{"id":"https://openalex.org/W1566408939","doi":"https://doi.org/10.1109/mva.2015.7153182","title":"Document image dataset indexing and compression using connected components clustering","display_name":"Document image dataset indexing and compression using connected components clustering","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1566408939","doi":"https://doi.org/10.1109/mva.2015.7153182","mag":"1566408939"},"language":"en","primary_location":{"id":"doi:10.1109/mva.2015.7153182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mva.2015.7153182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 14th IAPR International Conference on Machine Vision Applications (MVA)","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/A5076218326","display_name":"Houssem Chatbri","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Houssem Chatbri","raw_affiliation_strings":["Department of Computer Science, Graduate School of Systems and Information Engineering","Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Japan.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Graduate School of Systems and Information Engineering","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science, Graduate School of Systems and Information Engineering, University of Tsukuba, Japan.#TAB#","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078481609","display_name":"Keisuke Kameyama","orcid":"https://orcid.org/0000-0001-8810-8646"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kameyama","raw_affiliation_strings":["Faculty of Engineering, University of Tsukuba, Japan","Faculty of Engineering, Information and Systems, University of Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba,Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3744,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66837304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"267","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9994999766349792,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7598303556442261},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7489025592803955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7109862565994263},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6549604535102844},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5502141714096069},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5143867135047913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5091080069541931},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5071818828582764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47094830870628357},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4590652287006378},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4556196331977844},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4286397695541382},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4280097186565399},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4115438461303711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4080654978752136},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3754553198814392},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37531155347824097},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2180362045764923}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7598303556442261},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7489025592803955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109862565994263},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6549604535102844},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5502141714096069},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5143867135047913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5091080069541931},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5071818828582764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47094830870628357},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4590652287006378},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4556196331977844},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4286397695541382},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4280097186565399},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4115438461303711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4080654978752136},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3754553198814392},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37531155347824097},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2180362045764923},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mva.2015.7153182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mva.2015.7153182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 14th IAPR International Conference on Machine Vision Applications (MVA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W40026635","https://openalex.org/W1982005175","https://openalex.org/W1984622776","https://openalex.org/W2014959772","https://openalex.org/W2026732585","https://openalex.org/W2065116648","https://openalex.org/W2073640678","https://openalex.org/W2116112220","https://openalex.org/W2128119911","https://openalex.org/W2141756865","https://openalex.org/W2146691531","https://openalex.org/W2155729921","https://openalex.org/W6646131288"],"related_works":["https://openalex.org/W1835589799","https://openalex.org/W2144265691","https://openalex.org/W2386366915","https://openalex.org/W2953482628","https://openalex.org/W4220868150","https://openalex.org/W2022517628","https://openalex.org/W1605991620","https://openalex.org/W4387251676","https://openalex.org/W1487213935","https://openalex.org/W4385261619"],"abstract_inverted_index":{"We":[0,109],"present":[1],"a":[2,31,36,66,97],"method":[3,17],"for":[4,106],"document":[5,120,134],"image":[6,24,121,135],"dataset":[7,23],"indexing":[8,38,115,127],"and":[9,25,69,90,96,116,148,160],"compression":[10,79,117,143,155,162],"by":[11,51],"clustering":[12,28],"of":[13,39,100,171],"connected":[14,19],"components.":[15,58],"Our":[16,154],"extracts":[18],"components":[20],"from":[21,56],"each":[22],"performs":[26],"component":[27,46,107],"to":[29],"make":[30],"hash":[32,61,85],"table":[33,62,86],"that":[34,103,126],"is":[35,43,49,63,73,87],"compressed":[37,75],"the":[40,57,60,70,84,146,161,169],"dataset.":[41],"Clustering":[42],"based":[44],"on":[45],"similarity":[47],"which":[48],"estimated":[50],"comparing":[52],"shape":[53],"features":[54],"extracted":[55],"Then,":[59],"saved":[64],"in":[65,83,114,133],"text":[67,71],"file,":[68],"file":[72],"further":[74],"using":[76,92,118],"any":[77],"available":[78],"methodology.":[80],"Component":[81],"encoding":[82],"storage":[88],"efficient":[89],"done":[91],"components'":[93],"contour":[94],"points":[95,102],"reduced":[98],"number":[99],"interior":[101],"are":[104,157,164],"sufficient":[105],"reconstruction.":[108],"evaluate":[110],"our":[111],"method's":[112],"performances":[113],"four":[119],"datasets.":[122],"Experimental":[123],"results":[124],"show":[125,151],"significantly":[128],"improves":[129],"efficiency":[130],"when":[131],"used":[132],"retrieval.":[136],"In":[137],"addition,":[138],"comparative":[139],"evaluation":[140],"with":[141],"two":[142],"standards,":[144],"namely":[145],"ZIP":[147],"XZ":[149],"formats,":[150],"competitive":[152],"performances.":[153],"rates":[156],"below":[158],"20%":[159],"errors":[163],"very":[165],"low":[166],"being":[167],"at":[168],"order":[170],"10":[172],"<sup":[173],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">-6</sup>":[175],"%":[176],"per":[177],"image.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}