{"id":"https://openalex.org/W2799519010","doi":"https://doi.org/10.1117/12.2309615","title":"Training a whole-book LSTM-based recognizer with an optimal training set","display_name":"Training a whole-book LSTM-based recognizer with an optimal training set","publication_year":2018,"publication_date":"2018-04-13","ids":{"openalex":"https://openalex.org/W2799519010","doi":"https://doi.org/10.1117/12.2309615","mag":"2799519010"},"language":"en","primary_location":{"id":"doi:10.1117/12.2309615","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2309615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tenth International Conference on Machine Vision (ICMV 2017)","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/A5030589560","display_name":"Mohammad Reza Yousefi","orcid":"https://orcid.org/0000-0002-5126-8459"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mohammad Reza Yousefi","raw_affiliation_strings":["German Research Ctr. for Artificial Intelligence (Germany)"],"affiliations":[{"raw_affiliation_string":"German Research Ctr. for Artificial Intelligence (Germany)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001157606","display_name":"Ehsanollah Kabir","orcid":"https://orcid.org/0000-0002-5610-7611"},"institutions":[{"id":"https://openalex.org/I1516879","display_name":"Tarbiat Modares University","ror":"https://ror.org/03mwgfy56","country_code":"IR","type":"education","lineage":["https://openalex.org/I1516879"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ehsanollah Kabir","raw_affiliation_strings":["Tarbiat Modares Univ. (Iran, Islamic Republic of)"],"affiliations":[{"raw_affiliation_string":"Tarbiat Modares Univ. (Iran, Islamic Republic of)","institution_ids":["https://openalex.org/I1516879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005045822","display_name":"Mohammad Reza Soheili","orcid":"https://orcid.org/0000-0002-5974-3939"},"institutions":[{"id":"https://openalex.org/I181744264","display_name":"Kharazmi University","ror":"https://ror.org/05hsgex59","country_code":"IR","type":"education","lineage":["https://openalex.org/I181744264"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Reza Soheili","raw_affiliation_strings":["Kharazmi Univ. (Iran, Islamic Republic of)"],"affiliations":[{"raw_affiliation_string":"Kharazmi Univ. (Iran, Islamic Republic of)","institution_ids":["https://openalex.org/I181744264"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051650277","display_name":"Didier Stricker","orcid":"https://orcid.org/0009-0004-8794-6858"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Didier Stricker","raw_affiliation_strings":["German Research Ctr. for Artificial Intelligence (Germany)"],"affiliations":[{"raw_affiliation_string":"German Research Ctr. for Artificial Intelligence (Germany)","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030589560"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03064616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9402","issue":null,"first_page":"38","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9977999925613403,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9916999936103821,"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":0.8240936994552612},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6370877027511597},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6071293950080872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6006004214286804},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5912699699401855},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5890285968780518},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5057060718536377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48171812295913696},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4683603048324585},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.46226823329925537},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4554036557674408},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42623648047447205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3803212642669678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240936994552612},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6370877027511597},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6071293950080872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6006004214286804},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5912699699401855},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5890285968780518},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5057060718536377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48171812295913696},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4683603048324585},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.46226823329925537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4554036557674408},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42623648047447205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3803212642669678},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2309615","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2309615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tenth International Conference on Machine Vision (ICMV 2017)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1543458979","https://openalex.org/W1607307044","https://openalex.org/W1992477548","https://openalex.org/W2009444210","https://openalex.org/W2033154814","https://openalex.org/W2033260799","https://openalex.org/W2060580591","https://openalex.org/W2064675550","https://openalex.org/W2069360215","https://openalex.org/W2082552300","https://openalex.org/W2100906909","https://openalex.org/W2112796928","https://openalex.org/W2116604999","https://openalex.org/W2122585011","https://openalex.org/W2131244930","https://openalex.org/W2139191516","https://openalex.org/W2141960239","https://openalex.org/W2144499799","https://openalex.org/W2144839447","https://openalex.org/W2148695089","https://openalex.org/W2150355110","https://openalex.org/W2156532982","https://openalex.org/W6632483798","https://openalex.org/W6636382570","https://openalex.org/W6648427635","https://openalex.org/W6652514731","https://openalex.org/W6658693963","https://openalex.org/W6658748603","https://openalex.org/W6665521764","https://openalex.org/W6671236943","https://openalex.org/W6676622225","https://openalex.org/W6677280470","https://openalex.org/W6678131404","https://openalex.org/W6679459217","https://openalex.org/W6681266639","https://openalex.org/W6681335746","https://openalex.org/W6681794868","https://openalex.org/W6681983603","https://openalex.org/W6682050888","https://openalex.org/W6683152609"],"related_works":["https://openalex.org/W2944691285","https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2146197305","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2166312020","https://openalex.org/W2033669961"],"abstract_inverted_index":{"Despite":[0],"the":[1,24,37,55,118,128,131,135,140,144,164,174,218],"recent":[2],"progress":[3],"in":[4,14,16,95,130],"OCR":[5],"technologies,":[6],"whole-book":[7,96],"recognition,":[8],"is":[9,157,207],"still":[10],"a":[11,66,77,112,187,191,197,210],"challenging":[12],"task,":[13],"particular":[15],"case":[17],"of":[18,31,65,80,91,163,184,212,217],"old":[19],"and":[20,33,42,53,133],"historical":[21],"books,":[22],"that":[23,125,151,156,172,206],"unknown":[25],"font":[26],"faces":[27],"or":[28],"low":[29,70],"quality":[30],"paper":[32],"print":[34],"contributes":[35],"to":[36,50,75,103,120,180,202],"challenge.":[38],"Therefore,":[39],"pre-trained":[40],"recognizers":[41],"generic":[43],"methods":[44,72],"do":[45,86],"not":[46,87],"usually":[47,54],"perform":[48],"up":[49],"required":[51],"standards,":[52],"performance":[56],"degrades":[57],"for":[58,143,186],"larger":[59],"scale":[60],"recognition":[61],"tasks,":[62],"such":[63,84,93,196],"as":[64,139],"book.":[67,165,219],"Such":[68],"reportedly":[69],"error-rate":[71],"turn":[73],"out":[74],"require":[76],"great":[78],"deal":[79],"manual":[81],"correction.":[82],"Generally,":[83],"methodologies":[85],"make":[88],"effective":[89],"use":[90],"concepts":[92],"redundancy":[94],"recognition.":[97],"In":[98,166],"this":[99],"work,":[100],"we":[101,147,169],"propose":[102],"train":[104,149],"Long":[105],"Short":[106],"Term":[107],"Memory":[108],"(LSTM)":[109],"networks":[110],"on":[111,195,209],"minimal":[113],"training":[114,141],"set":[115,142,198,211],"obtained":[116],"from":[117],"book":[119],"be":[121],"recognized.":[122],"We":[123],"show":[124,171],"clustering":[126],"all":[127],"sub-words":[129],"book,":[132,190],"using":[134],"sub-word":[136,175],"cluster":[137,176],"centers":[138,177],"LSTM":[145,192],"network,":[146],"can":[148],"models":[150],"outperform":[152],"any":[153],"identical":[154,204],"network":[155,193,205],"trained":[158,194,208],"with":[159],"randomly":[160,214],"selected":[161,215],"pages":[162,183,216],"our":[167],"experiments,":[168],"also":[170],"although":[173],"are":[178],"equivalent":[179],"about":[181],"8":[182],"text":[185],"101-":[188],"page":[189],"performs":[199],"competitively":[200],"compared":[201],"an":[203],"60":[213]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}