{"id":"https://openalex.org/W2910755789","doi":"https://doi.org/10.1145/3292448.3292452","title":"Research on Text Location and Recognition in Natural Images with Deep Learning","display_name":"Research on Text Location and Recognition in Natural Images with Deep Learning","publication_year":2018,"publication_date":"2018-10-06","ids":{"openalex":"https://openalex.org/W2910755789","doi":"https://doi.org/10.1145/3292448.3292452","mag":"2910755789"},"language":"en","primary_location":{"id":"doi:10.1145/3292448.3292452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292448.3292452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Advances in Artificial Intelligence","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/A5100405787","display_name":"Ping Zhang","orcid":"https://orcid.org/0000-0002-0269-104X"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ping Zhang","raw_affiliation_strings":["Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008998270","display_name":"Ziyu Shi","orcid":"https://orcid.org/0000-0001-5411-575X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Shi","raw_affiliation_strings":["Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086029723","display_name":"Haichang Gao","orcid":"https://orcid.org/0000-0002-4969-5718"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichang Gao","raw_affiliation_strings":["Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China"],"affiliations":[{"raw_affiliation_string":"Institute of Software Engineering, Xidian University, Xi'an, Shaanxi, P.R.China","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100405787"],"corresponding_institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.2089,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.57776601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"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":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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9976000189781189,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9961000084877014,"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":0.8390741944313049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7619575262069702},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6089465618133545},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5863951444625854},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5801962018013},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5780527591705322},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5392746925354004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5102512836456299},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4913384020328522},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4722038209438324},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4712919294834137},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4691801369190216},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46689900755882263},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4229242503643036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39980846643447876},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38657188415527344},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25152578949928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390741944313049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7619575262069702},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6089465618133545},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5863951444625854},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5801962018013},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5780527591705322},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5392746925354004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5102512836456299},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4913384020328522},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4722038209438324},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4712919294834137},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4691801369190216},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46689900755882263},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4229242503643036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39980846643447876},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38657188415527344},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25152578949928284},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292448.3292452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3292448.3292452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Advances in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1924985727","https://openalex.org/W1988461287","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2599765304","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2613718673","https://openalex.org/W2777652944","https://openalex.org/W2784050770","https://openalex.org/W2949650786","https://openalex.org/W2951285986","https://openalex.org/W2952365771","https://openalex.org/W2953106684","https://openalex.org/W2962790387","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W3106250896","https://openalex.org/W6687483927","https://openalex.org/W6736305252","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W3164639770","https://openalex.org/W4312612713","https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W4383748232","https://openalex.org/W4387168087","https://openalex.org/W3107028621","https://openalex.org/W161774015","https://openalex.org/W3016798175"],"abstract_inverted_index":{"The":[0],"location":[1,29,79,87,93],"and":[2,28,43,56,80,110,121,132],"recognition":[3,130],"of":[4,38],"scene":[5,18,31,47,77,91],"text":[6,19,32,48,78,92],"has":[7],"been":[8],"a":[9],"difficult":[10,61],"topic":[11],"in":[12,129],"many":[13],"computer":[14],"vision":[15],"applications.":[16],"In":[17,67],"location,":[20],"which":[21],"differ":[22],"from":[23,35],"the":[24,39,50,65,84,90,115,122],"general":[25,85],"objects":[26,86],"detection":[27],"task,":[30],"always":[33],"suffers":[34],"large":[36],"variances":[37],"aspect":[40],"ratio,":[41],"scale,":[42],"orientation.":[44],"As":[45],"for":[46],"recognition,":[49],"changing":[51],"character":[52],"types,":[53],"sharpness,":[54],"sizes,":[55],"font":[57],"families":[58],"make":[59],"it":[60],"to":[62,89],"accurately":[63],"recognize":[64],"text.":[66],"this":[68],"paper,":[69],"we":[70],"have":[71],"carried":[72],"out":[73],"work":[74],"on":[75,101,118],"both":[76,128],"recognition.":[81],"We":[82,95],"apply":[83],"methods":[88],"task.":[94],"use":[96],"two":[97],"methods,":[98],"one":[99],"based":[100,117],"Convolutional":[102],"Neural":[103,107],"Network":[104,108],"(CNN),":[105],"Recurrent":[106],"(RNN)":[109],"Connectionist":[111],"Temporal":[112],"Classifier":[113],"(CTC),":[114],"other":[116],"CNN,":[119],"RNN":[120],"Attention":[123],"mechanism.":[124],"They":[125],"perform":[126],"well":[127],"speed":[131],"accuracy":[133],"rate":[134],"compared":[135],"with":[136],"previous":[137],"methods.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}