{"id":"https://openalex.org/W7118065961","doi":"https://doi.org/10.1007/s42044-025-00384-z","title":"A systematic image augmentation framework based on dataset limitations for small object detection","display_name":"A systematic image augmentation framework based on dataset limitations for small object detection","publication_year":2026,"publication_date":"2026-01-02","ids":{"openalex":"https://openalex.org/W7118065961","doi":"https://doi.org/10.1007/s42044-025-00384-z"},"language":"en","primary_location":{"id":"doi:10.1007/s42044-025-00384-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42044-025-00384-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42044-025-00384-z.pdf","source":{"id":"https://openalex.org/S4210220078","display_name":"Iran Journal of Computer Science","issn_l":"2520-8438","issn":["2520-8438","2520-8446"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iran Journal of Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42044-025-00384-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011549220","display_name":"Ume Nisa","orcid":"https://orcid.org/0009-0005-2560-0007"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Ume Nisa","raw_affiliation_strings":["School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023268855","display_name":"Muhammad Syafiq Mohd Pozi","orcid":"https://orcid.org/0000-0001-9379-7351"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Muhammad Syafiq Mohd Pozi","raw_affiliation_strings":["School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121844511","display_name":"Mohamed Ali Saip","orcid":null},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohamed Ali Saip","raw_affiliation_strings":["School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 06010, Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011549220","https://openalex.org/A5023268855"],"corresponding_institution_ids":["https://openalex.org/I94625822"],"apc_list":{"value":3190,"currency":"USD","value_usd":3190},"apc_paid":{"value":3190,"currency":"USD","value_usd":3190},"fwci":4.6258,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89148857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6699000000953674,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6699000000953674,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.04399999976158142,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03420000150799751,"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/object-detection","display_name":"Object detection","score":0.722599983215332},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6664000153541565},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5764999985694885},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5709999799728394},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47350001335144043},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4713999927043915},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623000144958496},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.722599983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7071999907493591},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4713999927043915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.2849999964237213},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42044-025-00384-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42044-025-00384-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42044-025-00384-z.pdf","source":{"id":"https://openalex.org/S4210220078","display_name":"Iran Journal of Computer Science","issn_l":"2520-8438","issn":["2520-8438","2520-8446"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iran Journal of Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42044-025-00384-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42044-025-00384-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42044-025-00384-z.pdf","source":{"id":"https://openalex.org/S4210220078","display_name":"Iran Journal of Computer Science","issn_l":"2520-8438","issn":["2520-8438","2520-8446"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iran Journal of Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309591","display_name":"Universiti Utara Malaysia","ror":"https://ror.org/01ss10648"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7118065961.pdf","grobid_xml":"https://content.openalex.org/works/W7118065961.