{"id":"https://openalex.org/W2060975379","doi":"https://doi.org/10.1145/2536146.2536157","title":"Duplicate detection approaches for quality assurance of document image collections","display_name":"Duplicate detection approaches for quality assurance of document image collections","publication_year":2013,"publication_date":"2013-10-28","ids":{"openalex":"https://openalex.org/W2060975379","doi":"https://doi.org/10.1145/2536146.2536157","mag":"2060975379"},"language":"en","primary_location":{"id":"doi:10.1145/2536146.2536157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2536146.2536157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Conference on Management of Emergent Digital EcoSystems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3439059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014584547","display_name":"Roman Graf","orcid":"https://orcid.org/0000-0002-4479-2092"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Roman Graf","raw_affiliation_strings":["Networks and Services, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","Networks and Services, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Networks and Services, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Networks and Services, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046830498","display_name":"Reinhold Huber-M\u00f6rk","orcid":null},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Reinhold Huber-M\u00f6rk","raw_affiliation_strings":["Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746568","display_name":"Alexander Schindler","orcid":"https://orcid.org/0000-0001-6058-7753"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexander Schindler","raw_affiliation_strings":["Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Research Area Intelligent Vision Systems, AIT - Austrian Institute of Technology GmbH, Vienna, Austria#TAB#","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024673660","display_name":"Sven Schlarb","orcid":"https://orcid.org/0000-0003-3717-0014"},"institutions":[{"id":"https://openalex.org/I2802781690","display_name":"Austrian National Library","ror":"https://ror.org/03dscga50","country_code":"AT","type":"archive","lineage":["https://openalex.org/I2802781690"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sven Schlarb","raw_affiliation_strings":["Austrian National Library, Vienna, Austria","Austrian National Library, Vienna, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"Austrian National Library, Vienna, Austria","institution_ids":["https://openalex.org/I2802781690"]},{"raw_affiliation_string":"Austrian National Library, Vienna, Austria#TAB#","institution_ids":["https://openalex.org/I2802781690"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014584547"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.2722,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60661862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"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":0.9908999800682068,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9904999732971191,"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/workflow","display_name":"Workflow","score":0.8343929052352905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332180976867676},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.5757743716239929},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47499504685401917},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45962584018707275},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45436033606529236},{"id":"https://openalex.org/keywords/digital-image","display_name":"Digital image","score":0.43101951479911804},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.42761263251304626},{"id":"https://openalex.org/keywords/digital-image-processing","display_name":"Digital image processing","score":0.41589099168777466},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3183715343475342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2672663927078247},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20310643315315247}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8343929052352905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332180976867676},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.5757743716239929},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47499504685401917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45962584018707275},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45436033606529236},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.43101951479911804},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.42761263251304626},{"id":"https://openalex.org/C104317675","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Digital image processing","level":4,"score":0.41589099168777466},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3183715343475342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2672663927078247},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20310643315315247},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2536146.2536157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2536146.2536157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Conference on Management of Emergent Digital EcoSystems","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:3439059","is_oa":true,"landing_page_url":"https://zenodo.org/record/3439059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3439059","is_oa":true,"landing_page_url":"https://zenodo.org/record/3439059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G4196209642","display_name":null,"funder_award_id":"270137","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338370","display_name":"FP7 Information and Communication Technologies","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W47947492","https://openalex.org/W1018200693","https://openalex.org/W1505641881","https://openalex.org/W1625255723","https://openalex.org/W2010668953","https://openalex.org/W2037515122","https://openalex.org/W2047389942","https://openalex.org/W2055289292","https://openalex.org/W2085261163","https://openalex.org/W2109822575","https://openalex.org/W2117228865","https://openalex.org/W2122715077","https://openalex.org/W2130703170","https://openalex.org/W2133665775","https://openalex.org/W2141362318","https://openalex.org/W2151103935","https://openalex.org/W2170288539","https://openalex.org/W2767812578"],"related_works":["https://openalex.org/W2356087891","https://openalex.org/W3036827782","https://openalex.org/W2348439329","https://openalex.org/W2553152692","https://openalex.org/W2951194758","https://openalex.org/W2183514925","https://openalex.org/W2080625741","https://openalex.org/W4377241632","https://openalex.org/W2373336158","https://openalex.org/W1997609524"],"abstract_inverted_index":{"This":[0],"paper":[1,39],"presents":[2],"an":[3],"evaluation":[4,161],"of":[5,30,45,72,86,138,145,153,163],"different":[6,46,73],"methods":[7,102,110],"for":[8,26,63,118,131],"automatic":[9],"duplicate":[10,64,82],"detection":[11,65,83,94],"in":[12,33,66,77,159],"digitized":[13],"collections.":[14,70],"These":[15],"approaches":[16,88],"are":[17,157],"meant":[18],"to":[19,51,79],"support":[20],"quality":[21],"assurance":[22],"and":[23,35,43,96,129,149],"decision":[24,116],"making":[25,117],"long":[27,119],"term":[28,120],"preservation":[29,61],"digital":[31,60,67,140],"content":[32,137],"libraries":[34],"archives.":[36],"In":[37],"this":[38],"we":[40],"demonstrate":[41,80],"advantages":[42],"drawbacks":[44],"approaches.":[47,84],"Our":[48],"goal":[49],"is":[50,89],"select":[52],"the":[53,59,136,139,146,150,154,160,164],"most":[54],"efficient":[55],"method":[56],"which":[57],"satisfies":[58],"requirements":[62],"document":[68],"image":[69,100,108],"Workflows":[71],"complexity":[74],"were":[75],"designed":[76],"order":[78],"possible":[81],"Assessment":[85],"individual":[87],"based":[90],"on":[91,135],"workflow":[92],"simplicity,":[93],"accuracy":[95],"acceptable":[97],"performance,":[98],"since":[99],"processing":[101,109],"typically":[103],"require":[104],"significant":[105],"computation.":[106],"Applied":[107],"create":[111],"expert":[112,127],"knowledge":[113,134,156],"that":[114],"facilitates":[115],"preservation.":[121],"We":[122],"employ":[123],"AI":[124],"technologies":[125],"like":[126],"rules":[128],"clustering":[130],"inferring":[132],"explicit":[133],"collection.":[141],"A":[142],"statistical":[143],"analysis":[144,152],"aggregated":[147,155],"information":[148],"qualitative":[151],"presented":[158],"part":[162],"paper.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
