{"id":"https://openalex.org/W3004229189","doi":"https://doi.org/10.1117/12.2557064","title":"Synthetic images generation for text detection and recognition in the wild","display_name":"Synthetic images generation for text detection and recognition in the wild","publication_year":2020,"publication_date":"2020-01-31","ids":{"openalex":"https://openalex.org/W3004229189","doi":"https://doi.org/10.1117/12.2557064","mag":"3004229189"},"language":"en","primary_location":{"id":"doi:10.1117/12.2557064","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2557064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twelfth International Conference on Machine Vision (ICMV 2019)","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/A5000954819","display_name":"Natalia Khanzhina","orcid":"https://orcid.org/0000-0003-0795-642X"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Natalia Khanzhina","raw_affiliation_strings":["ITMO Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"ITMO Univ. (Russian Federation)","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075035430","display_name":"Natalia Slepkova","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Natalia Slepkova","raw_affiliation_strings":["ITMO Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"ITMO Univ. (Russian Federation)","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112028318","display_name":"Andrey Filchenkov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Filchenkov","raw_affiliation_strings":["ITMO Univ. (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"ITMO Univ. (Russian Federation)","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000954819"],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35650669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9739999771118164,"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/T11448","display_name":"Face recognition and analysis","score":0.972000002861023,"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":0.8011566996574402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6935187578201294},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6532878279685974},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5988195538520813},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5934217572212219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49336257576942444},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48419860005378723},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4557388424873352},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3940795660018921},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.370184063911438},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2260816991329193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011566996574402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6935187578201294},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6532878279685974},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5988195538520813},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5934217572212219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49336257576942444},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48419860005378723},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4557388424873352},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3940795660018921},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.370184063911438},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2260816991329193}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2557064","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2557064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Twelfth International Conference on Machine Vision (ICMV 2019)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W4375867731","https://openalex.org/W2387011115","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Deep":[0],"neural":[1,33,86],"networks":[2,87],"help":[3],"solving":[4],"different":[5,43],"images":[6,69,106],"related":[7],"tasks":[8],"very":[9],"efficiently,":[10],"though":[11],"their":[12],"cost":[13],"is":[14,27],"high":[15],"whereas":[16],"a":[17,28],"lot":[18],"of":[19,121],"data":[20],"are":[21,55],"required":[22],"for":[23,36,42,47,67],"training.":[24],"While":[25],"there":[26],"great":[29],"demand":[30],"to":[31,98],"build":[32],"network":[34],"models":[35],"optical":[37],"character":[38],"detection":[39],"and":[40,53,77,109],"recognition":[41],"languages,":[44],"such":[45],"as,":[46],"mobile":[48],"real-time":[49],"applications,":[50],"datasets":[51,111],"collecting":[52],"labeling":[54],"quite":[56],"expensive.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,83],"propose":[62],"the":[63,89,100],"fully":[64],"automated":[65],"approach":[66,96],"synthetic":[68],"with":[70,114],"text":[71],"generation":[72],"based":[73],"on":[74,88,104,116],"deep":[75],"learning":[76],"projective":[78],"geometry":[79],"methods.":[80],"For":[81],"evaluation,":[82],"trained":[84],"two":[85],"dataset":[90],"generated":[91],"by":[92],"our":[93],"algorithm.":[94],"Our":[95],"enables":[97],"decrease":[99],"false":[101],"negative":[102],"rate":[103],"real":[105],"from":[107],"SVT":[108],"SVT-50":[110],"in":[112],"comparison":[113],"training":[115],"SynthText":[117],"dataset,":[118],"giving":[119],"~1%":[120],"F<sub>1</sub>-measure":[122],"increasing.":[123]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}