{"id":"https://openalex.org/W2024642444","doi":"https://doi.org/10.1117/12.335806","title":"The Bible, truth, and multilingual OCR evaluation","display_name":"The Bible, truth, and multilingual OCR evaluation","publication_year":1999,"publication_date":"1999-01-07","ids":{"openalex":"https://openalex.org/W2024642444","doi":"https://doi.org/10.1117/12.335806","mag":"2024642444"},"language":"en","primary_location":{"id":"doi:10.1117/12.335806","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.335806","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/A5052200294","display_name":"Tapas Kanungo","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tapas Kanungo","raw_affiliation_strings":["Univ. of Maryland/College Park (USA)","University of Maryland, College Park, United States"],"affiliations":[{"raw_affiliation_string":"Univ. of Maryland/College Park (USA)","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, United States","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059946729","display_name":"Philip Resnik","orcid":"https://orcid.org/0000-0002-6130-8602"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Resnik","raw_affiliation_strings":["Univ. of Maryland/College Park (USA)","University of Maryland, College Park, United States"],"affiliations":[{"raw_affiliation_string":"Univ. of Maryland/College Park (USA)","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, United States","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052200294"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":0.37337113,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.60545883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3651","issue":null,"first_page":"86","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9944999814033508,"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":0.9944999814033508,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9107000231742859,"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":0.8368990421295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7391992807388306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6431290507316589},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5009617805480957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4449272155761719},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.436197966337204},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3855816125869751},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35040295124053955},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12192842364311218}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8368990421295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391992807388306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6431290507316589},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5009617805480957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4449272155761719},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.436197966337204},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3855816125869751},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35040295124053955},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12192842364311218},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.335806","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.335806","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4249048193","https://openalex.org/W3000360420","https://openalex.org/W1931440630","https://openalex.org/W3172144307","https://openalex.org/W4396855230","https://openalex.org/W3184247917","https://openalex.org/W4235657630","https://openalex.org/W2331401504","https://openalex.org/W2620283452","https://openalex.org/W2123530708"],"abstract_inverted_index":{"In":[0],"this":[1,55],"paper":[2],"we":[3,97],"propose":[4],"to":[5,40,77,88],"use":[6],"the":[7,106,109,117],"Bible":[8,27,91,119],"as":[9],"a":[10,22,60,83],"dataset":[11,63,120],"for":[12,93],"comparing":[13],"OCR":[14,113],"accuracy":[15],"across":[16],"languages.":[17],"Besides":[18],"being":[19],"available":[20],"in":[21,32,123],"wide":[23],"range":[24],"of":[25,50,82],"languages,":[26,95],"translations":[28],"are":[29,98],"closely":[30],"parallel":[31],"content,":[33],"carefully":[34],"translated,":[35],"surprisingly":[36],"relevant":[37],"with":[38,64,102],"respect":[39],"modern-day":[41],"language,":[42],"and":[43,96,108],"quite":[44],"inexpensive.":[45],"A":[46],"project":[47],"at":[48],"University":[49],"Maryland":[51],"is":[52,121],"currently":[53,122],"implementing":[54],"idea.":[56],"We":[57,70,86],"have":[58,71],"created":[59],"scanned":[61],"image":[62,74],"groundtruth":[65],"from":[66],"an":[67],"Arabic":[68,118],"Bible.":[69,85],"also":[72],"used":[73],"degradation":[75],"models":[76],"create":[78],"synthetically":[79],"degraded":[80],"images":[81],"French":[84],"hope":[87],"generate":[89],"similar":[90,103],"datasets":[92],"other":[94],"exploring":[99],"alternative":[100],"corpora":[101],"properties":[104],"such":[105],"Koran":[107],"Bhagavad":[110],"Gita.":[111],"Quantitative":[112],"evaluation":[114],"based":[115],"on":[116],"progress.":[124]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
