{"id":"https://openalex.org/W2146431990","doi":"https://doi.org/10.1109/icip.2005.1530104","title":"Unsupervised style classification of document page images","display_name":"Unsupervised style classification of document page images","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2146431990","doi":"https://doi.org/10.1109/icip.2005.1530104","mag":"2146431990"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2005.1530104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2005.1530104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Image Processing 2005","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/A5008633788","display_name":"Song Mao","orcid":"https://orcid.org/0000-0001-7851-6347"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Song Mao","raw_affiliation_strings":["U.S. National Library of Medicine, Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"U.S. National Library of Medicine, Bethesda, MD, USA","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067896271","display_name":"Lan Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lan Nie","raw_affiliation_strings":["Computer Science and Engineering Department, Lehigh University, PA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Lehigh University, PA, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074891005","display_name":"Grid Thoma","orcid":"https://orcid.org/0000-0001-9836-2605"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.R. Thoma","raw_affiliation_strings":["U.S. National Library of Medicine, Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"U.S. National Library of Medicine, Bethesda, MD, USA","institution_ids":["https://openalex.org/I2800548410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008633788"],"corresponding_institution_ids":["https://openalex.org/I2800548410"],"apc_list":null,"apc_paid":null,"fwci":0.8954,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.78110204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"208","issue":null,"first_page":"II","last_page":"510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9865999817848206,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9534000158309937,"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":0.7615691423416138},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5897055268287659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5637734532356262},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5346160531044006},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5319217443466187},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5104088187217712},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5053487420082092},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.48796433210372925},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48544031381607056},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4803967773914337},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.46693888306617737},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42883315682411194},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.41594403982162476},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.41308820247650146},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3741723597049713},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35373643040657043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14540129899978638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615691423416138},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5897055268287659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637734532356262},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5346160531044006},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5319217443466187},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5104088187217712},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5053487420082092},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.48796433210372925},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48544031381607056},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4803967773914337},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.46693888306617737},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42883315682411194},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.41594403982162476},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.41308820247650146},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3741723597049713},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35373643040657043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14540129899978638},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2005.1530104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2005.1530104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Image Processing 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.1909","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.1909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://archive.nlm.nih.gov/pubs/mao/ICIP05Mao.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1967118885","https://openalex.org/W2012892907","https://openalex.org/W2119755031","https://openalex.org/W2130746998","https://openalex.org/W2132368650","https://openalex.org/W2165992492","https://openalex.org/W2999729612","https://openalex.org/W6653697124"],"related_works":["https://openalex.org/W1556724143","https://openalex.org/W2538371562","https://openalex.org/W3046994506","https://openalex.org/W1529573855","https://openalex.org/W2045631426","https://openalex.org/W1751894661","https://openalex.org/W4238415164","https://openalex.org/W2137763598","https://openalex.org/W2142127980","https://openalex.org/W2887224884"],"abstract_inverted_index":{"Style":[0],"classification":[1,62,187],"of":[2,12,15,47,71,107,133,148,155,176,189,195,198],"document":[3,26,37,48,80,101,161],"page":[4,49,81],"images":[5,50],"is":[6,92,123,141],"crucial":[7],"for":[8],"logical":[9,135],"structure":[10],"analysis":[11],"heterogeneous":[13],"collections":[14],"documents.":[16],"Both":[17],"layout":[18],"and":[19,129,174],"contextual":[20],"features":[21],"contain":[22],"significant":[23],"information":[24],"about":[25],"styles.":[27,201],"Most":[28],"existing":[29],"methods":[30,33],"are":[31,41],"supervised":[32],"in":[34],"which":[35,122,156],"specific":[36],"models":[38],"or":[39,68],"classifiers":[40],"learned":[42],"from":[43],"a":[44,105,159],"training":[45,67],"set":[46,106],"with":[51,170],"known":[52],"class":[53],"labels.":[54],"In":[55,74],"this":[56],"paper,":[57],"we":[58,76],"propose":[59,104],"an":[60,83,145,185],"unsupervised":[61],"method":[63],"that":[64],"involves":[65],"no":[66],"manual":[69],"selection":[70],"algorithm":[72,91,140,166,183],"parameters.":[73],"particular,":[75],"first":[77],"represent":[78],"each":[79,154],"as":[82],"ordered":[84],"labeled":[85],"X-Y":[86],"tree.":[87],"A":[88],"tree":[89,108],"matching":[90],"then":[93],"used":[94,142],"to":[95,125,143,158],"compute":[96],"style":[97,177],"dissimilarity":[98],"between":[99,117],"two":[100,118],"pages.":[102],"We":[103,163],"edit":[109],"cost":[110],"functions":[111],"based":[112],"on":[113,167],"Karl":[114],"Pearson":[115],"distance":[116],"multivariate":[119],"feature":[120],"observations,":[121],"robust":[124],"the":[126,138,149],"over-segmentation":[127],"problem":[128],"zone":[130],"length":[131],"variations":[132],"same":[134],"entities.":[136],"Finally,":[137],"K-medoids":[139],"find":[144],"optimal":[146],"grouping":[147],"trees":[150],"into":[151],"K":[152],"clusters,":[153],"corresponds":[157],"distinct":[160],"style.":[162],"evaluate":[164],"our":[165,182],"test":[168],"datasets":[169,193],"different":[171,200],"cluster":[172],"sizes":[173],"degrees":[175],"similarity.":[178],"Experimental":[179],"results":[180],"show":[181],"achieved":[184],"average":[186],"accuracy":[188],"95.69%":[190],"over":[191],"six":[192],"consisting":[194],"150":[196],"pages":[197],"11":[199]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}