{"id":"https://openalex.org/W2124430240","doi":"https://doi.org/10.1109/cvpr.2012.6248072","title":"Autonomous cleaning of corrupted scanned documents — A generative modeling approach","display_name":"Autonomous cleaning of corrupted scanned documents — A generative modeling approach","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2124430240","doi":"https://doi.org/10.1109/cvpr.2012.6248072","mag":"2124430240"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6248072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6248072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","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/A5023956515","display_name":"Zhenwen Dai","orcid":"https://orcid.org/0000-0002-9040-2315"},"institutions":[{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]},{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Zhenwen Dai","raw_affiliation_strings":["Frankfurt Institute for Advanced Studies, Department of Physics, Goethe-University Frankfurt am Main, Germany","Frankfurt Institute for Advanced Studies, Dept. of Physics, Goethe-University Frankfurt#TAB#"],"affiliations":[{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Department of Physics, Goethe-University Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I2801628138","https://openalex.org/I114090438"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Dept. of Physics, Goethe-University Frankfurt#TAB#","institution_ids":["https://openalex.org/I2801628138","https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022342273","display_name":"J\u00f6rg L\u00fccke","orcid":"https://orcid.org/0000-0001-9921-2529"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]},{"id":"https://openalex.org/I2801628138","display_name":"Frankfurt Institute for Advanced Studies","ror":"https://ror.org/05vmv8m79","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2801628138"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J. Lucke","raw_affiliation_strings":["Frankfurt Institute for Advanced Studies, Department of Physics, Goethe-University Frankfurt am Main, Germany","Frankfurt Institute for Advanced Studies, Dept. of Physics, Goethe-University Frankfurt#TAB#"],"affiliations":[{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Department of Physics, Goethe-University Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I2801628138","https://openalex.org/I114090438"]},{"raw_affiliation_string":"Frankfurt Institute for Advanced Studies, Dept. of Physics, Goethe-University Frankfurt#TAB#","institution_ids":["https://openalex.org/I2801628138","https://openalex.org/I114090438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023956515"],"corresponding_institution_ids":["https://openalex.org/I114090438","https://openalex.org/I2801628138"],"apc_list":null,"apc_paid":null,"fwci":1.3727,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8379578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3338","last_page":"3345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9962000250816345,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/dirt","display_name":"Dirt","score":0.7749010920524597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190663814544678},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6973757147789001},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6868065595626831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6735725402832031},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6131415367126465},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5659283399581909},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5557224750518799},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5363283157348633},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.43947625160217285},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43676280975341797},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4183058738708496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19145208597183228}],"concepts":[{"id":"https://openalex.org/C2778582501","wikidata":"https://www.wikidata.org/wiki/Q555882","display_name":"Dirt","level":2,"score":0.7749010920524597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190663814544678},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6973757147789001},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6868065595626831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6735725402832031},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6131415367126465},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5659283399581909},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5557224750518799},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5363283157348633},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.43947625160217285},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43676280975341797},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4183058738708496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19145208597183228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2012.6248072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6248072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1535389666","https://openalex.org/W1979743748","https://openalex.org/W1989975849","https://openalex.org/W2015861736","https://openalex.org/W2029189646","https://openalex.org/W2075674485","https://openalex.org/W2098207052","https://openalex.org/W2113606819","https://openalex.org/W2115441154","https://openalex.org/W2120954940","https://openalex.org/W2123782934","https://openalex.org/W2128209899","https://openalex.org/W2134963415","https://openalex.org/W2137680370","https://openalex.org/W2142968460","https://openalex.org/W2145889472","https://openalex.org/W2148217757","https://openalex.org/W2151103935","https://openalex.org/W2153443573","https://openalex.org/W2161969291","https://openalex.org/W2180187800","https://openalex.org/W2574026370","https://openalex.org/W3004698592","https://openalex.org/W6681895046"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"We":[0,23],"study":[1],"the":[2,37,39,78,89,97,118,138,152,157,168,216,220,236],"task":[3],"of":[4,88,101,122,204,219,235],"cleaning":[5],"scanned":[6],"text":[7],"documents":[8],"that":[9,177,197],"are":[10,108],"strongly":[11],"corrupted":[12,192],"by":[13,193],"dirt":[14,28],"such":[15],"as":[16],"manual":[17],"line":[18],"strokes,":[19],"spilled":[20],"ink":[21],"etc.":[22],"aim":[24],"at":[25],"autonomously":[26,210],"removing":[27],"from":[29,60,229],"a":[30,54,69,111,171,178,198,201],"single":[31,179],"letter-size":[32],"page":[33,40,180,199],"based":[34,136,214],"only":[35],"on":[36,137,215],"information":[38],"contains.":[41,223],"Our":[42],"approach,":[43],"therefore,":[44],"has":[45],"to":[46,56,166],"learn":[47,64],"character":[48,65,149,186,205],"representations":[49,59],"without":[50],"supervision":[51],"and":[52,82,96,129,151,209,238],"requires":[53],"mechanism":[55],"distinguish":[57],"learned":[58,139],"irregular":[61,153,160],"patterns.":[62],"To":[63],"representations,":[66],"we":[67,175,195,232],"use":[68],"probabilistic":[70],"generative":[71],"model":[72,90,106],"parameterizing":[73],"pattern":[74,83,92,94,103],"features,":[75],"feature":[76,127],"variances,":[77],"features'":[79],"planar":[80,126],"arrangements,":[81],"frequencies.":[84],"The":[85,105,159],"latent":[86],"variables":[87],"describe":[91],"class,":[93],"position,":[95,125],"presence":[98],"or":[99],"absence":[100],"individual":[102],"features.":[104],"parameters":[107,119],"optimized":[109],"using":[110,227],"novel":[112],"variational":[113],"EM":[114],"approximation.":[115],"After":[116],"learning,":[117],"represent,":[120],"independently":[121],"their":[123,130],"absolute":[124],"arrangements":[128],"variances.":[131],"A":[132],"quality":[133],"measure":[134],"defined":[135],"representation":[140],"then":[141],"allows":[142],"for":[143,242],"an":[144],"autonomous":[145],"discrimination":[146],"between":[147],"regular":[148],"patterns":[150,154,161],"making":[155],"up":[156],"dirt.":[158],"can":[162,207],"thus":[163],"be":[164,211],"removed":[165],"clean":[167],"document.":[169],"For":[170],"full":[172],"Latin":[173],"alphabet":[174],"found":[176],"does":[181],"not":[182],"contain":[183],"sufficiently":[184],"many":[185],"examples.":[187],"However,":[188],"even":[189],"if":[190],"heavily":[191],"dirt,":[194],"show":[196],"containing":[200],"lower":[202],"number":[203],"types":[206],"efficiently":[208],"cleaned":[212],"solely":[213],"structural":[217],"regularity":[218],"characters":[221,228],"it":[222],"In":[224],"different":[225,230],"examples":[226],"alphabets,":[231],"demonstrate":[233],"generality":[234],"approach":[237],"discuss":[239],"its":[240],"implications":[241],"future":[243],"developments.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}