{"id":"https://openalex.org/W1992271916","doi":"https://doi.org/10.1145/1815330.1815367","title":"An impact of linguistic features on automated classification of OCR texts","display_name":"An impact of linguistic features on automated classification of OCR texts","publication_year":2010,"publication_date":"2010-06-09","ids":{"openalex":"https://openalex.org/W1992271916","doi":"https://doi.org/10.1145/1815330.1815367","mag":"1992271916"},"language":"en","primary_location":{"id":"doi:10.1145/1815330.1815367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mie-u.repo.nii.ac.jp/records/8913","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067817436","display_name":"Gudila Paul Moshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gudila Paul Moshi","raw_affiliation_strings":["Mie university, Kurimamachiya, Tsu, Mie, Japan"],"affiliations":[{"raw_affiliation_string":"Mie university, Kurimamachiya, Tsu, Mie, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020598787","display_name":"Lazaro S. P. Busagala","orcid":null},"institutions":[{"id":"https://openalex.org/I84641585","display_name":"Sokoine University of Agriculture","ror":"https://ror.org/00jdryp44","country_code":"TZ","type":"education","lineage":["https://openalex.org/I84641585"]}],"countries":["TZ"],"is_corresponding":false,"raw_author_name":"Lazaro S. P. Busagala","raw_affiliation_strings":["Sokoine University of Agriculture (SUA), Morogoro, Tanzania"],"affiliations":[{"raw_affiliation_string":"Sokoine University of Agriculture (SUA), Morogoro, Tanzania","institution_ids":["https://openalex.org/I84641585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090113574","display_name":"Wataru Ohyama","orcid":"https://orcid.org/0000-0002-3661-0615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wataru Ohyama","raw_affiliation_strings":["Mie university, Kurimamachiya, Tsu, Mie, Japan"],"affiliations":[{"raw_affiliation_string":"Mie university, Kurimamachiya, Tsu, Mie, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111490360","display_name":"Tetsushi Wakabayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I178574317","display_name":"Mie University","ror":"https://ror.org/01529vy56","country_code":"JP","type":"education","lineage":["https://openalex.org/I178574317"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsushi Wakabayashi","raw_affiliation_strings":["Mie university, Kurimamachiya, Tsu"],"affiliations":[{"raw_affiliation_string":"Mie university, Kurimamachiya, Tsu","institution_ids":["https://openalex.org/I178574317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112312416","display_name":"Fumitaka Kimura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fumitaka Kimura","raw_affiliation_strings":["Mie university, Kurimamachiya, Tsu, Mie, Japan"],"affiliations":[{"raw_affiliation_string":"Mie university, Kurimamachiya, Tsu, Mie, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067817436"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.08700024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9932000041007996,"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":0.8473072052001953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8321916460990906},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6883342266082764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6805703639984131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6699034571647644},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5277816653251648},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5265446305274963},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5113293528556824},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4930214583873749},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.45789700746536255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4335739016532898},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3641340732574463},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34323984384536743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20412677526474},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16366785764694214}],"concepts":[{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8473072052001953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321916460990906},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6883342266082764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6805703639984131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6699034571647644},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5277816653251648},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5265446305274963},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5113293528556824},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4930214583873749},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.45789700746536255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4335739016532898},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3641340732574463},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34323984384536743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20412677526474},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16366785764694214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1815330.1815367","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01189:0002126035","is_oa":true,"landing_page_url":"https://mie-u.repo.nii.ac.jp/records/8913","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01189:0002126035","is_oa":true,"landing_page_url":"https://mie-u.repo.nii.ac.jp/records/8913","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1481731206","https://openalex.org/W1490760466","https://openalex.org/W1568869800","https://openalex.org/W1604513186","https://openalex.org/W1604792744","https://openalex.org/W1770825568","https://openalex.org/W1977188878","https://openalex.org/W2005422315","https://openalex.org/W2033751006","https://openalex.org/W2101154521","https://openalex.org/W2113680652","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2135346934","https://openalex.org/W2140336868","https://openalex.org/W2560674852"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":{"Optical":[0],"Character":[1],"reader":[2],"(OCR)":[3],"systems":[4],"can":[5,39],"be":[6,28,40],"used":[7,92],"in":[8,16,83,93],"digitizing":[9,20],"print":[10,21],"documents.":[11,22],"OCR":[12,55,80,94,106,128],"texts":[13,25,81,107],"are":[14],"generated":[15],"the":[17,43,88,118],"process":[18],"of":[19,45,64,73,120,127],"Usually":[23],"these":[24],"need":[26],"to":[27,32,57,78,108],"indexed":[29],"and":[30,36],"organized":[31],"simplify":[33],"their":[34],"access":[35],"retrieval.":[37],"This":[38],"done":[41],"by":[42],"use":[44],"automatic":[46],"classification":[47,125],"techniques.":[48],"However":[49],"it":[50,67],"is":[51,68,91],"currently":[52],"impossible":[53],"for":[54],"technology":[56],"recognize":[58],"all":[59],"characters":[60],"with":[61],"an":[62,110],"accuracy":[63],"100%.":[65],"Furthermore":[66],"not":[69],"known":[70],"whether":[71],"part":[72],"speech":[74],"(POS)":[75],"analysis":[76,104],"contributes":[77],"proper":[79],"representation":[82],"a":[84],"discriminative":[85],"way.":[86],"Conventionally,":[87],"bag-of-words":[89],"approach":[90],"text":[95],"classification.":[96],"In":[97],"this":[98],"paper":[99],"we":[100],"experimentally":[101],"evaluated":[102],"POS":[103,123],"on":[105],"formulate":[109],"informative":[111],"feature":[112],"set.":[113],"Empirical":[114],"results":[115],"indicate":[116],"that":[117],"combination":[119],"suitably":[121],"selected":[122],"improved":[124],"performance":[126],"texts.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}