{"id":"https://openalex.org/W2132669457","doi":"https://doi.org/10.1109/icdar.2007.4378738","title":"Robust Page Segmentation Based on Smearing and Error Correction Unifying Top-down and Bottom-up Approaches","display_name":"Robust Page Segmentation Based on Smearing and Error Correction Unifying Top-down and Bottom-up Approaches","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W2132669457","doi":"https://doi.org/10.1109/icdar.2007.4378738","mag":"2132669457"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2007.4378738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378738","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":"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/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107484450","display_name":"Rohit Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rohit Prasad","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044398772","display_name":"Ehry MacRostie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117418","display_name":"Babraham Bioscience Technologies (United Kingdom)","ror":"https://ror.org/02b4c4128","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210117418"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ehry MacRostie","raw_affiliation_strings":["Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge"],"affiliations":[{"raw_affiliation_string":"Speech & Language Processing Department, BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge","institution_ids":["https://openalex.org/I4210117418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108504544"],"corresponding_institution_ids":["https://openalex.org/I4210117418"],"apc_list":null,"apc_paid":null,"fwci":3.0825,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91818182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965999722480774,"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":0.9937999844551086,"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/segmentation","display_name":"Segmentation","score":0.7686300277709961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622588872909546},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.7451923489570618},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6900781393051147},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.6332153677940369},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4634639322757721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45975613594055176},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.13471171259880066},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10359042882919312}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7686300277709961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622588872909546},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.7451923489570618},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6900781393051147},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.6332153677940369},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4634639322757721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45975613594055176},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13471171259880066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10359042882919312},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2007.4378738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2007.4378738","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1491852184","https://openalex.org/W1541814010","https://openalex.org/W1612759903","https://openalex.org/W2006947050","https://openalex.org/W2015432638","https://openalex.org/W2055408294","https://openalex.org/W2096210305","https://openalex.org/W2105669280","https://openalex.org/W2112692009","https://openalex.org/W2117776121","https://openalex.org/W2130283001","https://openalex.org/W2135085165","https://openalex.org/W2135164809","https://openalex.org/W2153554054","https://openalex.org/W2162031011","https://openalex.org/W2163534337","https://openalex.org/W6676277762","https://openalex.org/W6677658504"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W4229787472","https://openalex.org/W2486541857","https://openalex.org/W2108840191","https://openalex.org/W2111522305"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4,84],"a":[5,15,24,52,74],"robust":[6],"multi-pass":[7],"page":[8,55],"segmentation":[9,30,56],"algorithm.":[10,57],"The":[11],"first":[12,36],"pass":[13,22],"uses":[14],"modified":[16],"smearing":[17,53],"algorithm":[18],"and":[19,28,43,60,89,99],"the":[20,32,35,41,97],"second":[21],"performs":[23],"hybrid":[25],"of":[26,34,51,76,102],"bottom-up":[27,42],"top-down":[29,44],"on":[31,48,87],"output":[33],"pass.":[37],"Unlike":[38],"traditional":[39],"approaches,":[40],"steps":[45],"are":[46,68,78],"based":[47,54],"primitive":[49],"results":[50,86],"Therefore,":[58],"\"split\"":[59],"\"merge\"":[61],"processes":[62],"start":[63],"with":[64],"text":[65,71],"blocks":[66,72],"that":[67],"mostly":[69],"true":[70],"but":[73],"few":[75],"them":[77],"either":[79],"touching":[80],"or":[81],"broken.":[82],"We":[83],"experimental":[85],"newspaper":[88],"journal":[90],"documents":[91],"from":[92],"different":[93],"languages":[94],"to":[95],"demonstrate":[96],"robustness":[98],"language":[100],"independence":[101],"our":[103],"approach.":[104]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}