{"id":"https://openalex.org/W2140565904","doi":"https://doi.org/10.5539/cis.v7n1p162","title":"Layout Analysis for Scanned PDF and Transformation to the Structured PDF Suitable for Vocalization and Navigation","display_name":"Layout Analysis for Scanned PDF and Transformation to the Structured PDF Suitable for Vocalization and Navigation","publication_year":2014,"publication_date":"2014-01-19","ids":{"openalex":"https://openalex.org/W2140565904","doi":"https://doi.org/10.5539/cis.v7n1p162","mag":"2140565904"},"language":"en","primary_location":{"id":"doi:10.5539/cis.v7n1p162","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v7n1p162","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/33591/19311","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ccsenet.org/journal/index.php/cis/article/download/33591/19311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070261421","display_name":"Azaedeh Nazemi","orcid":null},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Azaedeh Nazemi","raw_affiliation_strings":["Departent of Electrical and Computer Engineering, Curtin University, Perth,WA, Australia"],"affiliations":[{"raw_affiliation_string":"Departent of Electrical and Computer Engineering, Curtin University, Perth,WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083745045","display_name":"Iain Murray","orcid":"https://orcid.org/0000-0003-1840-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iain Murray","raw_affiliation_strings":["Departent of Electrical and Computer Engineering, Curtin University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Departent of Electrical and Computer Engineering, Curtin University, Perth, WA, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064002466","display_name":"David A. McMeekin","orcid":"https://orcid.org/0000-0001-6445-1183"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]},{"id":"https://openalex.org/I2800497579","display_name":"CRC for Spatial information","ror":"https://ror.org/022482e21","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2800497579"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David A. McMeekin","raw_affiliation_strings":["Department of Spatial Sciences, Curtin University, Perth, WA, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Spatial Sciences, Curtin University, Perth, WA, Australia","institution_ids":["https://openalex.org/I2800497579","https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070261421"],"corresponding_institution_ids":["https://openalex.org/I205640436"],"apc_list":null,"apc_paid":null,"fwci":0.4941,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71683192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"7","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.953499972820282,"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":0.953499972820282,"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":0.8801889419555664},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7054464817047119},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5980008840560913},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.544864296913147},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.519029974937439},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.502197265625},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49912595748901367},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4850977659225464},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.4625972807407379},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.4421808123588562},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4414265751838684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38325509428977966},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.38076886534690857},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2923685312271118},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10814961791038513}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801889419555664},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7054464817047119},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5980008840560913},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.544864296913147},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.519029974937439},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.502197265625},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49912595748901367},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4850977659225464},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.4625972807407379},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.4421808123588562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4414265751838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38325509428977966},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.38076886534690857},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2923685312271118},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10814961791038513},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5539/cis.v7n1p162","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v7n1p162","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/33591/19311","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1000.7039","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1000.7039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ccsenet.org/journal/index.php/cis/article/download/33591/19311/","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.984.9897","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.984.9897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://espace.library.curtin.edu.au/cgi-bin/espace.pdf?file%3D/2014/11/03/file_1/203476","raw_type":"text"},{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/8128","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11937/8128","pdf_url":null,"source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.5539/cis.v7n1p162","is_oa":true,"landing_page_url":"https://doi.org/10.5539/cis.v7n1p162","pdf_url":"https://ccsenet.org/journal/index.php/cis/article/download/33591/19311","source":{"id":"https://openalex.org/S2764452479","display_name":"Computer and Information Science","issn_l":"1913-8989","issn":["1913-8989","1913-8997"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322531","host_organization_name":"Canadian Center of Science and Education","host_organization_lineage":["https://openalex.org/P4310322531"],"host_organization_lineage_names":["Canadian Center of Science and Education"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer and Information Science","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2140565904.pdf","grobid_xml":"https://content.openalex.org/works/W2140565904.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W418182363","https://openalex.org/W1974161648","https://openalex.org/W2122395000","https://openalex.org/W6614506703"],"related_works":["https://openalex.org/W629813691","https://openalex.org/W2402920184","https://openalex.org/W3205782414","https://openalex.org/W2021368897","https://openalex.org/W2039452999","https://openalex.org/W2970150031","https://openalex.org/W1501910896","https://openalex.org/W4241373955","https://openalex.org/W2801595672","https://openalex.org/W2751365402"],"abstract_inverted_index":{"Information":[0],"can":[1,8,36,118],"include":[2],"text,":[3],"pictures":[4],"and":[5,22,38,54,105,124,178,186,204,220,229],"signatures":[6],"that":[7,136,157],"be":[9,120],"scanned":[10,69,102,170],"into":[11],"a":[12,42,83,155],"document":[13,117,176],"format,":[14,74],"such":[15,50,81,212],"as":[16,51,82,126,128,213],"the":[17,28,31,34,59,62,68,87,90,101,137,144,148,164,169,173,197,200,205],"Portable":[18],"Document":[19],"Format":[20],"(PDF),":[21],"easily":[23],"emailed":[24],"to":[25,78,132],"recipients":[26],"around":[27],"world.":[29],"Upon":[30],"document\u2019s":[32],"arrival,":[33],"receiver":[35],"open":[37,174],"view":[39],"it":[40,75],"using":[41,172],"vast":[43],"array":[44],"of":[45,61,89,147,168,199,207],"different":[46],"PDF":[47,63,70,103,171],"viewing":[48],"applications":[49],"Adobe":[52],"Reader":[53],"Apple":[55],"Preview.":[56],"Hence,":[57],"today":[58],"use":[60],"has":[64],"become":[65],"pervasive.":[66],"Since":[67],"is":[71,76,143],"an":[72,110],"image":[73],"inaccessible":[77],"assistive":[79],"technologies":[80],"screen":[84],"reader.":[85],"Therefore,":[86],"retrieval":[88],"information":[91],"needs":[92],"Optical":[93],"Character":[94],"Recognition":[95],"(OCR).":[96],"The":[97,189],"OCR":[98,138,179],"software":[99,139],"scans":[100],"file":[104],"through":[106],"text":[107,112,116,150],"extraction":[108],"generates":[109],"editable":[111],"formatted":[113],"document.":[114],"This":[115,152],"then":[119],"edited,":[121],"formatted,":[122],"searched":[123],"indexed":[125],"well":[127],"translated":[129],"or":[130],"converted":[131],"speech.":[133],"A":[134],"problem":[135],"does":[140],"not":[141],"solve":[142],"accurate":[145],"regeneration":[146],"full":[149],"layout.":[151],"paper":[153],"presents":[154],"technology":[156],"addresses":[158],"this":[159,194],"issue":[160],"by":[161],"closely":[162],"preserving":[163],"original":[165],"textual":[166],"layout":[167,185],"source":[175],"analysis":[177],"system":[180],"(OCRopus)":[181],"based":[182],"on":[183],"geometric":[184],"positioning":[187],"information.":[188],"main":[190],"issues":[191],"considered":[192],"in":[193],"research":[195],"are":[196],"preservation":[198],"correct":[201],"reading":[202],"order,":[203],"representation":[206],"common":[208],"logical":[209],"structured":[210],"elements":[211],"section":[214],"headings,":[215],"line":[216],"breaks,":[217],"paragraphs,":[218],"captions,":[219],"sidebars,":[221],"foot-bars,":[222],"running":[223],"headers,":[224],"embedded":[225],"images,":[226],"graphics,":[227],"tables":[228],"mathematical":[230],"expressions.":[231]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
