{"id":"https://openalex.org/W2168011783","doi":"https://doi.org/10.1109/icassp.2002.5745049","title":"Automatic detection and translation of text from natural scenes","display_name":"Automatic detection and translation of text from natural scenes","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2168011783","doi":"https://doi.org/10.1109/icassp.2002.5745049","mag":"2168011783"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745049","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5101445040","display_name":"Jie Yang","orcid":"https://orcid.org/0000-0003-1317-8142"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630815","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-8516-0913"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratory, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101445040"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":4.0364,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92517007,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9984999895095825,"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":0.9865999817848206,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8459199666976929},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.8021281361579895},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.762261152267456},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7460665702819824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6413655281066895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6223698854446411},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.6084093451499939},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5818649530410767},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4637618064880371},{"id":"https://openalex.org/keywords/translation-system","display_name":"Translation system","score":0.4538094997406006},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41975319385528564},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3403320908546448},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.23910704255104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8459199666976929},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.8021281361579895},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.762261152267456},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7460665702819824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6413655281066895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6223698854446411},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.6084093451499939},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5818649530410767},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4637618064880371},{"id":"https://openalex.org/C2992676002","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Translation system","level":3,"score":0.4538094997406006},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41975319385528564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3403320908546448},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.23910704255104065},{"id":"https://openalex.org/C202751555","wikidata":"https://www.wikidata.org/wiki/Q221681","display_name":"In vitro","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745049","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.8981","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.8981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.is.cs.cmu.edu/papers/speech/ICASSP02/icassp02_yang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1480779007","https://openalex.org/W1793478166","https://openalex.org/W1964728295","https://openalex.org/W1972774730","https://openalex.org/W1986434819","https://openalex.org/W1986926502","https://openalex.org/W2002785199","https://openalex.org/W2015880236","https://openalex.org/W2021251814","https://openalex.org/W2057597292","https://openalex.org/W2101627831","https://openalex.org/W2121839820","https://openalex.org/W2141658770","https://openalex.org/W2153624852","https://openalex.org/W2160069326","https://openalex.org/W2293005529","https://openalex.org/W2542201253","https://openalex.org/W3113972711","https://openalex.org/W4241881105","https://openalex.org/W6638215634","https://openalex.org/W6674682957"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3151736118","https://openalex.org/W2110143569","https://openalex.org/W2061528982","https://openalex.org/W2995952208","https://openalex.org/W4223522061","https://openalex.org/W2962700074","https://openalex.org/W2890508380","https://openalex.org/W2112440706","https://openalex.org/W2168011783"],"abstract_inverted_index":{"Large":[0],"amounts":[1],"of":[2,13,31,40,74],"information":[3,18],"are":[4,10],"embedded":[5],"in":[6,26],"natural":[7,14,34],"scenes.":[8,35],"Signs":[9],"good":[11],"examples":[12],"objects":[15],"with":[16],"high":[17],"content.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"discuss":[24],"problems":[25],"automatic":[27,41],"detection":[28,43],"and":[29,44,61,79,82],"translation":[30,56,60,89],"text":[32,42,85],"from":[33],"We":[36,51],"describe":[37],"the":[38,84,106],"chal1enges":[39],"propose":[45],"methods":[46],"to":[47],"address":[48],"these":[49],"chal1enges.":[50],"extend":[52],"example":[53],"based":[54],"machine":[55],"technology":[57],"for":[58,66],"sign":[59,68],"present":[62],"a":[63,94,101],"prototype":[64],"system":[65,71],"Chinese":[67],"translation.":[69],"This":[70],"is":[72],"capable":[73],"capturing":[75],"images,":[76],"automatically":[77],"detecting":[78],"recognizing":[80],"text,":[81],"translating":[83],"into":[86],"English.":[87],"The":[88],"can":[90],"be":[91],"displayed":[92],"on":[93],"palm":[95],"size":[96],"PDA,":[97],"or":[98],"synthesized":[99],"as":[100],"voice":[102],"output":[103],"message":[104],"over":[105],"earphones.":[107]},"counts_by_year":[{"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":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}