{"id":"https://openalex.org/W2964226591","doi":"https://doi.org/10.1109/vcip.2016.7805444","title":"A novel scene text detection algorithm based on convolutional neural network","display_name":"A novel scene text detection algorithm based on convolutional neural network","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2964226591","doi":"https://doi.org/10.1109/vcip.2016.7805444","mag":"2964226591"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2016.7805444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2016.7805444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Visual Communications and Image Processing (VCIP)","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/A5088322622","display_name":"Xiaohang Ren","orcid":"https://orcid.org/0000-0002-6223-0667"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohang Ren","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704070","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-3982-9145"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014610561","display_name":"Jianhua He","orcid":"https://orcid.org/0000-0002-5738-8507"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua He","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100327195","display_name":"Jun Sun","orcid":"https://orcid.org/0000-0002-0967-4859"},"institutions":[{"id":"https://openalex.org/I169199633","display_name":"Aston University","ror":"https://ror.org/05j0ve876","country_code":"GB","type":"education","lineage":["https://openalex.org/I169199633"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Sun","raw_affiliation_strings":["School of Engineering and Applied Science, Aston University"],"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Science, Aston University","institution_ids":["https://openalex.org/I169199633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088322622"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6779,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79332859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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":0.9962999820709229,"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":0.7501886487007141},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.734302282333374},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.697014331817627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6553314924240112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6364104747772217},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5846718549728394},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4878954589366913},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4205837845802307},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32122623920440674},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1581789255142212},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.071910560131073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501886487007141},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.734302282333374},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.697014331817627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6553314924240112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6364104747772217},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5846718549728394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4878954589366913},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4205837845802307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32122623920440674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1581789255142212},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.071910560131073},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/vcip.2016.7805444","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2016.7805444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:discovery.dundee.ac.uk:openaire_cris_publications/a7a34f85-a6bc-404d-b300-ef646d9fba0f","is_oa":false,"landing_page_url":"https://discovery.dundee.ac.uk/en/publications/a7a34f85-a6bc-404d-b300-ef646d9fba0f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400523","display_name":"Discovery Research Portal (University of Dundee)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177639307","host_organization_name":"University of Dundee","host_organization_lineage":["https://openalex.org/I177639307"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ren, X, Chen, K, Yang, X, Zhou, Y, He, J & Sun, J 2017, A novel scene text detection algorithm based on convolutional neural network. in 2016 Visual Communication and Image Processing (VCIP)., 7805444, IEEE, pp. 1-4, 2016 IEEE Visual Communication and Image Processing, VCIP 2016, Chengdu, China, 27/11/16. https://doi.org/10.1109/VCIP.2016.7805444","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:discovery.dundee.ac.uk:publications/a7a34f85-a6bc-404d-b300-ef646d9fba0f","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85011051633&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306400523","display_name":"Discovery Research Portal (University of Dundee)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177639307","host_organization_name":"University of Dundee","host_organization_lineage":["https://openalex.org/I177639307"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ren, X, Chen, K, Yang, X, Zhou, Y, He, J & Sun, J 2017, A novel scene text detection algorithm based on convolutional neural network. in 2016 Visual Communication and Image Processing (VCIP)., 7805444, IEEE, pp. 1-4, 2016 IEEE Visual Communication and Image Processing, VCIP 2016, Chengdu, China, 27/11/16. https://doi.org/10.1109/VCIP.2016.7805444","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W117491841","https://openalex.org/W1539000009","https://openalex.org/W1607307044","https://openalex.org/W1976382093","https://openalex.org/W2001999290","https://openalex.org/W2008806374","https://openalex.org/W2014286161","https://openalex.org/W2061802763","https://openalex.org/W2078997308","https://openalex.org/W2124404372","https://openalex.org/W2131447359","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2163605009","https://openalex.org/W6636382570","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W1979583797","https://openalex.org/W3082848404","https://openalex.org/W4293226380","https://openalex.org/W2372254676","https://openalex.org/W2793679056","https://openalex.org/W2080135837","https://openalex.org/W4283332091","https://openalex.org/W3145050838","https://openalex.org/W3141979996","https://openalex.org/W2604380918"],"abstract_inverted_index":{"Candidate":[0],"text":[1,14,28,34,41,64,75,90,139,143],"region":[2,35,42],"extraction":[3],"plays":[4],"a":[5,24,32,104],"critical":[6],"role":[7],"in":[8],"convolutional":[9],"neural":[10],"network":[11],"(CNN)":[12],"based":[13,26,46,146],"detection":[15,29,144,161],"from":[16,103],"natural":[17],"images.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"CNN":[25,121],"scene":[27],"algorithm":[30,145],"with":[31,151],"new":[33,142],"extractor.":[36],"The":[37,86,141],"so":[38],"called":[39],"candidate":[40,63,89],"extractor":[43],"I-MSER":[44,68,94,137,148],"is":[45,69,95,108,123,149],"on":[47,147],"Maximally":[48],"Stable":[49],"Extremal":[50],"Region":[51],"(MSER),":[52],"which":[53,107],"can":[54],"improve":[55],"the":[56,61,72,99,112,117,127,131,136,165],"independency":[57,87],"and":[58,80,155,158],"completeness":[59],"of":[60,67,88,130],"extracted":[62,132,134],"regions.":[65],"Design":[66],"motivated":[70],"by":[71,93,97,135],"observation":[73],"that":[74],"MSERs":[76],"have":[77],"high":[78],"similarity":[79],"are":[81],"close":[82],"to":[83,111,125,164],"each":[84],"other.":[85],"regions":[91,102,133],"obtained":[92],"guaranteed":[96],"selecting":[98],"most":[100],"representative":[101],"MSER":[105],"tree":[106],"generated":[109],"according":[110],"spatial":[113],"overlapping":[114],"relationship":[115],"among":[116],"MSERs.":[118],"A":[119],"multi-layer":[120],"model":[122],"trained":[124],"score":[126],"confidence":[128],"value":[129],"for":[138],"detection.":[140],"evaluated":[150],"wide-used":[152],"ICDAR":[153],"2011":[154],"2013":[156],"datasets":[157],"shows":[159],"improved":[160],"performance":[162],"compared":[163],"existing":[166],"algorithms.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}