{"id":"https://openalex.org/W2137982097","doi":"https://doi.org/10.1093/llc/fqs077","title":"Interactive layout analysis, content extraction, and transcription of historical printed books using Pattern Redundancy Analysis","display_name":"Interactive layout analysis, content extraction, and transcription of historical printed books using Pattern Redundancy Analysis","publication_year":2013,"publication_date":"2013-01-28","ids":{"openalex":"https://openalex.org/W2137982097","doi":"https://doi.org/10.1093/llc/fqs077","mag":"2137982097"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fqs077","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqs077","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-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/A5082792285","display_name":"Jean-Yves Ramel","orcid":"https://orcid.org/0000-0003-4427-4612"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-Y. Ramel","raw_affiliation_strings":["Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France","institution_ids":["https://openalex.org/I110017253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050406382","display_name":"Nicolas Sid\u00e8re","orcid":"https://orcid.org/0000-0001-6719-5007"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"N. Sidere","raw_affiliation_strings":["Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France","institution_ids":["https://openalex.org/I110017253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027849169","display_name":"Fr\u00e9d\u00e9ric Rayar","orcid":"https://orcid.org/0000-0003-1927-8400"},"institutions":[{"id":"https://openalex.org/I110017253","display_name":"Universit\u00e9 de Tours","ror":"https://ror.org/02wwzvj46","country_code":"FR","type":"education","lineage":["https://openalex.org/I110017253"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Rayar","raw_affiliation_strings":["Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Tours (EA 6300) Ecole d'ing\u00e9nieurs Polytechnique de l'Universit\u00e9 de Tours, France","institution_ids":["https://openalex.org/I110017253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I110017253"],"apc_list":null,"apc_paid":null,"fwci":1.0879,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81769896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"28","issue":"2","first_page":"301","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.992900013923645,"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":0.9812999963760376,"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":0.7699393033981323},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.7140200734138489},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.698885440826416},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.658807098865509},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6389734745025635},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5905112624168396},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5407500267028809},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4754566550254822},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4470069408416748},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.44547346234321594},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42662274837493896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38508400321006775},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3723616600036621},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313867747783661},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3174196481704712},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.122216135263443},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09209141135215759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699393033981323},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.7140200734138489},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.698885440826416},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.658807098865509},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6389734745025635},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5905112624168396},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5407500267028809},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4754566550254822},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4470069408416748},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.44547346234321594},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42662274837493896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38508400321006775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723616600036621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313867747783661},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3174196481704712},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.122216135263443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09209141135215759},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/llc/fqs077","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fqs077","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1967238710","https://openalex.org/W1979243088","https://openalex.org/W1999378673","https://openalex.org/W2044907962","https://openalex.org/W2079352267","https://openalex.org/W2125962095","https://openalex.org/W2128060444","https://openalex.org/W2130283001","https://openalex.org/W2163113711"],"related_works":["https://openalex.org/W2402920184","https://openalex.org/W2582695981","https://openalex.org/W2612325988","https://openalex.org/W2483185727","https://openalex.org/W3128815814","https://openalex.org/W2487016776","https://openalex.org/W2592284086","https://openalex.org/W2312737637","https://openalex.org/W2322748372","https://openalex.org/W4246957482"],"abstract_inverted_index":{"This":[0,125],"article":[1],"describes":[2],"the":[3,7,48,59,68,132,140,156,171,175,182,198,202,214,261,271,291,295,300,309,312,322,326],"work":[4,45],"performed":[5],"in":[6,55,106,220],"Pattern":[8],"Redundancy":[9],"Analysis":[10],"for":[11,290,329],"Document":[12],"Image":[13],"Indexing":[14],"and":[15,31,38,50,62,67,91,119,234,302,315,336],"Transcription":[16],"research":[17],"project.":[18],"The":[19,41,82,281],"project":[20],"focused":[21],"on":[22,47,276],"layout":[23,87],"analysis,":[24,88],"text/graphics":[25,89],"separation,":[26,90],"optical":[27,265],"character":[28,168,190],"recognition":[29,267,272],"(OCR),":[30],"text":[32,172],"transcription":[33,64,173,206],"processes":[34],"dedicated":[35],"to":[36,57,101,121,136,152,165,169,200,210,227,232,269,311,343],"old":[37,221],"precious":[39],"books.":[40,222,280],"originality":[42],"of":[43,52,65,70,113,131,134,142,174,181,192,264,274,283,293,304,318,325],"this":[44,205],"relies":[46],"analysis":[49],"exploitation":[51],"pattern":[53,92],"redundancy":[54,123],"documents":[56],"enable":[58],"efficient":[60],"indexing":[61],"quick":[63],"books":[66,246],"identification":[69,282],"typographic":[71,284],"materials.":[72],"For":[73],"these":[74],"purposes,":[75],"we":[76],"have":[77],"developed":[78],"two":[79],"software":[80],"packages.":[81],"first,":[83],"AGORA,":[84],"performs":[85],"page":[86],"(letterform)":[93],"extraction":[94],"simultaneously.":[95],"These":[96,253],"patterns":[97,104],"are":[98,161,184],"then":[99,162],"processed":[100],"group":[102],"similar":[103],"together":[105],"single":[107],"clusters":[108],"so":[109],"that":[110,217],"different":[111],"letterforms":[112,135,143,183],"a":[114,128,146,150],"book":[115],"can":[116],"be":[117,137,195,258,288],"extracted":[118],"analysed":[120],"compute":[122],"rates.":[124],"process":[126],"allows":[127,208],"significant":[129],"reduction":[130],"number":[133],"recognized.":[138],"Once":[139],"clustering":[141,230],"is":[144,224],"done,":[145],"user":[147,199],"may":[148],"assign":[149],"label":[151],"each":[153,166],"cluster":[154],"using":[155],"second":[157,323],"software,":[158],"RETRO.":[159],"Labels":[160],"automatically":[163],"assigned":[164],"corresponding":[167],"perform":[170],"whole":[176],"book.":[177,203],"Thus,":[178],"if":[179],"90%":[180],"detected":[185],"as":[186,298],"redundant,":[187],"only":[188],"one":[189],"out":[191],"ten":[193],"must":[194],"labelled":[196],"by":[197],"transcribe":[201],"Moreover,":[204],"method":[207],"us":[209],"deal":[211],"easily":[212],"with":[213,248],"special":[215],"characters":[216],"appear":[218],"frequently":[219,338],"It":[223],"also":[225,287],"possible":[226],"use":[228],"our":[229],"approach":[231],"extract":[233],"create":[235],"new":[236,254],"font":[237,255],"packages":[238,256],"from":[239,244,308],"specific":[240,279],"printing":[241,305,319,331],"material":[242],"(e.g.":[243],"rare":[245,277],"printed":[247],"particular":[249],"types":[250,306,332,342],"or":[251,278,340],"woodblocks).":[252],"could":[257,286],"incorporated":[259],"into":[260],"training":[262],"step":[263],"fonts":[266],"methods":[268],"improve":[270],"results":[273],"OCRs":[275],"materials":[285],"useful":[289],"study":[292],"both":[294],"aesthetic":[296],"(such":[297],"how":[299],"thickness":[301],"shape":[303],"evolved":[307],"15th":[310],"mid-16th":[313],"century)":[314],"economic":[316],"aspects":[317],"historically.":[320],"Until":[321],"half":[324],"16th":[327],"century,":[328],"instance,":[330],"circulated":[333],"among":[334],"workshops,":[335],"printers":[337],"sold":[339],"lent":[341],"their":[344],"fellows.":[345]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}