{"id":"https://openalex.org/W2404161323","doi":"https://doi.org/10.1109/icassp.2016.7471891","title":"Scene text recognition with high performance CNN classifier and efficient word inference","display_name":"Scene text recognition with high performance CNN classifier and efficient word inference","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2404161323","doi":"https://doi.org/10.1109/icassp.2016.7471891","mag":"2404161323"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5083694367","display_name":"Xinhao Liu","orcid":"https://orcid.org/0000-0002-5640-1837"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xinhao Liu","raw_affiliation_strings":["NTT Corporation, Kanagawa, Japan 243-0198","NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan 243-0198","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029349765","display_name":"Takahito Kawanishi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahito Kawanishi","raw_affiliation_strings":["NTT Corporation, Kanagawa, Japan 243-0198","NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan 243-0198","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036223449","display_name":"Xiaomeng Wu","orcid":"https://orcid.org/0000-0003-2816-1781"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaomeng Wu","raw_affiliation_strings":["NTT Corporation, Kanagawa, Japan 243-0198","NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan 243-0198","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["NTT Corporation, Kanagawa, Japan 243-0198","NTT Corporation, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan 243-0198","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Kanagawa, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083694367"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.0164,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82838229,"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":"1322","last_page":"1326"},"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":0.9957000017166138,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9940999746322632,"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":0.84922194480896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.747968316078186},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7015944719314575},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6160914301872253},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5966943502426147},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5612890124320984},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4918501377105713},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4842678904533386},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48222458362579346},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4561757743358612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4547343850135803},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4141223430633545},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.4137056767940521},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39601001143455505},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26956605911254883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84922194480896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.747968316078186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7015944719314575},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6160914301872253},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5966943502426147},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5612890124320984},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4918501377105713},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4842678904533386},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48222458362579346},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4561757743358612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4547343850135803},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4141223430633545},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.4137056767940521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39601001143455505},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26956605911254883},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W1521064364","https://openalex.org/W1557952530","https://openalex.org/W1579279110","https://openalex.org/W1607307044","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W1998599144","https://openalex.org/W2048716406","https://openalex.org/W2049951199","https://openalex.org/W2076014259","https://openalex.org/W2122221966","https://openalex.org/W2144506857","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2963718330","https://openalex.org/W2963911037","https://openalex.org/W4213116910","https://openalex.org/W6631165897","https://openalex.org/W6633516429","https://openalex.org/W6636382570","https://openalex.org/W6637242042","https://openalex.org/W6640036494","https://openalex.org/W6649973027","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4384296853","https://openalex.org/W4312612713","https://openalex.org/W2168844671","https://openalex.org/W954954433","https://openalex.org/W2188613573","https://openalex.org/W2218402054","https://openalex.org/W2085262576","https://openalex.org/W2943900795","https://openalex.org/W1762168263","https://openalex.org/W2902204561"],"abstract_inverted_index":{"The":[0],"recognition":[1,35,53,73],"of":[2,42],"text":[3],"in":[4,19],"natural":[5],"scene":[6],"images":[7],"is":[8],"a":[9,31,43],"practical":[10],"yet":[11],"challenging":[12],"task":[13],"due":[14],"to":[15,104],"the":[16,39,52,80,87,96,105],"large":[17],"variations":[18],"backgrounds,":[20],"textures,":[21],"fonts,":[22],"and":[23,66,70,86],"illumination":[24],"conditions.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,55],"propose":[30],"highly":[32],"accurate":[33],"character":[34],"model":[36],"by":[37],"utilizing":[38],"representational":[40],"power":[41],"specially":[44],"designed":[45],"Convolutional":[46],"Neural":[47],"Network":[48],"(CNN).":[49],"Based":[50],"on":[51,75],"model,":[54],"also":[56],"develop":[57],"an":[58],"efficient":[59],"post":[60],"processing":[61],"approach":[62,98],"for":[63],"error":[64],"correction":[65],"hypothesis":[67],"re-verification.":[68],"Character":[69],"word":[71],"image":[72],"experiments":[74],"two":[76],"public":[77],"datasets,":[78],"namely":[79],"ICDAR":[81],"2003":[82],"Robust":[83],"Reading":[84],"dataset":[85,92],"Street":[88],"View":[89],"Text":[90],"(SVT)":[91],"both":[93],"show":[94],"that":[95],"proposed":[97],"provides":[99],"superior":[100],"or":[101],"comparable":[102],"results":[103],"state-of-the-art":[106],"techniques.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}