{"id":"https://openalex.org/W2014468488","doi":"https://doi.org/10.1109/isda.2010.5687228","title":"Omni font OCR error correction with effect on retrieval","display_name":"Omni font OCR error correction with effect on retrieval","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2014468488","doi":"https://doi.org/10.1109/isda.2010.5687228","mag":"2014468488"},"language":"en","primary_location":{"id":"doi:10.1109/isda.2010.5687228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2010.5687228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th International Conference on Intelligent Systems Design and Applications","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/A5070783596","display_name":"Walid Magdy","orcid":"https://orcid.org/0000-0001-9676-1338"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]},{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["EG","IE"],"is_corresponding":false,"raw_author_name":"Walid Magdy","raw_affiliation_strings":["Faculty of Engineering, Cairo University, Egypt","School of Computing, University of Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Cairo University, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"School of Computing, University of Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933","https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111452036","display_name":"Kareem Darwish","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kareem Darwish","raw_affiliation_strings":["Cairo Microsoft Innovation Center, Microsoft Research Limited, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cairo Microsoft Innovation Center, Microsoft Research Limited, Cairo, Egypt","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"415","last_page":"420"},"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":0.9958999752998352,"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/T11439","display_name":"Video Analysis and Summarization","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8651103973388672},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8299959897994995},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.7944850921630859},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.733923077583313},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7184080481529236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6101499795913696},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5558599829673767},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5330881476402283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4802877604961395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45978763699531555},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4365652799606323},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4188229739665985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37888723611831665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2445879876613617},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1797240972518921},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09939387440681458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651103973388672},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8299959897994995},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.7944850921630859},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.733923077583313},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7184080481529236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6101499795913696},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5558599829673767},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5330881476402283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4802877604961395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45978763699531555},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4365652799606323},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4188229739665985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37888723611831665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2445879876613617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1797240972518921},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09939387440681458},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isda.2010.5687228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2010.5687228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 10th International Conference on Intelligent Systems Design and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1501437810","https://openalex.org/W1510248492","https://openalex.org/W1593368611","https://openalex.org/W1631260214","https://openalex.org/W1650656906","https://openalex.org/W1841959837","https://openalex.org/W1985708392","https://openalex.org/W2006477783","https://openalex.org/W2011586660","https://openalex.org/W2012191724","https://openalex.org/W2015338694","https://openalex.org/W2018616927","https://openalex.org/W2033937535","https://openalex.org/W2038218748","https://openalex.org/W2056250865","https://openalex.org/W2057900969","https://openalex.org/W2070661748","https://openalex.org/W2096550092","https://openalex.org/W2103430523","https://openalex.org/W2109556717","https://openalex.org/W2126815469","https://openalex.org/W2128254978","https://openalex.org/W2135809805","https://openalex.org/W2137970221","https://openalex.org/W2155903443","https://openalex.org/W2166968190","https://openalex.org/W2436413986","https://openalex.org/W3087923659","https://openalex.org/W4238592733","https://openalex.org/W6629966167","https://openalex.org/W6636891654","https://openalex.org/W6674461064","https://openalex.org/W6675321784","https://openalex.org/W6678977954","https://openalex.org/W6679212109","https://openalex.org/W6684612417","https://openalex.org/W6784013818"],"related_works":["https://openalex.org/W2402920184","https://openalex.org/W2147687867","https://openalex.org/W2582695981","https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2496907786","https://openalex.org/W2483185727","https://openalex.org/W2612325988","https://openalex.org/W2490611030","https://openalex.org/W2575782020"],"abstract_inverted_index":{"Recent":[0],"library":[1],"digitization":[2],"projects":[3],"attempt":[4],"to":[5,84],"provide":[6],"large":[7],"collections":[8],"of":[9,44,51,58,125,132,145,148],"printed":[10,157],"material":[11],"from":[12],"varying":[13],"sources":[14],"in":[15,34,68,154,160],"a":[16,40,71,133],"searchable":[17],"format.":[18],"The":[19,80,122,143],"scanned":[20,59],"documents":[21,158],"are":[22,89],"typically":[23,31],"processed":[24],"using":[25],"Optical":[26],"Character":[27],"Recognition":[28],"(OCR),":[29],"which":[30],"introduces":[32],"errors":[33,151],"the":[35,100,126,130],"text.":[36],"This":[37],"paper":[38],"proposes":[39],"technique":[41,81,102,128],"for":[42],"correction":[43,86,105,120],"OCR":[45,53],"degraded":[46],"text":[47],"that":[48,75,88],"is":[49,63,112,129,152],"independent":[50,57,147],"character-level":[52],"errors,":[54],"and":[55,94,115,140,163],"hence":[56],"document":[60],"source.":[61],"It":[62],"based":[64,90],"on":[65,91,109],"language":[66,92,135],"modeling":[67,93],"conjunction":[69],"with":[70,118],"uniform":[72],"character":[73,96,149],"model":[74,136],"uses":[76],"edit":[77],"distance":[78],"only.":[79],"compares":[82],"well":[83],"state-of-the-art":[85,119],"techniques":[87],"source-specific":[95],"error":[97],"models.":[98],"Although":[99],"proposed":[101,127],"yielded":[103],"lower":[104],"effectiveness,":[106],"its":[107],"impact":[108],"retrieval":[110],"effectiveness":[111],"statistically":[113],"significant":[114],"at":[116],"par":[117],"techniques.":[121],"main":[123],"requirement":[124],"training":[131],"\u201cgood\u201d":[134],"matching":[137],"genre,":[138],"style,":[139],"temporal":[141],"coverage.":[142],"advantage":[144],"being":[146],"level":[150],"clear":[153],"applications":[155],"were":[156],"vary":[159],"source,":[161],"font,":[162],"degradation":[164],"level.":[165]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}