{"id":"https://openalex.org/W4410794696","doi":"https://doi.org/10.1145/3727353.3727391","title":"Automatic Extraction of PDF Table Data Based on Deep Learning","display_name":"Automatic Extraction of PDF Table Data Based on Deep Learning","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4410794696","doi":"https://doi.org/10.1145/3727353.3727391"},"language":"en","primary_location":{"id":"doi:10.1145/3727353.3727391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727391","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727391","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112081540","display_name":"Wen Zhi Yang","orcid":"https://orcid.org/0009-0004-3179-1957"},"institutions":[{"id":"https://openalex.org/I4210097173","display_name":"Shandong Yingcai University","ror":"https://ror.org/00qhrkk71","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210097173"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Yang","raw_affiliation_strings":["Shandong Key Laboratory of Electric Power Big Data Processing and Security, Jinan, Shandong, China","Shandong Yingcai University, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0004-3179-1957","affiliations":[{"raw_affiliation_string":"Shandong Key Laboratory of Electric Power Big Data Processing and Security, Jinan, Shandong, China","institution_ids":[]},{"raw_affiliation_string":"Shandong Yingcai University, Jinan, Shandong, China","institution_ids":["https://openalex.org/I4210097173"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003190595","display_name":"Min Yu","orcid":"https://orcid.org/0009-0001-3440-1369"},"institutions":[{"id":"https://openalex.org/I4210097173","display_name":"Shandong Yingcai University","ror":"https://ror.org/00qhrkk71","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210097173"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Yu","raw_affiliation_strings":["Shandong Key Laboratory of Electric Power Big Data Processing and Security, Jinan, Shandong, China","Shandong Yingcai University, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0001-3440-1369","affiliations":[{"raw_affiliation_string":"Shandong Key Laboratory of Electric Power Big Data Processing and Security, Jinan, Shandong, China","institution_ids":[]},{"raw_affiliation_string":"Shandong Yingcai University, Jinan, Shandong, China","institution_ids":["https://openalex.org/I4210097173"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210097173"],"apc_list":null,"apc_paid":null,"fwci":1.403,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79216525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9702000021934509,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9702000021934509,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9560999870300293,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9535999894142151,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819634675979614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6239042282104492},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6074771881103516},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42756524682044983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32669419050216675},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3119266927242279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819634675979614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6239042282104492},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6074771881103516},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42756524682044983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32669419050216675},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3119266927242279},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3727353.3727391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727391","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3727353.3727391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727391","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727391","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410794696.pdf","grobid_xml":"https://content.openalex.org/works/W4410794696.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2910897241","https://openalex.org/W3118722740","https://openalex.org/W3181927451"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W4394193569","https://openalex.org/W1797990060","https://openalex.org/W4232484699","https://openalex.org/W2473636215","https://openalex.org/W4242025311","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"This":[0],"article":[1,71,121,191,220],"delves":[2],"into":[3],"the":[4,21,26,33,36,45,70,73,79,111,136,140,190,198,212,219,222],"automatic":[5,64],"extraction":[6,65],"technology":[7,66],"of":[8,25,35,44,78,113,126,160,226],"PDF":[9,39,84,114,131,230],"table":[10,55,85,132,231],"data":[11,49,232],"based":[12],"on":[13,20],"deep":[14],"learning,":[15,95],"with":[16,139,155,167],"a":[17,88,123,156,206],"particular":[18],"focus":[19],"application":[22],"and":[23,51,54,76,101,173,180,204,224,233],"performance":[24,128],"PaddleOCR":[27,80,92,147,227],"framework":[28,81],"in":[29,82,129,228],"this":[30],"field.":[31],"With":[32],"advent":[34],"information":[37,52],"age,":[38],"documents":[40],"have":[41],"become":[42],"one":[43],"primary":[46],"formats":[47],"for":[48,201],"exchange":[50],"storage,":[53],"data,":[56],"as":[57,177,196],"an":[58],"important":[59],"component":[60],"thereof,":[61],"renders":[62],"its":[63],"particularly":[67],"crucial.":[68],"Subsequently,":[69],"highlights":[72],"key":[74],"features":[75],"applications":[77],"extracting":[83,130,229],"data.":[86,133],"As":[87],"powerful":[89],"OCR":[90],"tool,":[91],"supports":[93],"multi-task":[94],"including":[96],"text":[97,99],"detection,":[98],"recognition,":[100],"layout":[102,202],"analysis,":[103],"among":[104],"others,":[105],"enabling":[106],"it":[107,143],"to":[108,162,187,216],"comprehensively":[109],"understand":[110],"structure":[112],"documents,":[115],"especially":[116],"those":[117],"containing":[118,170],"tables.":[119],"The":[120],"conducts":[122],"detailed":[124],"evaluation":[125],"PaddleOCR's":[127],"By":[134],"comparing":[135],"recognition":[137,157,181,213],"results":[138],"original":[141],"tables,":[142,154],"is":[144],"found":[145],"that":[146],"performs":[148],"exceptionally":[149],"well":[150],"when":[151,165],"processing":[152],"most":[153],"accuracy":[158,214],"rate":[159,215],"up":[161],"93%.":[163],"However,":[164],"dealing":[166],"complex":[168],"tables":[169],"merged":[171],"cells":[172],"watermarks,":[174],"issues":[175],"such":[176,195],"redundant":[178],"characters":[179],"errors":[182],"still":[183],"exist.":[184],"In":[185],"response":[186],"these":[188],"issues,":[189],"proposes":[192,234],"optimization":[193],"solutions,":[194],"utilizing":[197],"PP-PicoDet":[199],"model":[200],"analysis":[203],"incorporating":[205],"watermark":[207],"removal":[208],"step,":[209],"ultimately":[210],"increasing":[211],"96.4%.":[217],"Finally,":[218],"summarizes":[221],"advantages":[223],"disadvantages":[225],"future":[235],"research":[236],"directions.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}