{"id":"https://openalex.org/W7138008625","doi":"https://doi.org/10.1109/access.2026.3674930","title":"Document Image Layout Analysis Algorithm Based on Improved YOLOv8s","display_name":"Document Image Layout Analysis Algorithm Based on Improved YOLOv8s","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7138008625","doi":"https://doi.org/10.1109/access.2026.3674930"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3674930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3674930","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3674930","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068151620","display_name":"You Jing","orcid":"https://orcid.org/0000-0002-3724-7918"},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Jing","raw_affiliation_strings":["Aliyun School of Big Data, Changzhou University, Changzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aliyun School of Big Data, Changzhou University, Changzhou, Jiangsu, China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641317","display_name":"Gu Heng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153482","display_name":"Changzhou University","ror":"https://ror.org/04ymgwq66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153482"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu Heng","raw_affiliation_strings":["Aliyun School of Big Data, Changzhou University, Changzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aliyun School of Big Data, Changzhou University, Changzhou, Jiangsu, China","institution_ids":["https://openalex.org/I4210153482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725453","display_name":"Wang Zhirong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145263","display_name":"Changzhou City Planning and Design Institute","ror":"https://ror.org/05datqy35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145263"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Zhirong","raw_affiliation_strings":["Changzhou Inspection Testing and Standard Accreditation Institute, Changzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changzhou Inspection Testing and Standard Accreditation Institute, Changzhou, Jiangsu, China","institution_ids":["https://openalex.org/I4210145263"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129717657","display_name":"Yang Yuhua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145263","display_name":"Changzhou City Planning and Design Institute","ror":"https://ror.org/05datqy35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145263"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yuhua","raw_affiliation_strings":["Changzhou Inspection Testing and Standard Accreditation Institute, Changzhou, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changzhou Inspection Testing and Standard Accreditation Institute, Changzhou, Jiangsu, China","institution_ids":["https://openalex.org/I4210145263"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30493916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"44464","last_page":"44477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.1356000006198883,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.1356000006198883,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13567","display_name":"AI and Multimedia in Education","score":0.0949999988079071,"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"}},{"id":"https://openalex.org/T13647","display_name":"AI and Big Data Applications","score":0.07509999722242355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48089998960494995},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.4797999858856201},{"id":"https://openalex.org/keywords/algorithm-design","display_name":"Algorithm design","score":0.4634999930858612},{"id":"https://openalex.org/keywords/document-image-processing","display_name":"Document image processing","score":0.4530999958515167},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.427700012922287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723000049591064},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.4797999858856201},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.4530999958515167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4480000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44449999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43050000071525574},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.427700012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C5546195","wikidata":"https://www.wikidata.org/wiki/Q5969842","display_name":"IC layout editor","level":5,"score":0.26080000400543213},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C3020028006","wikidata":"https://www.wikidata.org/wiki/Q9158","display_name":"Electronic mail","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3674930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3674930","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1c374d729cb6471aa4e9153cfda22183","is_oa":true,"landing_page_url":"https://doaj.org/article/1c374d729cb6471aa4e9153cfda22183","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 44464-44477 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3674930","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3674930","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Document":[0],"layout":[1,85,110],"analysis":[2,86],"is":[3,132,137],"a":[4],"fundamental":[5],"and":[6,15,33,47,62,76,101,117,160,171,182,189,201],"critical":[7],"task":[8,106],"in":[9,22,80],"the":[10,40,71,105,114,118,122,140,156,168],"field":[11],"of":[12,30,42,73,107,179],"document":[13,48,84,108,130],"understanding":[14],"digital":[16],"transformation,":[17],"playing":[18],"an":[19,91,148],"irreplaceable":[20],"role":[21],"scenarios":[23],"such":[24],"as":[25,139],"intelligent":[26],"office":[27],"automation,":[28],"digitization":[29],"ancient":[31],"books,":[32],"knowledge":[34],"retrieval.":[35],"Its":[36],"accuracy":[37,65],"directly":[38],"affects":[39],"performance":[41],"downstream":[43],"tasks":[44],"like":[45],"OCR":[46],"structure":[49],"restoration.":[50],"However,":[51],"existing":[52,186],"deep":[53,82],"learning-based":[54,83],"methods":[55],"often":[56],"suffer":[57],"from":[58,129],"high":[59,77],"computational":[60,197],"costs":[61,79],"insufficient":[63],"detection":[64,94],"for":[66],"complex":[67],"layouts.":[68],"To":[69],"address":[70],"issues":[72],"low":[74],"efficiency":[75],"training":[78],"current":[81],"methods,":[87],"this":[88],"paper":[89],"proposes":[90],"improved":[92],"object":[93],"network":[95],"named":[96],"SL-YOLO":[97,175],"based":[98],"on":[99,167],"YOLOv8s,":[100],"applies":[102],"it":[103],"to":[104,125,154],"image":[109],"analysis.":[111],"By":[112],"introducing":[113],"C2f_Star":[115],"module":[116],"LSKA":[119],"attention":[120],"mechanism,":[121],"network\u2019s":[123],"ability":[124],"extract":[126],"multi-scale":[127],"features":[128],"images":[131],"effectively":[133],"enhanced.":[134],"The":[135],"WIoUv3":[136],"adopted":[138],"bounding":[141],"box":[142],"regression":[143],"loss":[144],"function,":[145],"along":[146],"with":[147],"appropriate":[149],"gradient":[150],"gain":[151],"allocation":[152],"strategy,":[153],"improve":[155],"model\u2019s":[157],"generalization":[158],"capability":[159],"overall":[161],"performance.":[162],"Experimental":[163],"results":[164],"demonstrate":[165],"that":[166],"LA,":[169],"CDLA,":[170],"IIITAR-":[172],"13K":[173],"datasets,":[174],"achieves":[176],"mAP@0.50:0.95":[177],"scores":[178],"71.2%,":[180],"86.9%,":[181],"81.5%,":[183],"respectively,":[184],"outperforming":[185],"two-stage":[187],"algorithms":[188],"other":[190],"one-stage":[191],"algorithms,":[192],"while":[193],"also":[194],"exhibiting":[195],"lower":[196],"complexity,":[198],"fewer":[199],"parameters,":[200],"faster":[202],"inference":[203],"efficiency.":[204]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-18T00:00:00"}