{"id":"https://openalex.org/W1495319514","doi":"https://doi.org/10.1109/lec.2002.1182287","title":"Page layout analyser for multilingual Indian documents","display_name":"Page layout analyser for multilingual Indian documents","publication_year":2003,"publication_date":"2003-10-01","ids":{"openalex":"https://openalex.org/W1495319514","doi":"https://doi.org/10.1109/lec.2002.1182287","mag":"1495319514"},"language":"en","primary_location":{"id":"doi:10.1109/lec.2002.1182287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lec.2002.1182287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Engineering Conference, 2002. Proceedings","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/A5085117078","display_name":"Abhra Chaudhuri","orcid":"https://orcid.org/0009-0004-3723-668X"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A.R. Chaudhuri","raw_affiliation_strings":["Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103339089","display_name":"A. K. Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A.K. Mandal","raw_affiliation_strings":["Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025093894","display_name":"B.B. Chaudhuri","orcid":"https://orcid.org/0000-0003-0297-8929"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"B.B. Chaudhuri","raw_affiliation_strings":["Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I6498739"],"apc_list":null,"apc_paid":null,"fwci":0.8087,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.72171199,"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":"24","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9891999959945679,"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/analyser","display_name":"Analyser","score":0.9190466403961182},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8871761560440063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912313938140869},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6694002747535706},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6407842636108398},{"id":"https://openalex.org/keywords/homogeneity","display_name":"Homogeneity (statistics)","score":0.6039521098136902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48564043641090393},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.46983760595321655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529092609882355},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.44379228353500366},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.4169315695762634},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4062400460243225},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.17126941680908203},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16610831022262573},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15160876512527466},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13674047589302063}],"concepts":[{"id":"https://openalex.org/C26834552","wikidata":"https://www.wikidata.org/wiki/Q3275846","display_name":"Analyser","level":2,"score":0.9190466403961182},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8871761560440063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912313938140869},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6694002747535706},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6407842636108398},{"id":"https://openalex.org/C142259097","wikidata":"https://www.wikidata.org/wiki/Q5891314","display_name":"Homogeneity (statistics)","level":2,"score":0.6039521098136902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48564043641090393},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.46983760595321655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529092609882355},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.44379228353500366},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.4169315695762634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4062400460243225},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.17126941680908203},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16610831022262573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15160876512527466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13674047589302063},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lec.2002.1182287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lec.2002.1182287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Engineering Conference, 2002. Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1993636010","https://openalex.org/W2006947050","https://openalex.org/W2033085384","https://openalex.org/W2052721056","https://openalex.org/W2067845231","https://openalex.org/W2135164809","https://openalex.org/W2141756865","https://openalex.org/W2144209937","https://openalex.org/W4241647099","https://openalex.org/W6652241244"],"related_works":["https://openalex.org/W1904432136","https://openalex.org/W2887281027","https://openalex.org/W1552656226","https://openalex.org/W2807873899","https://openalex.org/W4288429387","https://openalex.org/W3098552971","https://openalex.org/W2039934116","https://openalex.org/W1987186610","https://openalex.org/W282478887","https://openalex.org/W2096369514"],"abstract_inverted_index":{"An":[0],"advanced":[1],"Optical":[2],"Character":[3],"Recognition":[4],"(OCR)":[5],"system":[6],"is":[7,79,91,95],"equipped":[8],"with":[9],"the":[10,13,76,98,123],"module":[11],"of":[12,39,75,89,122],"page":[14],"layout":[15,65],"analyser.":[16],"It":[17,24],"separates":[18],"textual":[19,26],"zones":[20],"from":[21,28,106],"non-textual":[22,107],"zones.":[23],"identifies":[25],"blocks":[27],"multicolumn":[29],"documents":[30],"and":[31,42,113,119,137],"groups":[32],"them":[33],"into":[34],"homogenous":[35],"regions":[36,105],"in":[37,73,97,129],"terms":[38],"geometric":[40],"shape":[41],"spatial":[43],"distribution.":[44],"All":[45],"existing":[46],"OCR":[47],"modules":[48],"developed":[49],"for":[50],"various":[51,87],"Indian":[52,77,133],"scripts":[53,78],"can":[54,102],"handle":[55],"text":[56,104],"only":[57],"single-column":[58],"documents.":[59],"In":[60],"this":[61],"paper,":[62],"a":[63],"page,":[64],"analyser":[66],"that":[67,85,100],"uses":[68],"typical":[69],"common":[70],"features":[71],"present":[72],"most":[74,131],"introduced.":[80],"A":[81],"simple":[82],"compatibility":[83],"criterion":[84],"allows":[86],"degrees":[88],"homogeneity":[90],"defined.":[92],"The":[93],"page-analyser":[94],"robust":[96],"sense":[99],"it":[101],"distinguish":[103],"entities":[108],"such":[109],"as":[110],"images,":[111],"rulers,":[112],"noisy":[114],"signals":[115],"due":[116],"to":[117],"smudges":[118],"poor":[120],"quality":[121],"paper.":[124],"Test":[125],"results":[126],"are":[127],"shown":[128],"two":[130],"popular":[132],"Scripts,":[134],"Devnagari":[135],"(Hindi)":[136],"Bangla.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
