{"id":"https://openalex.org/W7139924825","doi":"https://doi.org/10.1016/j.procs.2026.01.058","title":"Raqim: A Hybrid Framework for Arabic OCR Correction Using Dictionary-Based Methods and Large Language Models","display_name":"Raqim: A Hybrid Framework for Arabic OCR Correction Using Dictionary-Based Methods and Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139924825","doi":"https://doi.org/10.1016/j.procs.2026.01.058"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.058","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.058","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.058","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130239694","display_name":"Layan Almegbil","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Layan Almegbil","raw_affiliation_strings":["Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130232956","display_name":"Khalid Alduwaysan","orcid":null},"institutions":[{"id":"https://openalex.org/I28022161","display_name":"King Saud University","ror":"https://ror.org/02f81g417","country_code":"SA","type":"education","lineage":["https://openalex.org/I28022161"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Khalid Alduwaysan","raw_affiliation_strings":["King Saud University, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Saud University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I28022161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130215361","display_name":"Sarah Alqahtani","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sarah Alqahtani","raw_affiliation_strings":["Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130251444","display_name":"Lama Alquraishi","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Lama Alquraishi","raw_affiliation_strings":["Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130231599","display_name":"Raghad Alanazi","orcid":null},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Raghad Alanazi","raw_affiliation_strings":["Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130227155","display_name":"Omar Elnashar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar Elnashar","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130222350","display_name":"Mohamed Amin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Amin","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085411452","display_name":"Waad Alshammari","orcid":"https://orcid.org/0000-0002-9166-5619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waad Alshammari","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309352","display_name":"Raghad Al-Rasheed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghad Al-Rasheed","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130249515","display_name":"Bayan Almuqhim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bayan Almuqhim","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090577539","display_name":"Abdulrahman Alosaimy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdulrahman AlOsaimy","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130246420","display_name":"Rawan Almatham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rawan Almatham","raw_affiliation_strings":["King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Salman Global Academy for Arabic Language, Riyadh, Saudi Arabia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5130232956"],"corresponding_institution_ids":["https://openalex.org/I28022161"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93127067,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"493","last_page":"502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6427000164985657,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6427000164985657,"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/T10028","display_name":"Topic Modeling","score":0.06509999930858612,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.054999999701976776,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5630999803543091},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5202000141143799},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31769999861717224},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.31470000743865967},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24570000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9463000297546387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6628000140190125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626800000667572},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.23680000007152557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.058","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.058","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.058","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.058","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7721797823905945}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"Raqim,":[3],"a":[4,33,37],"hybrid":[5],"framework":[6],"for":[7],"correcting":[8],"Arabic":[9],"optical":[10],"character":[11],"recognition":[12],"(OCR)":[13],"errors":[14],"by":[15,49],"integrating":[16],"dictionary-based":[17,107,120],"and":[18,78,122],"generative":[19],"techniques.":[20],"The":[21,80,92],"key":[22],"contributions":[23],"of":[24,31,39,55,61,114,118,125,131],"this":[25],"research":[26],"are:":[27],"(1)":[28],"the":[29,50,53,59,112,115,123,126,132],"development":[30],"CorpusFilter,":[32],"layer":[34],"built":[35],"on":[36],"dictionary":[38],"500,000":[40],"error-correction":[41],"pairs":[42],"extracted":[43],"from":[44,88],"real-world":[45],"OCR":[46,56],"outputs":[47],"generated":[48],"Tesseract":[51],"engine.(2)":[52],"enhancement":[54],"performance":[57,94],"through":[58],"integration":[60],"large":[62],"language":[63],"models":[64,130],"(LLMs).Correction":[65],"quality":[66],"was":[67,98,104],"assessed":[68],"across":[69],"four":[70],"LLMs:":[71],"GPT-4,":[72],"Gemini":[73,101],"2.0":[74,102],"Flash,":[75],"Mistral":[76],"Saba,":[77],"LLaMA3-8B.":[79],"results":[81,110],"show":[82],"that":[83],"CorpusFilter":[84],"alone":[85],"raised":[86],"accuracy":[87,97],"87.89%":[89],"to":[90],"89.18%.":[91],"highest":[93],"89.81%":[95],"correction":[96],"achieved":[99],"when":[100],"Flash":[103],"combined":[105],"with":[106],"correction.":[108],"These":[109],"illustrate":[111],"relevance":[113],"dual":[116],"approach":[117],"using":[119],"techniques":[121],"application":[124],"state-of-":[127],"the-art":[128],"deep":[129],"LLM":[133],"toolkit.":[134]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}
