{"id":"https://openalex.org/W2554682051","doi":"https://doi.org/10.1145/2910674.2910725","title":"BCE-Arabic-v1 dataset","display_name":"BCE-Arabic-v1 dataset","publication_year":2016,"publication_date":"2016-06-29","ids":{"openalex":"https://openalex.org/W2554682051","doi":"https://doi.org/10.1145/2910674.2910725","mag":"2554682051"},"language":"en","primary_location":{"id":"doi:10.1145/2910674.2910725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910674.2910725","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2910725&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2910725&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056953480","display_name":"Rana S.M. Saad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156128","display_name":"Electronics Research Institute","ror":"https://ror.org/0532wcf75","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210094263","https://openalex.org/I4210156128"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Rana S.M. Saad","raw_affiliation_strings":["Department of Computers and Systems, Electronics Research Institute, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computers and Systems, Electronics Research Institute, Cairo, Egypt","institution_ids":["https://openalex.org/I4210156128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073605585","display_name":"Randa Elanwar","orcid":"https://orcid.org/0000-0003-3690-7141"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I4210156128","display_name":"Electronics Research Institute","ror":"https://ror.org/0532wcf75","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210094263","https://openalex.org/I4210156128"]}],"countries":["EG","US"],"is_corresponding":false,"raw_author_name":"Randa I. Elanwar","raw_affiliation_strings":["Department of Computers and Systems, Electronics Research Institute, Cairo, Egypt and Department of Computer Science, Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computers and Systems, Electronics Research Institute, Cairo, Egypt and Department of Computer Science, Boston University, USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I4210156128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111822441","display_name":"N.S. Abdel Kader","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"N. S. Abdel Kader","raw_affiliation_strings":["Department of Electronics and Communications Engineering, Cairo University, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Communications Engineering, Cairo University, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059557009","display_name":"Samia A. Mashali","orcid":"https://orcid.org/0000-0002-5316-109X"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samia Mashali","raw_affiliation_strings":["Department of Computer Science, Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058798782","display_name":"Margrit Betke","orcid":"https://orcid.org/0000-0002-4491-6868"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margrit Betke","raw_affiliation_strings":["Department of Computer Science, Boston University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Boston University, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6039,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81053168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9835000038146973,"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":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.823591947555542},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.719292938709259},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6707895994186401},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6595516204833984},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6362878084182739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5677337050437927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4809812307357788},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.47400176525115967},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44838687777519226},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4403945207595825},{"id":"https://openalex.org/keywords/arabic-script","display_name":"Arabic script","score":0.437456876039505},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2774169445037842},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10873273015022278},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08456724882125854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823591947555542},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.719292938709259},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6707895994186401},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6595516204833984},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6362878084182739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5677337050437927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4809812307357788},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.47400176525115967},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44838687777519226},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4403945207595825},{"id":"https://openalex.org/C2777323237","wikidata":"https://www.wikidata.org/wiki/Q1828555","display_name":"Arabic script","level":3,"score":0.437456876039505},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2774169445037842},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10873273015022278},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08456724882125854},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2910674.2910725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910674.2910725","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2910725&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2910674.2910725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2910674.2910725","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2910725&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5209882110","display_name":"MRI Collaborative: Development of iRehab, an Intelligent Closed-Loop Instrument for Adaptive Rehabilitation","funder_award_id":"1337866","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2554682051.pdf","grobid_xml":"https://content.openalex.org/works/W2554682051.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W137651890","https://openalex.org/W189028356","https://openalex.org/W1561803714","https://openalex.org/W1975869473","https://openalex.org/W1989737761","https://openalex.org/W2021525266","https://openalex.org/W2072393922","https://openalex.org/W2096707493","https://openalex.org/W2103973877","https://openalex.org/W2114504958","https://openalex.org/W2116680608","https://openalex.org/W2120855160","https://openalex.org/W2128137392","https://openalex.org/W2138891831","https://openalex.org/W2142330437","https://openalex.org/W2148529025","https://openalex.org/W2149128132","https://openalex.org/W2156338447","https://openalex.org/W2318392748","https://openalex.org/W2406727294","https://openalex.org/W2527268310","https://openalex.org/W2536159077","https://openalex.org/W6607694189","https://openalex.org/W6699925990"],"related_works":["https://openalex.org/W4307308274","https://openalex.org/W597397715","https://openalex.org/W4309734222","https://openalex.org/W4391654281","https://openalex.org/W2895421669","https://openalex.org/W2093682362","https://openalex.org/W2894922719","https://openalex.org/W2599351107","https://openalex.org/W3108981824","https://openalex.org/W2890187879"],"abstract_inverted_index":{"Millions":[0],"of":[1,49,60,72,80,113,118,141,151,179,187,204],"individuals":[2],"in":[3,65,156,160,170,198],"the":[4,46,58,70,73,78,97,111,177,185,199,209],"Arab":[5],"world":[6],"have":[7],"significant":[8,194],"visual":[9,107],"impairments":[10],"that":[11,57,103,183],"make":[12],"it":[13],"difficult":[14],"for":[15,130,212],"them":[16],"to":[17,31,44,69,76,99,124],"access":[18],"printed":[19],"text.":[20],"Assistive":[21],"technologies":[22],"such":[23],"as":[24,127],"scanners":[25],"and":[26,133,147,154,163,168,196,201,207],"screen":[27],"readers":[28],"often":[29],"fail":[30],"turn":[32],"text":[33,159],"into":[34],"speech":[35],"because":[36],"optical":[37],"character":[38],"recognition":[39],"software":[40],"(OCR)":[41],"has":[42],"difficulty":[43],"interpret":[45],"textual":[47],"content":[48,153],"Arabic":[50,82,84,119,158],"documents.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"show":[56],"inaccessibility":[59],"scanned":[61,143],"PDF":[62],"documents":[63],"is":[64,89],"large":[66,115],"part":[67],"due":[68],"failure":[71],"OCR":[74,132],"engine":[75],"understand":[77],"layout":[79,86],"an":[81,91],"document.":[83],"document":[85,120,189],"analysis":[87],"(DLA)":[88],"therefore":[90],"urgent":[92],"research":[93],"topic,":[94],"motivated":[95],"by":[96],"goal":[98],"provide":[100],"assistive":[101],"technology":[102],"serves":[104],"people":[105],"with":[106],"impairments.":[108],"We":[109,175,192],"announce":[110],"launching":[112],"a":[114,128,149,180],"annotated":[116],"dataset":[117,137],"images,":[121],"called":[122],"BCE-Arabic-v1,":[123],"be":[125],"used":[126],"benchmark":[129,215],"DLA,":[131],"text-to-speech":[134],"research.":[135],"Our":[136],"contains":[138],"1,833":[139],"images":[140],"pages":[142],"from":[144],"180":[145],"books":[146],"represents":[148],"variety":[150],"page":[152],"layout,":[155],"particular,":[157],"various":[161],"fonts":[162],"sizes,":[164],"photographs,":[165],"tables,":[166],"diagrams,":[167],"charts":[169],"single":[171],"or":[172],"multiple":[173],"columns.":[174],"report":[176],"results":[178],"formative":[181],"study":[182],"investigated":[184],"performance":[186],"state-of-the-art":[188],"annotation":[190],"tools.":[191],"found":[193],"differences":[195],"limitations":[197],"functionality":[200],"labeling":[202],"speed":[203],"these":[205],"tools,":[206],"selected":[208],"best-performing":[210],"tool":[211],"annotating":[213],"our":[214],"BCE-Arabic-v1.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
