{"id":"https://openalex.org/W2564693945","doi":"https://doi.org/10.1109/icip.2016.7532964","title":"A Tesseract-based OCR framework for historical documents lacking ground-truth text","display_name":"A Tesseract-based OCR framework for historical documents lacking ground-truth text","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2564693945","doi":"https://doi.org/10.1109/icip.2016.7532964","mag":"2564693945"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2016.7532964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Image Processing (ICIP)","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/A5081046574","display_name":"Brennan Nunamaker","orcid":null},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"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":"Brennan Nunamaker","raw_affiliation_strings":["German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","Univeristy of Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Univeristy of Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112334801","display_name":"Syed Saqib Bukhari","orcid":null},"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":"Syed Saqib Bukhari","raw_affiliation_strings":["German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"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":"Damian Borth","raw_affiliation_strings":["German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"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"]},{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","Univeristy of Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artifical Intelligence(DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Univeristy of Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081046574"],"corresponding_institution_ids":["https://openalex.org/I153267046","https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.668,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78184839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3269","last_page":"3273"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9857000112533569,"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":0.7381173372268677},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6879005432128906},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.585904061794281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703112483024597},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4925609230995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381173372268677},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6879005432128906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.585904061794281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703112483024597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4925609230995178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2016.7532964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2016.7532964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[{"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":4,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2060580591","https://openalex.org/W2147393756","https://openalex.org/W2148695089"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2144190808","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2611614995","https://openalex.org/W2115485936","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Computationally":[0],"transcribing":[1],"historical":[2],"document":[3],"images":[4,45,62,106,136,188],"to":[5,20,60,110,122,153,182,211],"digital":[6,48],"text":[7,66,80,88],"often":[8],"requires":[9],"an":[10,82],"initial,":[11],"labor":[12],"intensive":[13],"recording":[14],"of":[15,37,78,102,107,158,194,201],"ground-truths":[16],"by":[17],"language":[18],"experts":[19],"provide":[21],"the":[22,34,52,74,100,103,114,134,156],"OCR":[23],"system":[24],"with":[25,42,170],"training":[26,38,143,217,229],"text.":[27,57,235],"This":[28,119],"paper":[29],"presents":[30],"a":[31,47,86,97,108,166,174,190,218,221,226],"framework":[32],"for":[33,54,129,177,216],"automatic":[35],"generation":[36,77,131],"data,":[39],"provided":[40],"only":[41,133,169],"labeled":[43],"character":[44,104,162,179,186,191],"and":[46,63,85,113,125],"font,":[49],"thus":[50],"removing":[51],"need":[53],"manually":[55],"generated":[56,228],"In":[58],"contrast":[59],"sample":[61,105,135,160,187],"their":[64],"real":[65,234],"as":[67,209],"ground-truth,":[68],"our":[69,198],"approach":[70],"is":[71,96],"based":[72],"on":[73,155,197],"random,":[75],"rule-based":[76],"\u201cmeaningless\u201d":[79],"in":[81,180,220],"image":[83,230],"file":[84],"ground-truth":[87],"file.":[89],"Furthermore,":[90],"we":[91],"experimentally":[92],"demonstrate":[93],"that":[94,140,172],"there":[95],"correlation":[98],"between":[99],"similarity":[101],"subset":[109],"each":[111,178],"other":[112,184],"resulting":[115],"model's":[116],"classification":[117],"performance.":[118],"allows":[120],"us":[121,152],"calculate":[123],"upper-":[124],"lower-bound":[126],"performance":[127],"subsets":[128],"model":[130,149,168,219],"using":[132,141,225],"themselves.":[137],"We":[138],"show":[139],"more":[142],"samples":[144,171],"does":[145],"not":[146],"unequivocally":[147],"improve":[148],"performance,":[150],"allowing":[151],"focus":[154],"case":[157],"one":[159],"per":[161],"during":[163],"training.":[164],"Training":[165],"Tesseract":[167,223],"maximize":[173],"dissimilarity":[175],"metric":[176],"regards":[181],"all":[183],"mean":[185],"yields":[189],"recognition":[192],"error":[193,214],"ca.":[195,212],"15%":[196],"custom":[199],"benchmark":[200],"15":[202],"<sup":[203],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[204],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">th</sup>":[205],"century":[206],"Latin":[207],"documents,":[208],"compared":[210],"27%":[213],"rate":[215],"traditional":[222],"style":[224],"synthetically":[227],"from":[231],"(manually":[232],"marked)":[233]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}