":[117],"levels,":[119],"PaddleOCR":[120],"achieves":[121],"the":[122,162],"strongest":[123],"overall":[124],"results,":[125],"leading":[126],"most":[127,163],"metrics":[129],"except":[130],"figures":[131],"attaining":[133],"high":[134],"Normalized":[135],"Edit":[136],"Distance":[137],"scores":[138],"easy,":[140],"medium,":[141],"hard":[143],"subsets.":[144],"also":[146],"observe":[147],"performance":[148],"variation":[149],"by":[150],"type.":[152],"Models":[153],"perform":[154],"well":[155],"documents,":[158],"while":[159],"slideshows":[160],"become":[161],"challenging.":[164]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-02-06T00:00:00"}