{"id":"https://openalex.org/W2100949927","doi":"https://doi.org/10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","title":"Structure recognition and information extraction from tabular documents","display_name":"Structure recognition and information extraction from tabular documents","publication_year":1996,"publication_date":"1996-01-01","ids":{"openalex":"https://openalex.org/W2100949927","doi":"https://doi.org/10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","mag":"2100949927"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","pdf_url":null,"source":{"id":"https://openalex.org/S15952048","display_name":"International Journal of Imaging Systems and Technology","issn_l":"0899-9457","issn":["0899-9457","1098-1098"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Imaging Systems and Technology","raw_type":"journal-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/A5111883802","display_name":"S. Chandran","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Surekha Chandran","raw_affiliation_strings":["Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080064923","display_name":"Sanjay Balasubramanian","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Balasubramanian","raw_affiliation_strings":["Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113689229","display_name":"Tarak Gandhi","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarak Gandhi","raw_affiliation_strings":["Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007002314","display_name":"Arathi Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arathi Prasad","raw_affiliation_strings":["Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063184621","display_name":"Rangachar Kasturi","orcid":"https://orcid.org/0000-0003-3956-1967"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rangachar Kasturi","raw_affiliation_strings":["Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pond Laboratory, The Pennsylvania State University, University Park, PA 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110360786","display_name":"Atul K. Chhabra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atul Chhabra","raw_affiliation_strings":["NYNEX Science and Technology, Inc., 500 Westchester Avenue, White Plains, NY 10604"],"affiliations":[{"raw_affiliation_string":"NYNEX Science and Technology, Inc., 500 Westchester Avenue, White Plains, NY 10604","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5111883802"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3450,"currency":"USD","value_usd":3450},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.23372206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":"4","first_page":"289","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.995199978351593,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9876000285148621,"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/table","display_name":"Table (database)","score":0.7959303855895996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642942667007446},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.6373544335365295},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6064149141311646},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5610896348953247},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5420329570770264},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5233568549156189},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.4900118410587311},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.465156614780426},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4398255944252014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4167138934135437},{"id":"https://openalex.org/keywords/horizontal-and-vertical","display_name":"Horizontal and vertical","score":0.414937287569046},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3792782425880432},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36146247386932373},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33418190479278564},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10574409365653992},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0774349570274353}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7959303855895996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642942667007446},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6373544335365295},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6064149141311646},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5610896348953247},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5420329570770264},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5233568549156189},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.4900118410587311},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.465156614780426},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4398255944252014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4167138934135437},{"id":"https://openalex.org/C59218005","wikidata":"https://www.wikidata.org/wiki/Q17027571","display_name":"Horizontal and vertical","level":2,"score":0.414937287569046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3792782425880432},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36146247386932373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33418190479278564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10574409365653992},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0774349570274353},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-1098(199624)7:4<289::aid-ima4>3.0.co;2-4","pdf_url":null,"source":{"id":"https://openalex.org/S15952048","display_name":"International Journal of Imaging Systems and Technology","issn_l":"0899-9457","issn":["0899-9457","1098-1098"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Imaging Systems and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2373330951","https://openalex.org/W4385504528","https://openalex.org/W2078210347"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,12,241],"system":[3],"for":[4,82,128],"the":[5,8,18,24,51,59,66,75,92,100,104,107,117,120,137,148,151,158,162,198,214,220,224,226,245],"extraction":[6],"of":[7,11,62,99,109,119,136,150,161,175,200,223],"structural":[9,159],"information":[10,95,160,171,196,228],"table":[13],"from":[14,172],"its":[15],"image.":[16],"Following":[17],"initial":[19],"binarization":[20],"and":[21,32,77,203,210,231,270],"deskewing":[22],"operations,":[23],"image":[25],"is":[26,229,235,273],"scanned":[27],"to":[28,64,96,115,156,168,212,239],"extract":[29,157,169],"all":[30],"horizontal":[31,76],"vertical":[33,78],"lines":[34,63],"that":[35],"may":[36],"be":[37,126,166,208],"present.":[38],"The":[39,123,153,248],"table's":[40],"dimensions":[41],"are":[42,71,113,252],"estimated":[43],"based":[44],"on":[45,58,147,185],"these":[46,110],"lines.":[47,86],"Unlike":[48],"other":[49],"systems,":[50],"procedure":[52,90,155],"described":[53],"here":[54],"does":[55],"not":[56],"depend":[57],"sole":[60],"existence":[61],"mark":[65],"item":[67,101,111],"blocks.":[68],"White":[69],"streams":[70],"recognized":[72,211],"in":[73,103,144,197,237,255,258,277],"both":[74],"directions":[79],"as":[80,130,132,260,262],"substitutes":[81],"any":[83],"missing":[84],"demarcation":[85,94],"A":[87],"structure":[88,118,149,222],"interpretation":[89,124],"uses":[91],"extracted":[93,230],"identify":[97],"each":[98],"blocks":[102,112],"table.":[105,152],"Subsequently,":[106],"interrelations":[108],"used":[114,167],"recognize":[116],"tabulated":[121],"data.":[122],"can":[125,165],"done":[127],"one-dimensional":[129],"well":[131],"two-dimensional":[133],"tables.":[134],"Interpretation":[135],"tabular":[138,163,176,246],"document":[139,164,215],"involves":[140],"character":[141],"recognition,":[142],"which":[143,206],"turn":[145],"depends":[146],"above":[154],"useful":[170],"different":[173],"types":[174],"drawings.":[177,191],"In":[178],"this":[179,278],"article,":[180],"we":[181],"focus":[182],"our":[183],"attention":[184],"interpreting":[186],"telephone":[187,249],"company":[188,250],"central":[189],"office":[190],"These":[192],"drawings":[193,251],"contain":[194],"additional":[195,227],"form":[199],"crossed-out":[201],"entries":[202],"repeated":[204],"entries,":[205],"must":[207],"detected":[209],"interpret":[213],"completely.":[216],"Hence,":[217],"after":[218],"extracting":[219],"basic":[221],"drawing,":[225],"cell":[232],"block":[233],"location":[234],"obtained":[236],"order":[238],"develop":[240],"data":[242],"base":[243],"representing":[244],"document.":[247],"very":[253],"large":[254,261],"size,":[256],"resulting":[257],"images":[259],"15,000":[263],"x":[264],"10,000":[265],"pixels.":[266],"Thus,":[267],"designing":[268],"efficient":[269],"fast":[271],"algorithms":[272],"an":[274],"important":[275],"criterion":[276],"research.":[279],"\u00a9":[280],"1996":[281],"John":[282],"Wiley":[283],"&":[284],"Sons,":[285],"Inc.":[286]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}