{"id":"https://openalex.org/W7225820039","doi":"https://doi.org/10.21203/rs.3.rs-11681786/v1","title":"A Mobile-Centric Comparative Evaluation of Deep Learning Models for Real-Time Flower Recognition","display_name":"A Mobile-Centric Comparative Evaluation of Deep Learning Models for Real-Time Flower Recognition","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225820039","doi":"https://doi.org/10.21203/rs.3.rs-11681786/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11681786/v1","doi":"https://doi.org/10.21203/rs.3.rs-11681786/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11681786/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11681786/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157981694","display_name":"Fatemeh Sabourinia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fatemeh Sabourinia","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0009-7681-5170","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157923851","display_name":"Alireza Zaeri","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alireza Zaeri","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0006-4836-4358","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024631330","display_name":"Vahid Abolghasemi","orcid":"https://orcid.org/0000-0002-2151-5180","observed_orcids":["https://orcid.org/0000-0002-2151-5180"]},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vahid Abolghasemi","raw_affiliation_strings":["University of Essex"],"raw_orcid":"https://orcid.org/0000-0002-2151-5180","affiliations":[{"raw_affiliation_string":"University of Essex","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5157981694"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9980000257492065,"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":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.732699990272522},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116999983787537},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5175999999046326},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11681786/v1","doi":"https://doi.org/10.21203/rs.3.rs-11681786/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11681786/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11681786/v1","doi":"https://doi.org/10.21203/rs.3.rs-11681786/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11681786/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Flower":[1],"recognition":[2,39,222],"has":[3],"important":[4],"applications":[5],"in":[6,45],"education,":[7],"agriculture,":[8],"and":[9,49,70,78,137,152,183,213,219],"intelligent":[10],"mobile":[11,31,165],"systems.":[12],"However,":[13],"previous":[14],"studies":[15],"have":[16],"primarily":[17],"focused":[18],"on":[19,85,121,192],"classification":[20,68,127],"accuracy,":[21],"with":[22,109],"less":[23],"attention":[24],"to":[25,63,81,171,180,203],"the":[26,46,86,141,145,159],"joint":[27],"requirements":[28],"of":[29,52,156],"real-time":[30],"deployment.":[32],"This":[33],"study":[34],"presents":[35],"a":[36,93,105,122,153],"mobile-centric":[37],"flower":[38,221],"framework":[40],"whose":[41],"technical":[42],"contribution":[43],"lies":[44],"dataset-specific":[47,210],"adaptation":[48,212],"deployment-oriented":[50,214],"evaluation":[51],"established":[53],"learning":[54,83],"architectures.":[55],"Rather":[56],"than":[57],"applying":[58],"an":[59,110,186],"identical":[60],"transfer-learning":[61],"configuration":[62],"all":[64],"convolutional":[65],"models,":[66],"architecture-specific":[67],"heads":[69],"training":[71,131],"strategies":[72],"were":[73,119],"developed":[74],"for":[75,164],"VGG16,":[76],"NASNet-Mobile,":[77],"MobileNetV2":[79,107,147],"according":[80],"their":[82],"behaviour":[84],"Oxford":[87],"102":[88],"Flowers":[89],"dataset.":[90],"In":[91],"addition,":[92],"hybrid":[94],"MobileNetV2\u2013XGBoost":[95],"pipeline":[96],"was":[97,168],"constructed":[98],"by":[99],"combining":[100],"deep":[101],"features":[102],"extracted":[103],"from":[104,177,201],"pretrained":[106],"backbone":[108],"independently":[111],"optimised":[112],"XGBoost":[113],"classifier.":[114],"The":[115],"four":[116],"resulting":[117],"pipelines":[118],"evaluated":[120],"common":[123],"data":[124],"split":[125],"using":[126],"performance,":[128],"inference":[129],"time,":[130,132],"model":[133,211],"size,":[134],"architectural":[135],"complexity,":[136],"deployment":[138],"feasibility.":[139],"On":[140],"2,539-image":[142],"test":[143],"set,":[144],"adapted":[146],"achieved":[148],"approximately":[149],"96%":[150],"accuracy":[151],"weighted":[154],"F1-score":[155],"0.96,":[157],"providing":[158],"most":[160],"suitable":[161],"overall":[162],"trade-off":[163],"use.":[166],"It":[167],"subsequently":[169],"converted":[170],"TensorFlow":[172],"Lite,":[173],"reducing":[174],"its":[175],"size":[176],"27.74":[178],"MB":[179],"2.53":[181],"MB,":[182],"integrated":[184],"into":[185],"offline":[187],"Android":[188,194],"application.":[189],"Repeated":[190],"measurements":[191],"physical":[193],"devices":[195],"produced":[196],"mean":[197],"preprocessing-plus-inference":[198],"latencies":[199],"ranging":[200],"55.57":[202],"68.11":[204],"ms.":[205],"These":[206],"results":[207],"demonstrate":[208],"that":[209],"selection":[215],"can":[216],"enable":[217],"accurate":[218],"responsive":[220],"without":[223],"cloud-based":[224],"processing.":[225]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}