{"id":"https://openalex.org/W4200141299","doi":"https://doi.org/10.1109/ispacs51563.2021.9651028","title":"Study on Mask R-CNN with Data Augmentation for Retail Product Detection","display_name":"Study on Mask R-CNN with Data Augmentation for Retail Product Detection","publication_year":2021,"publication_date":"2021-11-16","ids":{"openalex":"https://openalex.org/W4200141299","doi":"https://doi.org/10.1109/ispacs51563.2021.9651028"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs51563.2021.9651028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs51563.2021.9651028","pdf_url":null,"source":{"id":"https://openalex.org/S4363605678","display_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"},"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/A5027244750","display_name":"Matthew Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Kuo","raw_affiliation_strings":["Taipei American School, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taipei American School, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104097560","display_name":"Hung-Tse Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I75430998","display_name":"National Ilan University","ror":"https://ror.org/01npf0s58","country_code":"TW","type":"education","lineage":["https://openalex.org/I75430998"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Tse Chan","raw_affiliation_strings":["Dept. of Computer Scinece and Information Engineering, National Ilan University, Yilan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Scinece and Information Engineering, National Ilan University, Yilan, Taiwan","institution_ids":["https://openalex.org/I75430998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070037368","display_name":"Chih\u2010Hsien Hsia","orcid":"https://orcid.org/0000-0003-2665-0821"},"institutions":[{"id":"https://openalex.org/I75430998","display_name":"National Ilan University","ror":"https://ror.org/01npf0s58","country_code":"TW","type":"education","lineage":["https://openalex.org/I75430998"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Hsien Hsia","raw_affiliation_strings":["Dept. of Computer Scinece and Information Engineering, National Ilan University, Yilan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Scinece and Information Engineering, National Ilan University, Yilan, Taiwan","institution_ids":["https://openalex.org/I75430998"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5908,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79340974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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":0.9986000061035156,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12707","display_name":"Vehicle License Plate Recognition","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7864075899124146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.760398268699646},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.637704610824585},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6323976516723633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49226561188697815},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.483862042427063},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4680195748806},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46068552136421204},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.42901816964149475},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4194068908691406},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.4149951636791229},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4134475588798523},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.40843576192855835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10682052373886108},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09464731812477112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864075899124146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.760398268699646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.637704610824585},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6323976516723633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49226561188697815},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.483862042427063},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4680195748806},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46068552136421204},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.42901816964149475},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4194068908691406},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.4149951636791229},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4134475588798523},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.40843576192855835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10682052373886108},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09464731812477112},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispacs51563.2021.9651028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs51563.2021.9651028","pdf_url":null,"source":{"id":"https://openalex.org/S4363605678","display_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2768444794","https://openalex.org/W2963150697","https://openalex.org/W2974020870","https://openalex.org/W3000326606","https://openalex.org/W3091780000","https://openalex.org/W6687483927","https://openalex.org/W6730903564"],"related_works":["https://openalex.org/W2181570714","https://openalex.org/W1581632702","https://openalex.org/W2901758161","https://openalex.org/W3204852000","https://openalex.org/W2336272890","https://openalex.org/W3211418293","https://openalex.org/W325114128","https://openalex.org/W4308999381","https://openalex.org/W4308999963","https://openalex.org/W4285815683"],"abstract_inverted_index":{"In":[0,105],"deep":[1],"learning":[2],"(DL),":[3],"object":[4,83],"detection":[5,20,84],"is":[6],"a":[7,27,121],"computer":[8],"vision":[9],"technology":[10],"that":[11],"can":[12,115],"be":[13],"applied":[14],"in":[15,85,125],"many":[16],"fields,":[17],"including":[18],"face":[19],"and":[21,54],"tracking":[22],"the":[23,69,82,93,109,126,131],"soccer":[24],"ball":[25],"during":[26],"match.":[28],"Previously,":[29],"when":[30],"dealing":[31],"with":[32,44,61,76,120],"detecting":[33],"objects":[34,58,60,98,101],"from":[35,68],"small":[36],"retail":[37,86],"stores,":[38],"most":[39],"studies":[40],"used":[41],"Faster":[42],"R-CNN":[43,75],"ResNet101":[45],"as":[46],"its":[47],"backbone.":[48],"However,":[49],"this":[50,106],"method":[51,111],"sometimes":[52],"incorrectly":[53],"ineffectively":[55],"identifies":[56],"overlapped":[57,97],"or":[59,99],"parts":[62],"of":[63,118],"their":[64],"edges":[65],"cut":[66],"off":[67],"image.":[70],"This":[71],"paper":[72],"use":[73],"Mask":[74],"data":[77],"augmentation":[78],"(DA)":[79],"to":[80,91,130],"perform":[81],"product":[87],"recognition.":[88],"We":[89],"seek":[90],"minimalize":[92],"error":[94],"caused":[95],"by":[96],"adjacent":[100],"having":[102],"similar":[103],"colors.":[104],"experiment":[107],"result,":[108],"proposed":[110],"on":[112],"Snacks":[113],"dataset":[114],"achieve":[116],"mAP":[117],"98.92%":[119],"superior":[122],"recognition":[123,127],"rate":[124],"task":[128],"compared":[129],"state-of-the-art":[132],"methods.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}