{"id":"https://openalex.org/W2038329042","doi":"https://doi.org/10.1145/2501115.2501126","title":"Why multiple document image binarizations improve OCR","display_name":"Why multiple document image binarizations improve OCR","publication_year":2013,"publication_date":"2013-08-13","ids":{"openalex":"https://openalex.org/W2038329042","doi":"https://doi.org/10.1145/2501115.2501126","mag":"2038329042"},"language":"en","primary_location":{"id":"doi:10.1145/2501115.2501126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2501115.2501126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing","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/A5077722320","display_name":"William B. Lund","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William B. Lund","raw_affiliation_strings":["Brigham Young University, Provo, Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, Utah","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065220846","display_name":"Douglas J. Kennard","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas J. Kennard","raw_affiliation_strings":["Brigham Young University, Provo, Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, Utah","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090791372","display_name":"Eric K. Ringger","orcid":null},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric K. Ringger","raw_affiliation_strings":["Brigham Young University, Provo, Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brigham Young University, Provo, Utah","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5525,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70534156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"93"},"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":0.994700014591217,"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":0.9905999898910522,"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/optical-character-recognition","display_name":"Optical character recognition","score":0.9218877553939819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580646872520447},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.623102068901062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5735962986946106},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5526847243309021},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5508527755737305},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5452377200126648},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5252270698547363},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5104209780693054},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4771549105644226},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.42930716276168823},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41115519404411316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3922545313835144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3577824831008911},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.171941339969635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12502676248550415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11992740631103516}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.9218877553939819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580646872520447},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.623102068901062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735962986946106},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5526847243309021},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5508527755737305},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5452377200126648},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5252270698547363},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5104209780693054},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4771549105644226},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.42930716276168823},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41115519404411316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3922545313835144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3577824831008911},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.171941339969635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12502676248550415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11992740631103516},{"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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2501115.2501126","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2501115.2501126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W34011602","https://openalex.org/W1603541793","https://openalex.org/W1972016971","https://openalex.org/W1975679321","https://openalex.org/W2002638840","https://openalex.org/W2012022516","https://openalex.org/W2013767392","https://openalex.org/W2024348326","https://openalex.org/W2045566081","https://openalex.org/W2063828767","https://openalex.org/W2069189382","https://openalex.org/W2095581275","https://openalex.org/W2104543051","https://openalex.org/W2114781615","https://openalex.org/W2118756867","https://openalex.org/W2124990912","https://openalex.org/W2144872023","https://openalex.org/W2158275940","https://openalex.org/W2158698381","https://openalex.org/W6635954246"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W77769009","https://openalex.org/W2363407155","https://openalex.org/W2804608824","https://openalex.org/W2104148441","https://openalex.org/W4292068860","https://openalex.org/W3140870753","https://openalex.org/W2356293009","https://openalex.org/W71071520","https://openalex.org/W2785385789"],"abstract_inverted_index":{"Our":[0,81],"previous":[1],"work":[2],"has":[3],"shown":[4],"that":[5,84,98,168],"the":[6,22,60,66,85,99,109,115,121,133,137,155,158,162,169,171,174,177,179,187],"error":[7,117],"correction":[8,70],"of":[9,24,40,76,87,102,120,145,157,173,186],"optical":[10],"character":[11],"recognition":[12],"(OCR)":[13],"on":[14],"degraded":[15],"historical":[16],"machine-printed":[17],"documents":[18],"is":[19,71],"improved":[20],"with":[21,127,161],"use":[23],"multiple":[25,29,34,49,74],"information":[26,67,105],"sources":[27,86],"and":[28,62,97],"OCR":[30,55,123,156,175],"hypotheses":[31,151],"including":[32],"from":[33],"document":[35,79,188],"image":[36,160],"binarizations.":[37],"The":[38],"contributions":[39],"this":[41,141],"paper":[42],"are":[43,90,148,181],"in":[44,140,154],"demonstrating":[45],"how":[46],"diversity":[47],"among":[48,183],"binarizations":[50,75,103,126,185],"makes":[51],"those":[52],"improvements":[53],"to":[54,64,93,107,131],"accuracy":[56],"possible.":[57],"We":[58],"demonstrate":[59],"degree":[61],"breadth":[63],"which":[65],"required":[68],"for":[69],"distributed":[72,182],"across":[73],"a":[77],"given":[78],"image.":[80,189],"analysis":[82],"reveals":[83],"these":[88],"corrections":[89,180],"not":[91,152],"limited":[92],"any":[94],"single":[95],"binarization":[96],"full":[100],"range":[101],"holds":[104],"needed":[106],"achieve":[108],"best":[110],"result":[111],"as":[112],"measured":[113],"by":[114],"word":[116],"rate":[118],"(WER)":[119],"final":[122,134],"decision.":[124],"Even":[125],"high":[128],"WERs":[129],"contribute":[130],"improving":[132],"OCR.":[135],"For":[136],"corpus":[138],"used":[139],"research,":[142],"fully":[143],"2.68%":[144],"all":[146,184],"tokens":[147],"corrected":[149],"using":[150],"found":[153],"binarized":[159],"lowest":[163],"WER.":[164],"Further,":[165],"we":[166],"show":[167],"higher":[170],"WER":[172],"overall,":[176],"more":[178]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}