{"id":"https://openalex.org/W4392305649","doi":"https://doi.org/10.5220/0012422500003654","title":"Double Trouble? Impact and Detection of Duplicates in Face Image Datasets","display_name":"Double Trouble? Impact and Detection of Duplicates in Face Image Datasets","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392305649","doi":"https://doi.org/10.5220/0012422500003654"},"language":"en","primary_location":{"id":"doi:10.5220/0012422500003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012422500003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0012422500003654","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008474809","display_name":"Torsten Schlett","orcid":"https://orcid.org/0000-0003-0052-2741"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Torsten Schlett","raw_affiliation_strings":["da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I107257983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087866084","display_name":"Christian Rathgeb","orcid":"https://orcid.org/0000-0003-1901-9468"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Rathgeb","raw_affiliation_strings":["da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I107257983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017736954","display_name":"Juan Tapia","orcid":"https://orcid.org/0000-0001-9159-4075"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juan Tapia","raw_affiliation_strings":["da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I107257983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017716310","display_name":"Christoph Busch","orcid":"https://orcid.org/0000-0002-9159-2923"},"institutions":[{"id":"https://openalex.org/I107257983","display_name":"Darmstadt University of Applied Sciences","ror":"https://ror.org/047wbd030","country_code":"DE","type":"education","lineage":["https://openalex.org/I107257983"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Busch","raw_affiliation_strings":["da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"da/sec - Biometrics and Security Research Group, Hochschule Darmstadt, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I107257983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I107257983"],"apc_list":null,"apc_paid":null,"fwci":0.2629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45914205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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/T10828","display_name":"Biometric Identification and Security","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9708999991416931,"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":0.8258106708526611},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7238636016845703},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6976897716522217},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6526473164558411},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.6296849846839905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.609998881816864},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5794791579246521},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5278456211090088},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.514356255531311},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5062941312789917},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.43616020679473877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3936390280723572},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3451099991798401},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24074599146842957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258106708526611},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7238636016845703},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6976897716522217},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6526473164558411},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.6296849846839905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.609998881816864},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5794791579246521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5278456211090088},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.514356255531311},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5062941312789917},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.43616020679473877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3936390280723572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3451099991798401},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24074599146842957},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0012422500003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012422500003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0012422500003654","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0012422500003654","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1509966554","https://openalex.org/W1965804146","https://openalex.org/W2009119155","https://openalex.org/W2134013617","https://openalex.org/W2515770085","https://openalex.org/W2800958090","https://openalex.org/W2963314072","https://openalex.org/W2969985801","https://openalex.org/W2972738593","https://openalex.org/W3161821165","https://openalex.org/W4287272562","https://openalex.org/W4386066208","https://openalex.org/W4389105023"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"Various":[0],"face":[1,34,49,55,58,72],"image":[2,35,40,50,59],"datasets":[3],"intended":[4],"for":[5,75,111],"facial":[6],"biometrics":[7],"research":[8],"were":[9],"created":[10],"via":[11],"web-scraping,":[12],"i.e.":[13],"the":[14,21,46,68,71,125,128],"collection":[15],"of":[16,48,70,107,109],"images":[17,73],"publicly":[18],"available":[19],"on":[20,54,124],"internet.This":[22],"work":[23],"presents":[24],"an":[25],"approach":[26,42,81],"to":[27,84,105],"detect":[28],"both":[29,74],"exactly":[30],"and":[31,39,57,66,92,116],"nearly":[32],"identical":[33],"duplicates,":[36],"using":[37],"file":[38],"hashes.The":[41],"is":[43,82],"extended":[44],"through":[45,127],"use":[47],"preprocessing.Additional":[51],"steps":[52],"based":[53],"recognition":[56,115],"quality":[60,117],"assessment":[61,118],"models":[62],"reduce":[63],"false":[64],"positives,":[65],"facilitate":[67],"deduplication":[69],"intra-and":[76],"inter-subject":[77],"duplicate":[78,129],"sets.The":[79],"presented":[80],"applied":[83],"five":[85],"datasets,":[86],"namely":[87],"LFW,":[88],"TinyFace,":[89],"Adience,":[90],"CASIA-WebFace,":[91],"C-MS-Celeb":[93],"(a":[94],"cleaned":[95],"MS-Celeb-1M":[96],"variant).Duplicates":[97],"are":[98],"detected":[99],"within":[100],"every":[101],"dataset,":[102],"with":[103],"hundreds":[104,106],"thousands":[108],"duplicates":[110],"all":[112],"except":[113],"LFW.Face":[114],"experiments":[119],"indicate":[120],"a":[121],"minor":[122],"impact":[123],"results":[126],"removal.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-03-05T00:00:00"}