{"id":"https://openalex.org/W2171788462","doi":"https://doi.org/10.1109/tip.2010.2101611","title":"Text Segmentation for MRC Document Compression","display_name":"Text Segmentation for MRC Document Compression","publication_year":2010,"publication_date":"2010-12-23","ids":{"openalex":"https://openalex.org/W2171788462","doi":"https://doi.org/10.1109/tip.2010.2101611","mag":"2171788462","pmid":"https://pubmed.ncbi.nlm.nih.gov/21189243"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2010.2101611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2010.2101611","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5047552045","display_name":"Eri Haneda","orcid":"https://orcid.org/0000-0003-2660-9028"},"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":"E Haneda","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University,West Lafayette, IN 47907-2035, USA. ehaneda@ecn.purdue.edu","School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,West Lafayette, IN 47907-2035, USA. ehaneda@ecn.purdue.edu","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056657991","display_name":"Charles A. Bouman","orcid":"https://orcid.org/0000-0001-8504-0383"},"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":"C A Bouman","raw_affiliation_strings":["School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.539,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90879716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"6","first_page":"1611","last_page":"1626"},"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9976000189781189,"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/segmentation","display_name":"Segmentation","score":0.748830258846283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7005435824394226},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.6458919644355774},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5669968128204346},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5629866123199463},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5480955243110657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5457737445831299},{"id":"https://openalex.org/keywords/raster-graphics","display_name":"Raster graphics","score":0.544019877910614},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5423458814620972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5302999019622803},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4990725517272949},{"id":"https://openalex.org/keywords/connected-component-labeling","display_name":"Connected-component labeling","score":0.4450942277908325},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.442778617143631},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41658177971839905},{"id":"https://openalex.org/keywords/markov-random-field","display_name":"Markov random field","score":0.41307246685028076}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.748830258846283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005435824394226},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.6458919644355774},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5669968128204346},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5629866123199463},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5480955243110657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457737445831299},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.544019877910614},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5423458814620972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5302999019622803},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4990725517272949},{"id":"https://openalex.org/C58737948","wikidata":"https://www.wikidata.org/wiki/Q3136397","display_name":"Connected-component labeling","level":5,"score":0.4450942277908325},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.442778617143631},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41658177971839905},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.41307246685028076},{"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/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007089","descriptor_name":"Image Enhancement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007089","descriptor_name":"Image Enhancement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007089","descriptor_name":"Image