{"id":"https://openalex.org/W2086838552","doi":"https://doi.org/10.1109/icassp.2014.6853796","title":"Text detection and recognition in natural scenes and consumer videos","display_name":"Text detection and recognition in natural scenes and consumer videos","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2086838552","doi":"https://doi.org/10.1109/icassp.2014.6853796","mag":"2086838552"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086355248","display_name":"Arpit Jain","orcid":"https://orcid.org/0000-0002-3158-7305"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arpit Jain","raw_affiliation_strings":["College Park in Electrical and Computer Engineering Department, University of Maryland","Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College Park in Electrical and Computer Engineering Department, University of Maryland","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102329211","display_name":"Xujun Peng","orcid":"https://orcid.org/0000-0001-9373-7092"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xujun Peng","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102227196","display_name":"Pradeep Natarajan","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradeep Natarajan","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Language & Multimedia Bus. Unit Raytheon BBN Technol., Speech, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.798,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91148733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1249"},"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":0.9983000159263611,"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":0.9980000257492065,"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":0.7857616543769836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7594934105873108},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6468345522880554},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6254912614822388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6130223274230957},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.5779767036437988},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5116980075836182},{"id":"https://openalex.org/keywords/histogram-of-oriented-gradients","display_name":"Histogram of oriented gradients","score":0.49776938557624817},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.48193883895874023},{"id":"https://openalex.org/keywords/gabor-filter","display_name":"Gabor filter","score":0.43536508083343506},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4215397238731384},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42011114954948425},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3546953797340393},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3060946464538574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.28449389338493347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857616543769836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7594934105873108},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6468345522880554},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6254912614822388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6130223274230957},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.5779767036437988},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5116980075836182},{"id":"https://openalex.org/C17426736","wikidata":"https://www.wikidata.org/wiki/Q419918","display_name":"Histogram of oriented gradients","level":4,"score":0.49776938557624817},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.48193883895874023},{"id":"https://openalex.org/C2779883129","wikidata":"https://www.wikidata.org/wiki/Q2447890","display_name":"Gabor filter","level":3,"score":0.43536508083343506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4215397238731384},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42011114954948425},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3546953797340393},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3060946464538574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28449389338493347},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":24,"referenced_works":["https://openalex.org/W1547848520","https://openalex.org/W1998042868","https://openalex.org/W2001642682","https://openalex.org/W2017278151","https://openalex.org/W2018451638","https://openalex.org/W2023415694","https://openalex.org/W2025871304","https://openalex.org/W2027883219","https://openalex.org/W2050036944","https://openalex.org/W2061802763","https://openalex.org/W2091696127","https://openalex.org/W2104606180","https://openalex.org/W2111308925","https://openalex.org/W2133059825","https://openalex.org/W2142159465","https://openalex.org/W2145023731","https://openalex.org/W2153635508","https://openalex.org/W2161969291","https://openalex.org/W2901992801","https://openalex.org/W2917663306","https://openalex.org/W6632893558","https://openalex.org/W6675436802","https://openalex.org/W6680597956","https://openalex.org/W6681153094"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W2539884462"],"abstract_inverted_index":{"We":[0,71,124],"propose":[1],"an":[2],"end-to-end":[3],"system":[4,90,121,147],"for":[5,68,91,100,122],"text":[6,31,129],"detection":[7,130,146,171],"and":[8,13,25,45,54,79,109,131],"recognition":[9,132],"in":[10,128,162],"natural":[11],"scenes":[12],"consumer":[14,140],"videos.":[15],"Maximally":[16],"Stable":[17],"Extremal":[18],"Regions":[19],"which":[20],"are":[21,28,48,106],"robust":[22],"to":[23,50,82,111],"illumination":[24],"viewpoint":[26],"variations":[27],"selected":[29],"as":[30,37,65],"candidates.":[32],"Rich":[33],"shape":[34],"descriptors":[35],"such":[36],"Histogram":[38],"of":[39,153],"Oriented":[40],"Gradients,":[41],"Gabor":[42],"filter,":[43],"corners":[44],"geometrical":[46],"features":[47],"used":[49],"represent":[51],"the":[52,89,144,150,163],"candidates":[53,63],"classified":[55],"using":[56],"a":[57,112,138],"support":[58],"vector":[59],"machine.":[60],"Positively":[61],"labeled":[62],"serve":[64],"anchor":[66],"regions":[67,75],"word":[69,84],"formation.":[70],"then":[72],"group":[73],"candidate":[74],"based":[76,116,160],"on":[77,137],"geometric":[78],"color":[80],"properties":[81],"form":[83],"boundaries.":[85],"To":[86],"speed":[87],"up":[88],"practical":[92],"applications,":[93],"we":[94],"use":[95],"Partial":[96],"Least":[97],"Squares":[98],"approach":[99,155],"dimensionality":[101],"reduction.":[102],"The":[103],"detected":[104],"words":[105],"binarized,":[107],"filtered":[108],"passed":[110],"hidden":[113],"Markov":[114],"model":[115],"Optical":[117],"Character":[118],"Recognition":[119],"(OCR)":[120],"recognition.":[123],"show":[125],"significant":[126],"improvement":[127],"tasks":[133],"over":[134],"previous":[135],"approaches":[136],"large":[139],"video":[141],"dataset.":[142],"Furthermore,":[143],"event":[145,170],"built":[148],"upon":[149],"OCR":[151],"output":[152],"this":[154],"outperformed":[156],"multiple":[157],"other":[158],"OCR-only":[159],"submissions":[161],"recently":[164],"concluded":[165],"NIST":[166],"TRECVID":[167],"2013":[168],"multimedia":[169],"evaluations.":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}