{"id":"https://openalex.org/W4408861331","doi":"https://doi.org/10.1109/icca62237.2024.10928060","title":"Fine-Tuning an Arabic OCR Model using Tesseract 5.0","display_name":"Fine-Tuning an Arabic OCR Model using Tesseract 5.0","publication_year":2024,"publication_date":"2024-12-17","ids":{"openalex":"https://openalex.org/W4408861331","doi":"https://doi.org/10.1109/icca62237.2024.10928060"},"language":"en","primary_location":{"id":"doi:10.1109/icca62237.2024.10928060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca62237.2024.10928060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Computer and Applications (ICCA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116806070","display_name":"Omar Samir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar Samir","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116806071","display_name":"Yousef Waleed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yousef Waleed","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104081888","display_name":"Ibrahim Ahmed","orcid":"https://orcid.org/0000-0001-7814-5152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ibrahim Ahmed","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116806072","display_name":"Omar El-Gohary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omar El-Gohary","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116806073","display_name":"Shaden El-Naggar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaden El-Naggar","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116806074","display_name":"Farida Fawzy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farida Fawzy","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Malak Emam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malak Emam","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mayar Emam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayar Emam","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068529187","display_name":"Mohamed Taher Alrefaie","orcid":"https://orcid.org/0000-0002-2031-3528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Taher Al-Refaie","raw_affiliation_strings":["Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Egypt University of Informatics, New Administrative Capital,Computing and Information Sciences,Egypt","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3629,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83251232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9733999967575073,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9416999816894531,"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/arabic","display_name":"Arabic","score":0.6404551267623901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6339939832687378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5511595010757446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4614737033843994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3609467148780823},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13575959205627441}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6404551267623901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6339939832687378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511595010757446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4614737033843994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3609467148780823},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13575959205627441},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca62237.2024.10928060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca62237.2024.10928060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Computer and Applications (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W6804721635"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Optical":[0],"Character":[1],"Recognition":[2],"(OCR)":[3],"is":[4],"a":[5,47,125],"crucial":[6],"technology":[7],"for":[8,25],"the":[9,29,60,64,69,73,96,99,108,111,118],"digital":[10],"processing":[11],"and":[12,53,88,104,106],"preservation":[13],"of":[14,31,63,98,110,120],"textual":[15],"information.":[16],"While":[17],"significant":[18],"progress":[19],"has":[20],"been":[21],"made":[22],"in":[23,78,134],"OCR":[24,57,66,128],"commonly":[26],"used":[27],"languages,":[28],"recognition":[30],"Arabic":[32,56,100,127],"script":[33],"poses":[34],"unique":[35],"challenges":[36],"due":[37],"to":[38,50,117,141],"its":[39],"complex":[40],"linguistic":[41],"characteristics.":[42],"This":[43,114],"research":[44],"paper":[45],"presents":[46],"comprehensive":[48],"approach":[49],"collecting":[51],"data":[52],"training":[54],"an":[55],"system":[58],"using":[59],"latest":[61],"version":[62],"Tesseract":[65,71],"engine.":[67],"Integrating":[68],"customized":[70],"model,":[72],"study":[74,115],"achieved":[75],"high":[76],"accuracy":[77],"text":[79,143],"recognition,":[80,123],"as":[81],"measured":[82],"by":[83],"character":[84,122],"error":[85,90],"rate":[86,91],"(CER)":[87],"word":[89],"(WER).":[92],"The":[93],"findings":[94],"highlight":[95],"complexities":[97],"language,":[101],"including":[102],"diacritics":[103],"ligatures,":[105],"discuss":[107],"limitations":[109],"current":[112],"approach.":[113],"contributes":[116],"advancement":[119],"optical":[121],"providing":[124],"robust":[126],"solution":[129],"that":[130],"can":[131],"be":[132],"leveraged":[133],"various":[135],"applications,":[136],"from":[137],"digitizing":[138],"historical":[139],"documents":[140],"automating":[142],"extraction.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
