{"id":"https://openalex.org/W2039013656","doi":"https://doi.org/10.1117/12.410861","title":"Evaluating text categorization in the presence of OCR errors","display_name":"Evaluating text categorization in the presence of OCR errors","publication_year":2000,"publication_date":"2000-12-21","ids":{"openalex":"https://openalex.org/W2039013656","doi":"https://doi.org/10.1117/12.410861","mag":"2039013656"},"language":"en","primary_location":{"id":"doi:10.1117/12.410861","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.410861","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":"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/A5024937756","display_name":"Kazem Taghva","orcid":"https://orcid.org/0000-0001-8320-0080"},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazem Taghva","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109089515","display_name":"Thomas A. Nartker","orcid":null},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas A. Nartker","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042105622","display_name":"Julie Borsack","orcid":null},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Borsack","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089770494","display_name":"Steven Lumos","orcid":null},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Lumos","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006493083","display_name":"Allen Condit","orcid":null},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Condit","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011285210","display_name":"Ron Young","orcid":null},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Young","raw_affiliation_strings":["Univ. of Nevada/Las Vegas (United States)","University of Nevada Las Vegas United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Nevada/Las Vegas (United States)","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"University of Nevada Las Vegas United States","institution_ids":["https://openalex.org/I133999245"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133999245"],"apc_list":null,"apc_paid":null,"fwci":0.5579,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.6328685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4307","issue":null,"first_page":"68","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/categorization","display_name":"Categorization","score":0.8687995076179504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6911183595657349},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.688197135925293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6331983208656311},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5508806109428406},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5156773328781128},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4986746311187744},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4843848645687103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4747507870197296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4462621212005615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4117122292518616},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1307375431060791}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8687995076179504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6911183595657349},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.688197135925293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331983208656311},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5508806109428406},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5156773328781128},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4986746311187744},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4843848645687103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4747507870197296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4462621212005615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4117122292518616},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1307375431060791}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.410861","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.410861","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1550206324","https://openalex.org/W1924689489","https://openalex.org/W1976978162","https://openalex.org/W2009190245","https://openalex.org/W2082729696","https://openalex.org/W2085763602","https://openalex.org/W2099111195","https://openalex.org/W2126502509","https://openalex.org/W2127994451","https://openalex.org/W2149684865"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W2390698788","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125"],"abstract_inverted_index":{"In":[0,16],"this":[1],"paper":[2],"we":[3,18,32],"describe":[4],"experiments":[5],"that":[6,20,45],"investigate":[7],"the":[8,38],"effects":[9],"of":[10,53],"OCR":[11,24,54],"errors":[12,25,55],"on":[13,29,37],"text":[14],"categorization.":[15],"particular,":[17],"show":[19],"in":[21],"our":[22],"environment,":[23],"have":[26],"no":[27],"effect":[28],"categorization":[30,58],"when":[31],"use":[33],"a":[34,50],"classifier":[35],"based":[36],"naive":[39],"Bayes":[40],"model.":[41],"We":[42],"also":[43],"observe":[44],"dimensionality":[46],"reduction":[47],"techniques":[48],"eliminate":[49],"large":[51],"number":[52],"and":[56],"improve":[57],"results.":[59]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
