{"id":"https://openalex.org/W2584605571","doi":"https://doi.org/10.1145/3078081.3078098","title":"Case Study of a highly automated Layout Analysis and OCR of an incunabulum","display_name":"Case Study of a highly automated Layout Analysis and OCR of an incunabulum","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2584605571","doi":"https://doi.org/10.1145/3078081.3078098","mag":"2584605571"},"language":"en","primary_location":{"id":"doi:10.1145/3078081.3078098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","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/A5063938010","display_name":"Christian Reul","orcid":"https://orcid.org/0000-0002-1776-1469"},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian Reul","raw_affiliation_strings":["University of W\u00fcrzburg, Am Hubland, W\u00fcrzburg"],"affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, Am Hubland, W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010778935","display_name":"Marco Dittrich","orcid":null},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Dittrich","raw_affiliation_strings":["University Library of W\u00fcrzburg, Am Hubland, W\u00fcrzburg"],"affiliations":[{"raw_affiliation_string":"University Library of W\u00fcrzburg, Am Hubland, W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068751356","display_name":"Martin Gruner","orcid":null},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Gruner","raw_affiliation_strings":["University Library of W\u00fcrzburg, Am Hubland, W\u00fcrzburg"],"affiliations":[{"raw_affiliation_string":"University Library of W\u00fcrzburg, Am Hubland, W\u00fcrzburg","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063938010"],"corresponding_institution_ids":["https://openalex.org/I25974101"],"apc_list":null,"apc_paid":null,"fwci":0.7399,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79986667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9836000204086304,"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/digitization","display_name":"Digitization","score":0.770601749420166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7357061505317688},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7063182592391968},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7009617686271667},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6412031650543213},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6189441680908203},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48737436532974243},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42878457903862},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.4065892994403839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40487760305404663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3917270004749298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3606069087982178},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3469824194908142},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24442216753959656},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2061081826686859},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15295907855033875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1394234597682953},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12707063555717468}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.770601749420166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357061505317688},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7063182592391968},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7009617686271667},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6412031650543213},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6189441680908203},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48737436532974243},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42878457903862},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.4065892994403839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40487760305404663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3917270004749298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3606069087982178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3469824194908142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24442216753959656},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2061081826686859},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15295907855033875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1394234597682953},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12707063555717468},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3078081.3078098","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1989737761","https://openalex.org/W2041904910","https://openalex.org/W2042106258","https://openalex.org/W2060580591","https://openalex.org/W2147105110","https://openalex.org/W2340674967","https://openalex.org/W2402677432","https://openalex.org/W2519856923","https://openalex.org/W2534524893","https://openalex.org/W2581377258","https://openalex.org/W2777421064","https://openalex.org/W2963414181"],"related_works":["https://openalex.org/W1539704186","https://openalex.org/W4254109238","https://openalex.org/W2399890175","https://openalex.org/W3204576215","https://openalex.org/W4295934125","https://openalex.org/W3160316822","https://openalex.org/W1581784047","https://openalex.org/W4283017656","https://openalex.org/W2774927939","https://openalex.org/W4381663721"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"the":[3,20,41,55,95,97,121,141,146],"first":[4],"thorough":[5],"documentation":[6],"of":[7,43,77,140],"a":[8,75,78,83],"high":[9],"quality":[10],"digitization":[11],"process":[12],"applied":[13],"to":[14,107,153],"an":[15],"early":[16],"printed":[17,47,138],"book":[18],"from":[19,104,129,134],"incunabulum":[21],"period":[22],"(1450-1500).":[23],"The":[24,61,137],"entire":[25],"OCR":[26,116,147],"related":[27],"workflow":[28],"including":[29],"preprocessing,":[30],"layout":[31,88],"analysis":[32,89],"and":[33,70,82,156],"text":[34,127],"recognition":[35,62],"is":[36],"illustrated":[37],"in":[38,48,50,115],"detail":[39],"using":[40],"example":[42],"'Der":[44],"Heiligen":[45],"Leben',":[46],"Nuremberg":[49],"1488.":[51],"For":[52],"each":[53],"step":[54],"required":[56,98],"time":[57],"expenditure":[58],"was":[59,64,90,101],"recorded.":[60],"rate":[63],"excellent":[65],"both":[66],"on":[67],"character":[68],"(97.97%)":[69],"word":[71],"(91.58%)":[72],"level.":[73],"Furthermore,":[74],"comparison":[76],"highly":[79],"automated":[80],"(LAREX)":[81],"manual":[84],"(Aletheia)":[85],"method":[86],"for":[87,120,125],"performed.":[91],"By":[92],"substantially":[93],"automating":[94],"segmentation":[96],"human":[99,122],"effort":[100,123],"reduced":[102],"considerably":[103],"39":[105],"hours":[106],"around":[108],"eight":[109],"hours,":[110],"without":[111],"any":[112],"significant":[113],"drop":[114],"accuracy.":[117],"Realistic":[118],"estimates":[119],"necessary":[124],"full":[126],"extraction":[128],"incunabula":[130],"can":[131],"be":[132,154],"derived":[133],"this":[135],"study.":[136],"pages":[139],"complete":[142],"work":[143],"together":[144],"with":[145],"result":[148],"are":[149],"available":[150],"online1":[151],"ready":[152],"inspected":[155],"downloaded.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}