{"id":"https://openalex.org/W2106247188","doi":"https://doi.org/10.1109/icdar.2007.4378699","title":"An Efficient Word Segmentation Technique for Historical and Degraded Machine-Printed Documents","display_name":"An Efficient Word Segmentation Technique for Historical and Degraded Machine-Printed Documents","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2106247188","doi":"https://doi.org/10.1109/icdar.2007.4378699","mag":"2106247188"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4378699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378699","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015419644","display_name":"Michail Makridis","orcid":"https://orcid.org/0000-0001-7462-4674"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"M. Makridis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","Democritus University of Thrace, Xanthi#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]},{"raw_affiliation_string":"Democritus University of Thrace, Xanthi#TAB#","institution_ids":["https://openalex.org/I147962203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068569936","display_name":"\u039d\u03b9\u03ba\u03cc\u03bb\u03b1\u03bf\u03c2 \u039d\u03b9\u03ba\u03bf\u03bb\u03ac\u03bf\u03c5","orcid":"https://orcid.org/0000-0001-8453-7574"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"N. Nikolaou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","Democritus University of Thrace, Xanthi#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]},{"raw_affiliation_string":"Democritus University of Thrace, Xanthi#TAB#","institution_ids":["https://openalex.org/I147962203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006291450","display_name":"Basilis Gatos","orcid":"https://orcid.org/0000-0001-9873-0826"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"B. Gatos","raw_affiliation_strings":["Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research Demokritos, Athens, Greece","Democritus University of Thrace, 67 100 Xanthi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center for Scientific Research Demokritos, Athens, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"raw_affiliation_string":"Democritus University of Thrace, 67 100 Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0512,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.75569813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T10601","display_name":"Handwritten Text Recognition Techniques","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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.994700014591217,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9850999712944031,"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/computer-science","display_name":"Computer science","score":0.8394848108291626},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8039448261260986},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.7003424763679504},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6403690576553345},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.636235237121582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6105650067329407},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.539131760597229},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5366325974464417},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5132021903991699},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4890500009059906},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.4761795401573181},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44693881273269653},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4226554334163666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38901054859161377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3661949932575226},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2693224251270294},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19609421491622925},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09415900707244873}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8394848108291626},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8039448261260986},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7003424763679504},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6403690576553345},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.636235237121582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6105650067329407},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.539131760597229},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5366325974464417},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5132021903991699},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4890500009059906},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.4761795401573181},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44693881273269653},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4226554334163666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38901054859161377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3661949932575226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2693224251270294},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19609421491622925},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09415900707244873},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdar.2007.4378699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378699","pdf_url":null,"source":{"id":"https://openalex.org/S4210215987","display_name":"Proceedings of the International Conference on Document Analysis and Recognition","issn_l":"1520-5363","issn":["1520-5363","2379-2140"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.2079","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.2079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iit.demokritos.gr/~bgat/Icdar2007_AnEfficientWordSegm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1491852184","https://openalex.org/W1535506285","https://openalex.org/W1921780317","https://openalex.org/W2048072578","https://openalex.org/W2054530826","https://openalex.org/W2063476404","https://openalex.org/W2092269560","https://openalex.org/W2096210305","https://openalex.org/W2096497661","https://openalex.org/W2118756867","https://openalex.org/W2131136277","https://openalex.org/W2142472163","https://openalex.org/W2162031011","https://openalex.org/W6632111166","https://openalex.org/W6673536509","https://openalex.org/W6679325557"],"related_works":["https://openalex.org/W2067514453","https://openalex.org/W2784287639","https://openalex.org/W3023805750","https://openalex.org/W4294702218","https://openalex.org/W2119179626","https://openalex.org/W4308094881","https://openalex.org/W2038329042","https://openalex.org/W2067601176","https://openalex.org/W2131730163","https://openalex.org/W2189110401"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,32,101,116,141],"is":[2,12,67],"a":[3,27,71,105],"crucial":[4],"step":[5],"for":[6,14,30,143],"segmentation-free":[7],"document":[8],"analysis":[9],"systems":[10],"and":[11,35,53,59,62,86,103,123,145],"used":[13],"creating":[15],"an":[16],"index":[17],"based":[18,68],"on":[19,93,120],"word":[20,31,115,140],"matching.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"propose":[26],"novel":[28],"methodology":[29,133],"in":[33,96],"historical":[34,122,144],"degraded":[36,124,146],"machine-printed":[37,125,147],"documents.":[38,148],"The":[39],"proposed":[40],"technique":[41],"faces":[42],"problems":[43],"such":[44],"as":[45,90,92],"having":[46,51,60],"text":[47,52,64,82,107],"of":[48],"different":[49],"size,":[50],"non-text":[54],"areas":[55],"lying":[56],"very":[57],"near":[58],"non-straight":[61],"warped":[63],"lines.":[65],"It":[66],"on:":[69],"(i)":[70],"dynamic":[72],"run":[73],"length":[74],"smoothing":[75],"algorithm":[76],"that":[77,111,131],"helps":[78],"grouping":[79],"together":[80],"homogeneous":[81],"regions,":[83],"(ii)":[84],"noise":[85],"punctuation":[87],"marks":[88],"removal":[89],"well":[91],"obstacle":[94],"detection":[95],"order":[97],"to":[98,137],"facilitate":[99],"the":[100,113],"process":[102],"(iv)":[104],"draft":[106],"line":[108],"estimation":[109],"procedure":[110],"guides":[112],"final":[114],"result.":[117],"After":[118],"testing":[119],"numerous":[121],"documents,":[126],"it":[127],"has":[128],"turned":[129],"out":[130],"our":[132],"performs":[134],"better":[135],"compared":[136],"current":[138],"state-of-the-art":[139],"techniques":[142]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}