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W1594676769","https://openalex.org/W1861492603","https://openalex.org/W2168356304","https://openalex.org/W2176924101","https://openalex.org/W2613825824","https://openalex.org/W2888962714","https://openalex.org/W2962749812","https://openalex.org/W2962777203","https://openalex.org/W2964979676","https://openalex.org/W2980432661","https://openalex.org/W2985384565","https://openalex.org/W2988916019","https://openalex.org/W2989611864","https://openalex.org/W2992240579","https://openalex.org/W2997408160","https://openalex.org/W3013419941","https://openalex.org/W3047737426","https://openalex.org/W3114606989","https://openalex.org/W3122799380","https://openalex.org/W3127366396","https://openalex.org/W3131731103","https://openalex.org/W3138977901","https://openalex.org/W3156982815","https://openalex.org/W3159166099","https://openalex.org/W3160733999","https://openalex.org/W3170019900","https://openalex.org/W3200360746","https://openalex.org/W3201797941","https://openalex.org/W3208123866","https://openalex.org/W3208285567","https://openalex.org/W3208645658","https://openalex.org/W3210586215","https://openalex.org/W3210997132","https://openalex.org/W3215941943","https://openalex.org/W4207064056","https://openalex.org/W4210567611","https://openalex.org/W4214648418","https://openalex.org/W4220676733","https://openalex.org/W4226435487","https://openalex.org/W4229453634","https://openalex.org/W4283717190","https://openalex.org/W4309226255","https://openalex.org/W4319336644","https://openalex.org/W4323351162","https://openalex.org/W4323921464","https://openalex.org/W4362588662","https://openalex.org/W4378222290","https://openalex.org/W4382568144","https://openalex.org/W4384526044","https://openalex.org/W4393273568","https://openalex.org/W4401229097","https://openalex.org/W4405022676","https://openalex.org/W4406047466","https://openalex.org/W4406163781","https://openalex.org/W4407168451","https://openalex.org/W4408220296","https://openalex.org/W4409426948","https://openalex.org/W4410777984"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Small":[1],"object":[2,16,35,87,132,160],"detection":[3,36,243,256],"in":[4,191,206,215,221,240,263],"aerial":[5,264],"images":[6,113],"remains":[7],"a":[8,44,79,195,203,218],"significant":[9],"challenge":[10],"due":[11],"to":[12,84],"low-resolution":[13],"instances,":[14],"sparse":[15],"distribution,":[17],"and":[18,30,63,92,110,117,121,151,162,184,202,258,272],"the":[19,28,141,174,212,224,229,234,237,242,267],"lack":[20],"of":[21,33,60,67,100,173,228,236,244,269],"large,":[22],"diverse":[23],"datasets.":[24,274],"These":[25,247],"limitations":[26,268],"reduce":[27],"accuracy":[29,257],"generalization":[31],"ability":[32],"modern":[34],"algorithms.":[37],"To":[38],"address":[39],"this,":[40],"we":[41,77],"first":[42,105],"propose":[43,78],"three-tier":[45],"systematic":[46,65],"framework":[47],"for":[48,260],"optimizing":[49],"data":[50,80],"augmentation":[51,61,81,252],"strategies,":[52],"which":[53,153],"includes":[54],"(1)":[55],"dataset":[56,90],"analysis,":[57],"(2)":[58],"definition":[59],"objectives,":[62],"(3)":[64],"selection":[66],"techniques":[68],"based":[69],"on":[70,180,200],"identified":[71],"challenges.":[72],"Building":[73],"upon":[74],"this":[75],"framework,":[76],"pipeline":[82,98,175,239],"designed":[83],"enhance":[85],"small":[86,261],"visibility,":[88],"improve":[89],"balance,":[91],"increase":[93,205],"model":[94],"robustness.":[95],"The":[96,104,144,171,186],"proposed":[97,238],"consists":[99],"two":[101,181],"primary":[102],"stages.":[103],"stage":[106,125,146],"performs":[107],"image":[108,149],"segmentation":[109],"cropping,":[111],"dividing":[112],"into":[114],"smaller":[115],"segments":[116,129],"applying":[118],"localized":[119],"zoom-in":[120],"center-cropping":[122],"techniques.":[123],"This":[124],"selectively":[126],"retains":[127],"only":[128,211],"with":[130,166],"high":[131],"density,":[133],"discarding":[134],"empty":[135],"or":[136],"irrelevant":[137],"regions,":[138],"thereby":[139],"increasing":[140],"object-to-image":[142],"ratio.":[143],"second":[145],"involves":[147],"object-centric":[148],"resizing":[150],"augmentation,":[152],"standardizes":[154],"input":[155],"dimensions":[156],"while":[157],"maintaining":[158],"enhanced":[159],"clarity":[161],"scale,":[163],"ensuring":[164],"compatibility":[165],"convolutional":[167],"neural":[168],"networks":[169],"(CNNs).":[170],"effectiveness":[172,235],"is":[176],"validated":[177],"using":[178,208],"YOLOv8m":[179],"datasets":[182],"AI-TODv2":[183,201,216],"SODA-A.":[185],"results":[187,248],"demonstrate":[188],"substantial":[189],"improvements":[190],"performance":[192],"metrics,":[193],"including":[194],"$$+$$":[196],"+":[197],"15.9%":[198],"AP@0.5":[199],"23.6%":[204],"SODA-A":[207],"YOLOv8m.":[209],"But":[210],"class":[213],"\u2018ship\u2019":[214],"showed":[217],"decline.":[219],"Notably,":[220],"both":[222],"datasets,":[223],"average":[225],"precision":[226],"(AP)":[227],"classes":[230],"has":[231],"improved,":[232],"highlighting":[233],"enhancing":[241],"hard-to-detect":[245],"classes.":[246],"confirm":[249],"that":[250],"our":[251],"strategy":[253],"significantly":[254],"improves":[255],"recall":[259],"objects":[262],"scenes,":[265],"overcoming":[266],"sparse,":[270],"dense,":[271],"imbalanced":[273]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-01-03T00:00:00"}