{"id":"https://openalex.org/W2067966908","doi":"https://doi.org/10.1145/2034691.2034722","title":"Document visual similarity measure for document search","display_name":"Document visual similarity measure for document search","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W2067966908","doi":"https://doi.org/10.1145/2034691.2034722","mag":"2067966908"},"language":"en","primary_location":{"id":"doi:10.1145/2034691.2034722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","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/A5027306642","display_name":"Ildus Ahmadullin","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ildus Ahmadullin","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043967979","display_name":"Jan P. Allebach","orcid":"https://orcid.org/0000-0001-5608-8249"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Allebach","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012980226","display_name":"Niranjan Damera-Venkata","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niranjan Damera-Venkata","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077871435","display_name":"Jian Fan","orcid":"https://orcid.org/0000-0001-5009-9588"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Fan","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039823017","display_name":"Seungyon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seungyon Lee","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659445","display_name":"Qian Lin","orcid":"https://orcid.org/0009-0000-7034-7331"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Lin","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107840655","display_name":"Jerry Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry Liu","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075359615","display_name":"Eamonn O\u2019Brien-Strain","orcid":null},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eamonn O'Brien-Strain","raw_affiliation_strings":["HP Labs, Palo Alto, CA, USA","HP Labs, Palo ALto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"HP Labs, Palo ALto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027306642"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.5213,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68897303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9945999979972839,"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/hellinger-distance","display_name":"Hellinger distance","score":0.9210198521614075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993703246116638},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6277270317077637},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6243353486061096},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6016849875450134},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5910007357597351},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5502731800079346},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.48375487327575684},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.46597835421562195},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.46032702922821045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42377424240112305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4219232499599457},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3262559175491333},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28455719351768494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24108976125717163},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.16373354196548462},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08161488175392151}],"concepts":[{"id":"https://openalex.org/C153024298","wikidata":"https://www.wikidata.org/wiki/Q3030678","display_name":"Hellinger distance","level":2,"score":0.9210198521614075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993703246116638},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6277270317077637},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6243353486061096},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6016849875450134},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5910007357597351},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5502731800079346},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.48375487327575684},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.46597835421562195},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.46032702922821045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42377424240112305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219232499599457},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3262559175491333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28455719351768494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24108976125717163},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.16373354196548462},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08161488175392151},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2034691.2034722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1504337617","https://openalex.org/W1984821985","https://openalex.org/W2065128999","https://openalex.org/W2100470808","https://openalex.org/W2106596127","https://openalex.org/W2113119382","https://openalex.org/W2123487311","https://openalex.org/W2144935315","https://openalex.org/W2151658918","https://openalex.org/W3148595793"],"related_works":["https://openalex.org/W2050620380","https://openalex.org/W1977834563","https://openalex.org/W1979265735","https://openalex.org/W2153363506","https://openalex.org/W2043026651","https://openalex.org/W2146350580","https://openalex.org/W3106798595","https://openalex.org/W2090890022","https://openalex.org/W2052451333","https://openalex.org/W2364202348"],"abstract_inverted_index":{"Managing":[0],"large":[1],"document":[2,14,62,85,92,143,155],"databases":[3],"has":[4],"become":[5],"an":[6,112],"important":[7],"task.":[8],"Being":[9],"able":[10],"to":[11,23,28,80,131,149],"automatically":[12],"compare":[13],"layouts":[15],"and":[16,18,89,101],"classify":[17],"search":[19,140],"documents":[20,45,77,108,152],"with":[21,78],"respect":[22,79],"their":[24,48],"visual":[25,49,58],"appearance":[26,59],"proves":[27,130],"be":[29,132,158],"desirable":[30],"in":[31,134,141,153],"many":[32],"applications.":[33],"We":[34,70],"propose":[35],"a":[36,41,97,142,154],"new":[37],"algorithm":[38],"that":[39],"approximates":[40],"metric":[42],"function":[43],"between":[44,83,103,118],"based":[46,54],"on":[47,56],"similarity.":[50],"The":[51],"comparison":[52],"is":[53,94],"only":[55],"the":[57,61,72,104,115,122,126,135,146],"of":[60,74,106,114,137],"without":[63],"taking":[64],"into":[65],"consideration":[66],"its":[67],"text":[68],"content.":[69],"measure":[71],"similarity":[73],"single":[75],"page":[76],"distance":[81,117,124],"functions":[82],"three":[84],"components:":[86],"background,":[87],"text,":[88],"saliency.":[90],"Each":[91],"component":[93],"represented":[95],"as":[96,111],"Gaussian":[98],"mixture":[99],"distribution;":[100],"distances":[102],"components":[105],"different":[107],"are":[109],"calculated":[110],"approximation":[113],"Hellinger":[116,123],"corresponding":[119],"distributions.":[120],"Since":[121],"obeys":[125],"triangle":[127],"inequality,":[128],"it":[129],"favorable":[133],"task":[136],"nearest":[138],"neighbor":[139],"database.":[144],"Thus,":[145],"computation":[147],"required":[148],"find":[150],"similar":[151],"database":[156],"can":[157],"significantly":[159],"reduced.":[160]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}