{"id":"https://openalex.org/W2747189008","doi":"https://doi.org/10.1145/3095713.3095724","title":"A Robust Ensemble of ResNets for Character Level End-to-end Text Detection in Natural Scene Images","display_name":"A Robust Ensemble of ResNets for Character Level End-to-end Text Detection in Natural Scene Images","publication_year":2017,"publication_date":"2017-06-19","ids":{"openalex":"https://openalex.org/W2747189008","doi":"https://doi.org/10.1145/3095713.3095724","mag":"2747189008"},"language":"en","primary_location":{"id":"doi:10.1145/3095713.3095724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3095713.3095724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing","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/A5100746306","display_name":"Jinsu Kim","orcid":"https://orcid.org/0000-0002-6739-2833"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinsu Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015878311","display_name":"Yoonhyung Kim","orcid":"https://orcid.org/0000-0002-5608-8473"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonhyung Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changick Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daehak-ro, Yuseong-gu, Daejeon","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100746306"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10801711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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/character","display_name":"Character (mathematics)","score":0.8643462657928467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8050806522369385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7221850156784058},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6422519087791443},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6397233009338379},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4696822762489319},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4592764973640442},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.4431692361831665},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4418284595012665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39842838048934937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11210596561431885}],"concepts":[{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.8643462657928467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050806522369385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7221850156784058},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6422519087791443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6397233009338379},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4696822762489319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4592764973640442},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.4431692361831665},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4418284595012665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39842838048934937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11210596561431885},{"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:10.1145/3095713.3095724","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3095713.3095724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W117491841","https://openalex.org/W1607307044","https://openalex.org/W1686810756","https://openalex.org/W1935817682","https://openalex.org/W2008806374","https://openalex.org/W2061052400","https://openalex.org/W2078997308","https://openalex.org/W2083954025","https://openalex.org/W2124404372","https://openalex.org/W2142159465","https://openalex.org/W2148214126","https://openalex.org/W2152322845","https://openalex.org/W2194775991","https://openalex.org/W2217433794","https://openalex.org/W2468724597","https://openalex.org/W2472159136"],"related_works":["https://openalex.org/W4251972423","https://openalex.org/W1503216044","https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W1482912984"],"abstract_inverted_index":{"Detecting":[0],"text":[1,18,27,35,37,40,177],"in":[2,21],"natural":[3,22],"scene":[4,23],"images":[5,110],"is":[6,120,135],"a":[7,15],"challenging":[8],"task.":[9],"In":[10,25,88,152],"this":[11],"paper,":[12],"we":[13],"propose":[14],"character-level":[16],"end-to-end":[17],"detection":[19,28,178],"algorithm":[20],"images.":[24],"general,":[26],"tasks":[29,58],"are":[30,98,145,163,182],"categorized":[31],"into":[32,122],"three":[33,138],"parts:":[34],"localization,":[36],"segmentation,":[38],"and":[39,80,111],"recognition.":[41],"The":[42,188],"proposed":[43,61,189],"method":[44,62,190],"aims":[45],"not":[46],"only":[47],"to":[48,52,154,165],"localize":[49],"but":[50],"also":[51],"recognize":[53],"text.":[54],"To":[55,174],"do":[56],"these":[57],"successfully,":[59],"the":[60,89,101,131,170,176,195],"consists":[63],"of":[64,75,137,158,169,172],"four":[65],"steps:":[66],"character":[67,81,90,95,124,161,180],"candidate":[68,91,96],"patch":[69,71,92,119,125,128],"extraction,":[70],"classification":[72,159,167],"using":[73,104,130],"ensemble":[74,171],"ResNets,":[76],"non-character":[77,127,150],"region":[78,82],"elimination,":[79],"grouping":[83],"via":[84,184],"self-tuning":[85,185],"spectral":[86,186],"clustering.":[87,187],"extraction":[93],"step,":[94],"patches":[97],"extracted":[99],"from":[100,108],"image":[102],"by":[103,129,147],"both":[105],"edge":[106],"information":[107],"multi-scale":[109],"Maximally":[112],"Stable":[113],"Extremal":[114],"Regions":[115],"(MSERs).":[116],"Then":[117],"each":[118],"classified":[121],"either":[123],"or":[126],"deep":[132],"network":[133],"that":[134],"composed":[136],"ResNets":[139],"with":[140],"different":[141],"hyper-parameters.":[142],"Text":[143],"regions":[144,181],"determined":[146],"filtering":[148],"out":[149],"patches.":[151],"order":[153],"make":[155],"further":[156],"reduction":[157],"errors,":[160],"characteristics":[162],"employed":[164],"compensate":[166],"results":[168],"ResNets.":[173],"evaluate":[175],"performance,":[179],"grouped":[183],"shows":[191],"competitive":[192],"performance":[193],"on":[194],"ICDAR":[196],"2013":[197],"dataset.":[198]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}