{"id":"https://openalex.org/W2058178431","doi":"https://doi.org/10.1117/12.2003731","title":"A segmentation-free approach to Arabic and Urdu OCR","display_name":"A segmentation-free approach to Arabic and Urdu OCR","publication_year":2013,"publication_date":"2013-02-04","ids":{"openalex":"https://openalex.org/W2058178431","doi":"https://doi.org/10.1117/12.2003731","mag":"2058178431"},"language":"en","primary_location":{"id":"doi:10.1117/12.2003731","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2003731","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},"type":"article","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/A5069476356","display_name":"Nazly Sabbour","orcid":null},"institutions":[{"id":"https://openalex.org/I96823368","display_name":"German University in Cairo","ror":"https://ror.org/03rjt0z37","country_code":"EG","type":"education","lineage":["https://openalex.org/I96823368"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Nazly Sabbour","raw_affiliation_strings":["German Univ. in Cairo (Egypt)","German University in Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"German Univ. in Cairo (Egypt)","institution_ids":["https://openalex.org/I96823368"]},{"raw_affiliation_string":"German University in Cairo, Egypt","institution_ids":["https://openalex.org/I96823368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003304863","display_name":"Faisal Shafait","orcid":"https://orcid.org/0000-0002-0922-0566"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Faisal Shafait","raw_affiliation_strings":["German Research Ctr. for Artificial Intelligence (Germany)"],"affiliations":[{"raw_affiliation_string":"German Research Ctr. for Artificial Intelligence (Germany)","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069476356"],"corresponding_institution_ids":["https://openalex.org/I96823368"],"apc_list":null,"apc_paid":null,"fwci":6.6346,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.97220542,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8658","issue":null,"first_page":"86580N","last_page":"86580N"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9987999796867371,"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":0.9962999820709229,"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/urdu","display_name":"Urdu","score":0.9703769087791443},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8554199934005737},{"id":"https://openalex.org/keywords/cursive","display_name":"Cursive","score":0.8357235193252563},{"id":"https://openalex.org/keywords/arabic-script","display_name":"Arabic script","score":0.7854386568069458},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7103034257888794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6577052474021912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6442795395851135},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6175092458724976},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49425625801086426},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4148557782173157},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23922660946846008},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1865687370300293}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.9703769087791443},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554199934005737},{"id":"https://openalex.org/C2778943297","wikidata":"https://www.wikidata.org/wiki/Q1079418","display_name":"Cursive","level":2,"score":0.8357235193252563},{"id":"https://openalex.org/C2777323237","wikidata":"https://www.wikidata.org/wiki/Q1828555","display_name":"Arabic script","level":3,"score":0.7854386568069458},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7103034257888794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6577052474021912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442795395851135},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6175092458724976},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49425625801086426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4148557782173157},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23922660946846008},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1865687370300293},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1117/12.2003731","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2003731","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/4b1bdb5c-167c-42d8-bbb9-cf621ace3550","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/4b1bdb5c-167c-42d8-bbb9-cf621ace3550","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sabbour , N &amp; Shafait , F 2013 , A segmentation-free approach to Arabic and Urdu OCR . in Document Recognition and Retrieval XX . vol. 8658 , SPIE , USA , pp. 1-12 , IS &amp;T/SPIE Electronic Imaging Conference , Burlingame , California , United States , 3/02/13 . https://doi.org/10.1117/12.2003731","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csse.uwa.edu.au/~shafait/papers/Nazly-Shape-Context-Urdu-OCR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W5860701","https://openalex.org/W2030881003","https://openalex.org/W2057175746","https://openalex.org/W2077966050","https://openalex.org/W2085511467","https://openalex.org/W2126727781","https://openalex.org/W2132072045","https://openalex.org/W2142336626","https://openalex.org/W2144887653"],"related_works":["https://openalex.org/W1876505772","https://openalex.org/W1493190742","https://openalex.org/W3135396011","https://openalex.org/W2058178431","https://openalex.org/W2949697310","https://openalex.org/W2616807405","https://openalex.org/W4309734222","https://openalex.org/W2157057015","https://openalex.org/W3108981824","https://openalex.org/W3087330769"],"abstract_inverted_index":{"In":[0,102],"this":[1],"paper,":[2],"we":[3,108,151],"present":[4],"a":[5,111,128],"generic":[6],"Optical":[7],"Character":[8],"Recognition":[9],"system":[10,135,158],"for":[11,22,86,97,136],"Arabic":[12,23,29,44,53,73,88,143,163],"script":[13,24,30,54,89],"languages":[14],"called":[15,116],"Nabocr.":[16],"Nabocr":[17,63],"uses":[18],"OCR":[19],"approaches":[20],"specific":[21],"recognition.":[25],"Performing":[26],"recognition":[27,129],"on":[28,171],"text":[31,38,115,139],"is":[32,47,64,140,148,174],"relatively":[33],"more":[34],"difficult":[35],"than":[36],"Latin":[37],"due":[39],"to":[40,67,83,104],"the":[41,146,154,166,176],"nature":[42],"of":[43,113,127,133,156,168],"script,":[45],"which":[46,123],"cursive":[48],"and":[49,72,100,165],"context":[50],"sensitive.":[51],"Moreover,":[52,150],"has":[55],"different":[56,125],"writing":[57],"styles":[58],"that":[59],"vary":[60],"in":[61],"complexity.":[62],"initially":[65],"trained":[66,80],"recognize":[68],"both":[69,98,169],"Urdu":[70,99,106,114,137],"Nastaleeq":[71],"Naskh":[74],"fonts.":[75],"However,":[76],"it":[77],"can":[78],"be":[79,84],"by":[81],"users":[82],"used":[85],"other":[87],"languages.":[90],"We":[91],"have":[92,109,152],"evaluated":[93],"our":[94,134,157],"system's":[95],"performance":[96,132,147,155,167],"Arabic.":[101],"order":[103],"evaluate":[105],"recognition,":[107,164],"generated":[110],"dataset":[112],"UPTI":[117],"(Urdu":[118],"Printed":[119],"Text":[120],"Image":[121],"Database),":[122],"measures":[124],"aspects":[126],"system.":[130],"The":[131],"clean":[138,144,172],"91%.":[141],"For":[142],"text,":[145],"86%.":[149],"compared":[153],"against":[159],"Tesseract's":[160],"newly":[161],"released":[162],"systems":[170],"images":[173],"almost":[175],"same.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-11T06:13:24.991567","created_date":"2025-10-10T00:00:00"}
