{"id":"https://openalex.org/W7204103995","doi":"https://doi.org/10.1108/ijpcc-02-2025-0077","title":"Leveraging computer vision and natural language processing for efficient metadata extraction in digitized books","display_name":"Leveraging computer vision and natural language processing for efficient metadata extraction in digitized books","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204103995","doi":"https://doi.org/10.1108/ijpcc-02-2025-0077"},"language":"en","primary_location":{"id":"doi:10.1108/ijpcc-02-2025-0077","doi":"https://doi.org/10.1108/ijpcc-02-2025-0077","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijpcc-02-2025-0077","pdf_url":null,"source":{"id":"https://openalex.org/S172682790","display_name":"International Journal of Pervasive Computing and Communications","issn_l":"1742-7371","issn":["1742-7371","1742-738X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pervasive Computing and Communications","raw_type":"journal-article"},"volume":null,"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/A5061307708","display_name":"Amalia Amalia","orcid":"https://orcid.org/0000-0003-0595-8296","observed_orcids":["https://orcid.org/0000-0003-0595-8296"]},"institutions":[{"id":"https://openalex.org/I254887060","display_name":"Universitas Sumatera Utara","ror":"https://ror.org/01kknrc90","country_code":"ID","type":"education","lineage":["https://openalex.org/I254887060"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Amalia Amalia","raw_affiliation_strings":["Universitas Sumatera Utara Department of Computer Science, , Medan,"],"raw_orcid":"https://orcid.org/0000-0003-0595-8296","affiliations":[{"raw_affiliation_string":"Universitas Sumatera Utara Department of Computer Science, , Medan,","institution_ids":["https://openalex.org/I254887060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053264918","display_name":"Baihaqi Siregar","orcid":"https://orcid.org/0000-0001-7195-4010","observed_orcids":["https://orcid.org/0000-0001-7195-4010"]},"institutions":[{"id":"https://openalex.org/I254887060","display_name":"Universitas Sumatera Utara","ror":"https://ror.org/01kknrc90","country_code":"ID","type":"education","lineage":["https://openalex.org/I254887060"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Baihaqi Siregar","raw_affiliation_strings":["Universitas Sumatera Utara Department of Information Technology, , Medan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Sumatera Utara Department of Information Technology, , Medan,","institution_ids":["https://openalex.org/I254887060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5099016204","display_name":"Khairul Imam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I254887060","display_name":"Universitas Sumatera Utara","ror":"https://ror.org/01kknrc90","country_code":"ID","type":"education","lineage":["https://openalex.org/I254887060"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Khairul Imam","raw_affiliation_strings":["Universitas Sumatera Utara Department of Computer Science, , Medan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitas Sumatera Utara Department of Computer Science, , Medan,","institution_ids":["https://openalex.org/I254887060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061307708"],"corresponding_institution_ids":["https://openalex.org/I254887060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67069497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.986299991607666,"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":0.986299991607666,"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/T14330","display_name":"Library Science and Information Systems","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/metadata-extraction","display_name":"metadata extraction","score":0.722000002861023},{"id":"https://openalex.org/keywords/digitized-books","display_name":"digitized books","score":0.9940000176429749},{"id":"https://openalex.org/keywords/digital-libraries","display_name":"digital libraries","score":0.6830000281333923},{"id":"https://openalex.org/keywords/page-classification","display_name":"page classification","score":0.7839999794960022},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.6819999814033508},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.9309999942779541},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9980000257492065},{"id":"https://openalex.org/keywords/bibliographic-metadata","display_name":"bibliographic metadata","score":0.7990000247955322},{"id":"https://openalex.org/keywords/mobilenetv2","display_name":"MobileNetV2","score":0.7549999952316284},{"id":"https://openalex.org/keywords/efficientdet","display_name":"EfficientDet","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9089999794960022},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9020000100135803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6176999807357788},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5153999924659729},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3756999969482422},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.30149999260902405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2779344036","wikidata":"https://www.wikidata.org/wiki/Q11320476","display_name":"Digital