{"id":"https://openalex.org/W2730200455","doi":"https://doi.org/10.2352/issn.2470-1173.2017.10.imawm-163","title":"Training Object Detection And Recognition CNN Models Using Data Augmentation","display_name":"Training Object Detection And Recognition CNN Models Using Data Augmentation","publication_year":2017,"publication_date":"2017-01-29","ids":{"openalex":"https://openalex.org/W2730200455","doi":"https://doi.org/10.2352/issn.2470-1173.2017.10.imawm-163","mag":"2730200455"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2017.10.imawm-163","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2017.10.imawm-163","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-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/A5081614352","display_name":"Daniel Mas Montserrat","orcid":"https://orcid.org/0000-0002-7946-7724"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Mas Montserrat","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100659445","display_name":"Qian Lin","orcid":"https://orcid.org/0009-0000-7034-7331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043967979","display_name":"Jan P. Allebach","orcid":"https://orcid.org/0000-0001-5608-8249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Allebach","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081614352"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3999,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.93655491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"10","first_page":"27","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8805000185966492,"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":0.8805000185966492,"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":0.8116999864578247,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.7551000118255615,"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/computer-science","display_name":"Computer science","score":0.8431078195571899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7698681950569153},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7456551194190979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6046326160430908},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5642112493515015},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5539132356643677},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5383034944534302},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.5015132427215576},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49797558784484863},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4639887809753418},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4586145877838135},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.45190539956092834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44417813420295715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33094316720962524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431078195571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7698681950569153},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7456551194190979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6046326160430908},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5642112493515015},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5539132356643677},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5383034944534302},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.5015132427215576},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49797558784484863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4639887809753418},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4586145877838135},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.45190539956092834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44417813420295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33094316720962524},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2017.10.imawm-163","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2017.10.imawm-163","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2350336482","https://openalex.org/W2154472250","https://openalex.org/W2229352698","https://openalex.org/W4387272257"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,11,186],"deep":[3],"learning":[4],"methods":[5,85],"has":[6,44],"shown":[7],"that":[8,48,118],"key":[9],"steps":[10],"object":[12,40],"detection":[13,41],"and":[14,21,42,88,108,173,192],"recognition,":[15],"including":[16],"feature":[17],"extraction,":[18],"region":[19],"proposals,":[20],"classification,":[22],"can":[23],"be":[24,52],"done":[25,92],"using":[26,196],"Convolutional":[27],"Neural":[28],"Networks":[29],"(CNN)":[30],"with":[31,167],"high":[32],"accuracy.":[33],"However,":[34],"the":[35,56,61,80,94,119,123,130,134,155,158,168,187],"use":[36,81],"of":[37,55,65,82,114,133,157],"CNNs":[38],"for":[39,69,171],"recognition":[43],"significant":[45],"technical":[46],"challenges":[47],"still":[49],"need":[50],"to":[51,74,97,122,143,153],"addressed.":[53],"One":[54,72],"most":[57],"daunting":[58],"problems":[59],"is":[60,78,117,165,178],"very":[62],"large":[63],"number":[64],"training":[66,95,100,125,159],"images":[67,126],"required":[68],"each":[70],"class/label.":[71],"way":[73],"address":[75],"this":[76,137],"problem":[77],"through":[79],"data":[83,96,115,144,148],"augmentation":[84,116,149],"where":[86],"linear":[87],"nonlinear":[89],"transforms":[90],"are":[91,151],"on":[93,180,200],"create":[98],"\"new\"":[99],"images.":[101],"Typical":[102],"transformations":[103],"include":[104],"spatial":[105],"flipping,":[106],"warping":[107],"other":[109],"deformations.":[110],"An":[111],"important":[112],"concept":[113],"deformations":[120],"applied":[121],"labeled":[124],"do":[127],"not":[128],"change":[129],"semantic":[131],"meaning":[132],"classes/labels.":[135],"In":[136],"paper":[138],"we":[139],"investigate":[140],"several":[141,147],"approaches":[142],"augmentation.":[145],"First,":[146],"techniques":[150],"used":[152],"increase":[154],"size":[156],"dataset.":[160],"Then,":[161],"a":[162,197,201],"Faster":[163],"R-CNN":[164],"trained":[166],"augmented":[169],"dataset":[170],"detect":[172],"recognize":[174],"objects.":[175],"Our":[176],"work":[177],"focused":[179],"two":[181],"different":[182],"scenarios:":[183],"detecting":[184,193],"objects":[185,194],"wild":[188],"(i.e.":[189,204],"commercial":[190],"logos)":[191],"captured":[195],"camera":[198],"mounted":[199],"computer":[202],"system":[203],"toy":[205],"animals).":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}