{"id":"https://openalex.org/W2730951118","doi":"https://doi.org/10.1145/3058555.3058581","title":"Extraction of Tabular Data from Document Images","display_name":"Extraction of Tabular Data from Document Images","publication_year":2017,"publication_date":"2017-04-02","ids":{"openalex":"https://openalex.org/W2730951118","doi":"https://doi.org/10.1145/3058555.3058581","mag":"2730951118"},"language":"en","primary_location":{"id":"doi:10.1145/3058555.3058581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3058555.3058581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Web for All Conference","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/A5034159634","display_name":"Manolis Vasileiadis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Manolis Vasileiadis","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076372245","display_name":"Nikolaos Kaklanis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Kaklanis","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064307246","display_name":"Konstantinos Votis","orcid":"https://orcid.org/0000-0001-6381-8326"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Votis","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087452615","display_name":"Dimitrios Tzovaras","orcid":"https://orcid.org/0000-0001-6915-6722"},"institutions":[{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Tzovaras","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thermi-Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034159634"],"corresponding_institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"],"apc_list":null,"apc_paid":null,"fwci":0.2731,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62971922,"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":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9883000254631042,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9473999738693237,"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/computer-science","display_name":"Computer science","score":0.8497540950775146},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7138710618019104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6460416316986084},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5502526760101318},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.463497132062912},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44363903999328613},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.4309902787208557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41639405488967896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4145217537879944},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33675265312194824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8497540950775146},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7138710618019104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6460416316986084},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5502526760101318},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.463497132062912},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44363903999328613},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.4309902787208557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41639405488967896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4145217537879944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33675265312194824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3058555.3058581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3058555.3058581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Web for All Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8767707713","display_name":null,"funder_award_id":"610510","funder_id":"https://openalex.org/F4320333065","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320333065","display_name":"Seventh Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2088980200","https://openalex.org/W2113438614","https://openalex.org/W2137998699","https://openalex.org/W2168445392","https://openalex.org/W2577020101","https://openalex.org/W2618354619"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W2784269775","https://openalex.org/W2952904874","https://openalex.org/W324626582","https://openalex.org/W4389302559"],"abstract_inverted_index":{"In":[0],"this":[1,74],"paper,":[2],"we":[3],"propose":[4],"a":[5,53,58],"heuristics-based":[6],"method":[7],"for":[8,112],"automatic":[9],"detection":[10],"and":[11,38,66],"extraction":[12],"of":[13,41,60,70,82,87,99],"tabular":[14,68,90],"data":[15,37,91],"from":[16],"document":[17,100],"images.":[18],"The":[19],"proposed":[20],"approach":[21],"utilizes":[22],"page":[23],"segmentation":[24],"techniques,":[25],"along":[26],"with":[27,114],"an":[28,76],"OCR":[29],"engine,":[30],"in":[31,44,52,62],"order":[32,63],"to":[33,64],"acquire":[34],"the":[35,45,84,97],"text":[36],"bounding":[39],"boxes":[40],"each":[42],"word":[43],"document.":[46],"These":[47],"elements":[48],"are":[49],"then":[50],"grouped":[51],"bottom-up":[54],"fashion,":[55],"based":[56],"on":[57,73],"series":[59],"rules,":[61],"identify":[65],"reconstruct":[67],"arrangements":[69],"data.":[71],"Based":[72],"methodology,":[75],"open":[77],"source":[78],"cross-platform":[79],"tool":[80],"capable":[81],"recognizing":[83],"semantic":[85],"structure":[86],"documents":[88],"containing":[89],"has":[92],"been":[93],"implemented,":[94],"thus":[95],"widening":[96],"range":[98],"types":[101],"than":[102],"can":[103],"be":[104],"successfully":[105],"converted":[106],"into":[107],"alternative":[108],"accessible":[109],"formats,":[110],"suitable":[111],"users":[113],"visual":[115],"impairments.":[116]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
