{"id":"https://openalex.org/W2043611036","doi":"https://doi.org/10.1145/1166160.1166193","title":"Quality enhancement in information extraction from scanned documents","display_name":"Quality enhancement in information extraction from scanned documents","publication_year":2006,"publication_date":"2006-10-10","ids":{"openalex":"https://openalex.org/W2043611036","doi":"https://doi.org/10.1145/1166160.1166193","mag":"2043611036"},"language":"en","primary_location":{"id":"doi:10.1145/1166160.1166193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","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/A5087434029","display_name":"Atsuhiro Takasu","orcid":"https://orcid.org/0000-0002-9061-7949"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Atsuhiro Takasu","raw_affiliation_strings":["National Institute of Informatics","National Institute of Informatics,"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics,","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030583821","display_name":"Kenro Aihara","orcid":"https://orcid.org/0000-0002-4287-2523"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenro Aihara","raw_affiliation_strings":["National Institute of Informatics","National Institute of Informatics,"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics,","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087434029"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":1.51238901,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82599544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9966999888420105,"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":0.8454042673110962},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8354635238647461},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5433964133262634},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.5343097448348999},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5206845998764038},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5206443667411804},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5009598731994629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4685695171356201},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4572888910770416},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45087337493896484},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3912142515182495},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3842190206050873},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3464123606681824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3410089910030365},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.1633453071117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8454042673110962},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8354635238647461},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5433964133262634},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.5343097448348999},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5206845998764038},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5206443667411804},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5009598731994629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4685695171356201},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4572888910770416},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45087337493896484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3912142515182495},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3842190206050873},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3464123606681824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3410089910030365},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.1633453071117401},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1166160.1166193","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","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":5,"referenced_works":["https://openalex.org/W1487429615","https://openalex.org/W1901493722","https://openalex.org/W2068613363","https://openalex.org/W2102443632","https://openalex.org/W2145130412"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664","https://openalex.org/W2942471066"],"abstract_inverted_index":{"When":[0],"constructing":[1,36],"a":[2,53,85],"large":[3],"document":[4,19,38],"archive,":[5],"an":[6],"important":[7],"element":[8],"is":[9,33],"the":[10,44,47,67,81,101],"digitizing":[11],"of":[12,88],"printed":[13],"documents.":[14],"Although":[15],"various":[16,74],"techniques":[17],"for":[18,58],"image":[20],"analysis":[21],"such":[22],"as":[23],"Optical":[24],"Character":[25],"Recognition":[26],"(OCR)":[27],"have":[28],"been":[29],"developed,":[30],"error":[31],"handling":[32],"required":[34],"in":[35,73],"real":[37],"archive":[39],"systems.":[40],"This":[41,92],"paper":[42,93],"discusses":[43,95],"problem":[45],"from":[46],"quality":[48],"enhancement":[49],"perspective":[50],"and":[51,76,98,106],"proposes":[52],"robust":[54],"reference":[55],"extraction":[56,104],"method":[57,69,83],"academic":[59],"articles":[60,71],"scanned":[61],"with":[62],"OCR":[63],"mark-up.":[64],"We":[65],"applied":[66],"proposed":[68,82],"to":[70],"appearing":[72],"journals,":[75],"these":[77],"experiments":[78],"showed":[79],"that":[80],"achieved":[84],"recognition":[86],"accuracy":[87,105],"more":[89],"than":[90],"94%.":[91],"also":[94],"manual":[96],"correction":[97],"investigates":[99],"experimentally":[100],"relationship":[102],"between":[103],"cost":[107],"reduction.":[108]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}