{"id":"https://openalex.org/W4385470515","doi":"https://doi.org/10.1145/3604951.3605513","title":"Document Layout Analysis with Deep Learning and Heuristics","display_name":"Document Layout Analysis with Deep Learning and Heuristics","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385470515","doi":"https://doi.org/10.1145/3604951.3605513"},"language":"en","primary_location":{"id":"doi:10.1145/3604951.3605513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","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/A5037059057","display_name":"Vahid Rezanezhad","orcid":"https://orcid.org/0009-0007-8041-6506"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Vahid Rezanezhad","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0009-0007-8041-6506","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061484718","display_name":"Konstantin Baierer","orcid":"https://orcid.org/0000-0003-2397-242X"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Konstantin Baierer","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2397-242X","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089350313","display_name":"Mike Gerber","orcid":"https://orcid.org/0000-0003-2167-4322"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mike Gerber","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2167-4322","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050564431","display_name":"Kai Labusch","orcid":"https://orcid.org/0000-0002-7275-5483"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kai Labusch","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7275-5483","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060385793","display_name":"Clemens Neudecker","orcid":"https://orcid.org/0000-0001-5293-8322"},"institutions":[{"id":"https://openalex.org/I2802918869","display_name":"Berlin State Library","ror":"https://ror.org/02ysgg478","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2800703586","https://openalex.org/I2802918869"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Clemens Neudecker","raw_affiliation_strings":["Berlin State Library, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5293-8322","affiliations":[{"raw_affiliation_string":"Berlin State Library, Germany","institution_ids":["https://openalex.org/I2802918869"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037059057"],"corresponding_institution_ids":["https://openalex.org/I2802918869"],"apc_list":null,"apc_paid":null,"fwci":0.471,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6422829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9979000091552734,"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":0.9977999925613403,"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/document-layout-analysis","display_name":"Document layout analysis","score":0.838453471660614},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234508633613586},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7618227005004883},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.659581184387207},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6400206089019775},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.589094340801239},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.5754358768463135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5734134316444397},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4945013225078583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46410879492759705},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43924859166145325},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.436906635761261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43606898188591003},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4030272960662842},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1881827712059021}],"concepts":[{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.838453471660614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234508633613586},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7618227005004883},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.659581184387207},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6400206089019775},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.589094340801239},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.5754358768463135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5734134316444397},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4945013225078583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46410879492759705},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43924859166145325},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.436906635761261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43606898188591003},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4030272960662842},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1881827712059021},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3604951.3605513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604951.3605513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Workshop on Historical Document Imaging and Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8899999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1597517899","https://openalex.org/W1903029394","https://openalex.org/W2013848960","https://openalex.org/W2053050503","https://openalex.org/W2106311500","https://openalex.org/W2108598243","https://openalex.org/W2149128132","https://openalex.org/W2151765755","https://openalex.org/W2734349601","https://openalex.org/W2768926640","https://openalex.org/W2786956341","https://openalex.org/W2798826627","https://openalex.org/W2962747717","https://openalex.org/W2981353851","https://openalex.org/W2981597140","https://openalex.org/W2997154779","https://openalex.org/W3104637907","https://openalex.org/W3104953317","https://openalex.org/W3108646486","https://openalex.org/W3158084495","https://openalex.org/W3198266319","https://openalex.org/W4287278744","https://openalex.org/W4287324217"],"related_works":["https://openalex.org/W2573990671","https://openalex.org/W2131730163","https://openalex.org/W2051072213","https://openalex.org/W3046471831","https://openalex.org/W2784287639","https://openalex.org/W4294702218","https://openalex.org/W2119179626","https://openalex.org/W2007589418","https://openalex.org/W2189110401","https://openalex.org/W2276772277"],"abstract_inverted_index":{"The":[0],"automated":[1],"yet":[2],"highly":[3],"accurate":[4],"layout":[5,36,58,96],"analysis":[6,59],"(segmentation)":[7],"of":[8,19,32,88,132],"historical":[9,26,63,134],"document":[10,57,135],"images":[11],"remains":[12],"a":[13,29,56],"key":[14],"challenge":[15],"for":[16,62],"the":[17,85,110,112,127,130],"improvement":[18],"Optical":[20],"Character":[21],"Recognition":[22],"(OCR)":[23],"results.":[24],"But":[25],"documents":[27,64],"exhibit":[28],"wide":[30],"array":[31],"features":[33],"that":[34],"disturb":[35],"analysis,":[37],"such":[38],"as":[39],"multiple":[40],"columns,":[41],"drop":[42],"capitals":[43],"and":[44,82,101,115,120],"illustrations,":[45],"skewed":[46],"or":[47],"curved":[48],"text":[49,89],"lines,":[50],"noise,":[51],"annotations,":[52],"etc.":[53],"We":[54,108],"present":[55],"(DLA)":[60],"system":[61,92],"implemented":[65],"by":[66],"pixel-wise":[67],"segmentation":[68],"using":[69],"convolutional":[70],"neural":[71],"networks.":[72],"In":[73],"addition,":[74],"heuristic":[75],"methods":[76],"are":[77],"applied":[78],"to":[79,83,126],"detect":[80,94],"marginals":[81],"determine":[84],"reading":[86],"order":[87],"regions.":[90],"Our":[91],"can":[93],"more":[95],"classes":[97],"(e.g.":[98],"initials,":[99],"marginals)":[100],"achieves":[102],"higher":[103],"accuracy":[104],"than":[105],"competitive":[106],"approaches.":[107],"describe":[109],"algorithm,":[111],"different":[113],"models":[114],"how":[116],"they":[117],"were":[118],"trained":[119],"discuss":[121],"our":[122],"results":[123],"in":[124],"comparison":[125],"state-of-the-art":[128],"on":[129],"basis":[131],"three":[133],"datasets.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}