{"id":"https://openalex.org/W4408403671","doi":"https://doi.org/10.1145/3677389.3702524","title":"Text Extraction for Complex Historical Documents: A Modular Approach to Layout Detection and OCR","display_name":"Text Extraction for Complex Historical Documents: A Modular Approach to Layout Detection and OCR","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4408403671","doi":"https://doi.org/10.1145/3677389.3702524"},"language":"en","primary_location":{"id":"doi:10.1145/3677389.3702524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","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/A5093734247","display_name":"David Fleischhacker","orcid":"https://orcid.org/0009-0003-4787-9091"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"David Fleischhacker","raw_affiliation_strings":["Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0009-0003-4787-9091","affiliations":[{"raw_affiliation_string":"Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068741102","display_name":"Wolfgang G\u00f6derle","orcid":"https://orcid.org/0000-0002-9417-5316"},"institutions":[{"id":"https://openalex.org/I4210161060","display_name":"Max Planck Institute for the Science of Human History","ror":"https://ror.org/05mjrzy91","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210161060"]},{"id":"https://openalex.org/I4387154167","display_name":"Max Planck Institute of Geoanthropology","ror":"https://ror.org/00js75b59","country_code":null,"type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4387154167"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Thomas G\u00f6derle","raw_affiliation_strings":["Structural Changes of the Technosphere, Max Planck Institute of Geoanthropology, Jena, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9417-5316","affiliations":[{"raw_affiliation_string":"Structural Changes of the Technosphere, Max Planck Institute of Geoanthropology, Jena, Germany","institution_ids":["https://openalex.org/I4210161060","https://openalex.org/I4387154167"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014398832","display_name":"Roman Kern","orcid":"https://orcid.org/0000-0003-0202-6100"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roman Kern","raw_affiliation_strings":["Graz University of Technology, Graz, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0202-6100","affiliations":[{"raw_affiliation_string":"Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093734247"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.4604,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66688216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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":0.9951000213623047,"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":0.7542035579681396},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.685823917388916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.569524884223938},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5574051141738892},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5364575386047363},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.47347986698150635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4516465365886688},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15238136053085327},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11257568001747131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542035579681396},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.685823917388916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.569524884223938},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5574051141738892},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5364575386047363},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.47347986698150635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4516465365886688},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15238136053085327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11257568001747131},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677389.3702524","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2922714365","https://openalex.org/W3021347667","https://openalex.org/W3023805750","https://openalex.org/W3047881567","https://openalex.org/W4234947583"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2292997772","https://openalex.org/W2088988140","https://openalex.org/W3171015545","https://openalex.org/W2103019253","https://openalex.org/W2951529875","https://openalex.org/W2391453316","https://openalex.org/W4396648495"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,27],"modular":[3,84],"approach":[4,55],"for":[5,48,59,87],"high-precision":[6],"extraction":[7],"of":[8],"data":[9,36],"from":[10],"retro-digitized":[11],"historical":[12,62,92],"texts":[13],"with":[14,26,64],"complex":[15],"layouts.":[16],"Our":[17,54],"two-stage":[18],"process":[19],"combines":[20],"AI-driven":[21],"layout":[22],"recognition":[23],"using":[24],"YOLOv9":[25],"fine-tuned":[28],"Kraken":[29],"OCR":[30],"engine.":[31],"By":[32],"leveraging":[33],"synthetic":[34],"training":[35],"and":[37,67,79],"custom":[38],"fonts,":[39],"we":[40],"achieve":[41],"low":[42],"single-digit":[43],"Character":[44],"Error":[45],"Rates":[46],"(CER)":[47],"19th-century":[49],"documents":[50],"like":[51],"the":[52],"Schematismus.":[53],"is":[56],"particularly":[57],"effective":[58],"processing":[60,80],"large-scale":[61],"collections":[63],"intricate":[65],"layouts":[66],"nested":[68],"structures,":[69],"demonstrating":[70],"significant":[71],"improvements":[72],"over":[73],"existing":[74],"solutions":[75],"in":[76],"both":[77],"accuracy":[78],"efficiency.":[81],"The":[82],"system's":[83],"design":[85],"allows":[86],"easy":[88],"adaptation":[89],"to":[90],"different":[91],"document":[93],"types":[94],"while":[95],"maintaining":[96],"high":[97],"performance":[98],"levels.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}