content","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/ijpcc-02-2025-0077","doi":"https://doi.org/10.1108/ijpcc-02-2025-0077","is_oa":false,"landing_page_url":"https://doi.org/10.1108/ijpcc-02-2025-0077","pdf_url":null,"source":{"id":"https://openalex.org/S172682790","display_name":"International Journal of Pervasive Computing and Communications","issn_l":"1742-7371","issn":["1742-7371","1742-738X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pervasive Computing and Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.8057358860969543,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1601433541","https://openalex.org/W1866900365","https://openalex.org/W1873781437","https://openalex.org/W1945277895","https://openalex.org/W1998037981","https://openalex.org/W2099244020","https://openalex.org/W2108598243","https://openalex.org/W2133059825","https://openalex.org/W2757390651","https://openalex.org/W2889830604","https://openalex.org/W2891334607","https://openalex.org/W2963163009","https://openalex.org/W3003711898","https://openalex.org/W3034971973","https://openalex.org/W3163476226","https://openalex.org/W3202466114","https://openalex.org/W3206672312","https://openalex.org/W3209681642","https://openalex.org/W4225480862","https://openalex.org/W4236506895","https://openalex.org/W4313015712","https://openalex.org/W4315570198","https://openalex.org/W4321786146","https://openalex.org/W4366833488","https://openalex.org/W4386004102","https://openalex.org/W4397011937","https://openalex.org/W4402422259","https://openalex.org/W4402422666","https://openalex.org/W4403344409","https://openalex.org/W4410854808","https://openalex.org/W4411359700","https://openalex.org/W4411980533","https://openalex.org/W4414253921","https://openalex.org/W7091525510"],"related_works":[],"abstract_inverted_index":{"Purpose":[0],"High-quality":[1],"book":[2],"metadata":[3,15,45,191,216],"improves":[4],"digital":[5,194],"libraries":[6],"by":[7,50,93],"supporting":[8],"cataloging,":[9],"searchability":[10],"and":[11,28,54,73,83,98,121,144,151,157,162,164,185,209],"automated":[12],"classification.":[13],"However,":[14],"generation":[16],"from":[17,47,89],"scanned":[18],"books":[19,49,117],"remains":[20],"challenging":[21],"due":[22],"to":[23,37,64,101,188,206],"limited":[24],"annotated":[25,125],"data":[26,113,202],"sets":[27],"optical":[29],"character":[30],"recognition":[31,96],"(OCR)":[32],"limitations.":[33],"This":[34,171],"study":[35,172],"aims":[36],"propose":[38],"a":[39,111,174],"deep":[40],"learning-based":[41],"framework":[42,61,107,176],"for":[43,153,159,166,213],"automatic":[44],"extraction":[46,192],"digitized":[48],"integrating":[51],"computer":[52],"vision":[53],"natural":[55],"language":[56],"processing":[57],"(NLP).":[58],"Design/methodology/approach":[59],"The":[60,106,128],"uses":[62],"MobileNetV2":[63],"classify":[65],"title":[66,154],"pages,":[67,155,168],"table":[68],"of":[69,115,149],"contents":[70],"(ToC)":[71],"pages":[72,161],"content":[74,167],"pages.":[75,126],"EfficientDet":[76],"detects":[77],"metadata-related":[78],"regions,":[79,91],"such":[80],"as":[81],"titles":[82],"author":[84],"information.":[85],"OCR":[86,207],"extracts":[87],"text":[88],"these":[90],"followed":[92],"named":[94],"entity":[95],"(NER)":[97],"regular":[99],"expressions":[100],"refine":[102],"the":[103,138],"extracted":[104],"metadata.":[105],"was":[108],"evaluated":[109],"using":[110],"custom":[112],"set":[114],"188":[116],"published":[118],"between":[119],"1800":[120],"2021,":[122],"comprising":[123],"857":[124],"Findings":[127],"page":[129,179],"classification":[130],"model":[131,139],"achieved":[132],"97.16%":[133],"accuracy.":[134],"For":[135],"object":[136,181],"detection,":[137,182],"obtained":[140],"average":[141,145],"precision":[142],"(AP)":[143],"recall":[146],"(AR)":[147],"scores":[148],"71.7%":[150],"42.0%":[152],"55.1%":[156],"33.4%":[158],"ToC":[160],"87.9%":[163],"54.4%":[165],"respectively.":[169],"Originality/value":[170],"contributes":[173],"scalable":[175],"that":[177],"combines":[178],"classification,":[180],"OCR,":[183],"NER":[184],"rule-based":[186],"refinement":[187],"reduce":[189],"manual":[190],"in":[193],"library":[195],"management.":[196],"Future":[197],"research":[198],"can":[199],"expand":[200],"multilingual":[201],"sets,":[203],"improve":[204],"robustness":[205],"noise":[208],"explore":[210],"end-to-end":[211],"learning":[212],"richer":[214],"bibliographic":[215],"extraction.":[217]},"counts_by_year":[],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2026-08-25T00:00:00"}