Enhancement","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2010.2101611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2010.2101611","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:21189243","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21189243","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W28766783","https://openalex.org/W49742075","https://openalex.org/W73629738","https://openalex.org/W79749824","https://openalex.org/W1554544485","https://openalex.org/W1600276254","https://openalex.org/W1975153766","https://openalex.org/W1992516180","https://openalex.org/W2007667797","https://openalex.org/W2009667652","https://openalex.org/W2015432638","https://openalex.org/W2016847844","https://openalex.org/W2021422668","https://openalex.org/W2027883219","https://openalex.org/W2041028608","https://openalex.org/W2053476892","https://openalex.org/W2060884415","https://openalex.org/W2073640678","https://openalex.org/W2080718738","https://openalex.org/W2083970667","https://openalex.org/W2084917952","https://openalex.org/W2095844239","https://openalex.org/W2097090565","https://openalex.org/W2100617128","https://openalex.org/W2101897555","https://openalex.org/W2103233308","https://openalex.org/W2103261738","https://openalex.org/W2105408040","https://openalex.org/W2106596127","https://openalex.org/W2114220616","https://openalex.org/W2124189704","https://openalex.org/W2126397022","https://openalex.org/W2128060444","https://openalex.org/W2130023865","https://openalex.org/W2130608499","https://openalex.org/W2132463201","https://openalex.org/W2133059825","https://openalex.org/W2135085165","https://openalex.org/W2135164809","https://openalex.org/W2141756865","https://openalex.org/W2144209937","https://openalex.org/W2147880316","https://openalex.org/W2151658918","https://openalex.org/W2155440966","https://openalex.org/W2158295445","https://openalex.org/W2169402356","https://openalex.org/W2752885492","https://openalex.org/W2977486570","https://openalex.org/W4206519171","https://openalex.org/W6671925633","https://openalex.org/W6674470930","https://openalex.org/W6674793120","https://openalex.org/W6679494170","https://openalex.org/W6682082992","https://openalex.org/W6768394776"],"related_works":["https://openalex.org/W2166767718","https://openalex.org/W2164805551","https://openalex.org/W2551987074","https://openalex.org/W4308936289","https://openalex.org/W2357849651","https://openalex.org/W2396229236","https://openalex.org/W1602119326","https://openalex.org/W2135547413","https://openalex.org/W154206032","https://openalex.org/W2103507220"],"abstract_inverted_index":{"The":[0,29,97,116,141],"mixed":[1],"raster":[2],"content":[3],"(MRC)":[4],"standard":[5],"(ITU-T":[6],"T.44)":[7],"specifies":[8],"a":[9,47,58,80,105,111,150,193],"framework":[10,152],"for":[11,85],"document":[12,39,60,87],"compression":[13,27,33,55],"which":[14],"can":[15,209],"dramatically":[16],"improve":[17,156,210],"the":[18,35,38,51,66,72,91,124,157,177,182,205,211,219],"compression/quality":[19],"tradeoff":[20],"as":[21,46],"compared":[22],"to":[23,31,70,155,167],"traditional":[24],"lossy":[25],"image":[26],"algorithms.":[28,96],"key":[30],"MRC":[32,59,86,170],"is":[34,62,104],"separation":[36],"of":[37,57,94,131,160,188,198,213],"into":[40,149],"foreground":[41],"and":[42,54,172],"background":[43],"layers,":[44],"represented":[45],"binary":[48,73],"mask.":[49,74],"Therefore,":[50],"resulting":[52],"quality":[53,212],"ratio":[56],"encoder":[61],"highly":[63],"dependent":[64],"upon":[65,90],"segmentation":[67,83,102,107,126,144,158,174,207],"algorithm":[68,108,184,208],"used":[69],"compute":[71],"In":[75,165],"this":[76],"paper,":[77],"we":[78,179],"propose":[79],"novel":[81],"multiscale":[82,151],"scheme":[84],"encoding":[88],"based":[89],"sequential":[92],"application":[93],"two":[95],"first":[98],"algorithm,":[99,118],"cost":[100,113],"optimized":[101],"(COS),":[103],"blockwise":[106],"formulated":[109],"in":[110,153,176],"global":[112],"optimization":[114],"framework.":[115],"second":[117],"connected":[119,132],"component":[120],"classification":[121],"(CCC),":[122],"refines":[123],"initial":[125],"by":[127],"classifying":[128],"feature":[129],"vectors":[130],"components":[133],"using":[134],"an":[135],"Markov":[136],"random":[137],"field":[138],"(MRF)":[139],"model.":[140],"combined":[142],"COS/CCC":[143],"algorithms":[145,175],"are":[146],"then":[147],"incorporated":[148],"order":[154],"accuracy":[159,187],"text":[161,189],"with":[162,192],"varying":[163],"size.":[164],"comparisons":[166],"state-of-the-art":[168],"commercial":[169],"products":[171],"selected":[173],"literature,":[178],"show":[180],"that":[181,204],"new":[183],"achieves":[185],"greater":[186],"detection":[190,196],"but":[191],"lower":[194],"false":[195],"rate":[197],"nontext":[199],"features.":[200],"We":[201],"also":[202],"demonstrate":[203],"proposed":[206],"decoded":[214],"documents":[215],"while":[216],"simultaneously":[217],"lowering":[218],"bit":[220],"rate.":[221]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}