{"id":"https://openalex.org/W2122279599","doi":"https://doi.org/10.1109/icassp.2008.4517870","title":"Multi-frame combination for robust videotext recognition","display_name":"Multi-frame combination for robust videotext recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2122279599","doi":"https://doi.org/10.1109/icassp.2008.4517870","mag":"2122279599"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4517870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517870","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5107484450","display_name":"Rohit Prasad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Prasad","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113479110","display_name":"Shirin Saleem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shirin Saleem","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044398772","display_name":"Ehry MacRostie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehry MacRostie","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029617574","display_name":"M. Decerbo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Decerbo","raw_affiliation_strings":["BBN Technologies, GTE, Cambridge, MA, USA","BBN Technol., Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, GTE, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"BBN Technol., Cambridge, MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5213,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59762167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1357","last_page":"1360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9966999888420105,"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":0.9927999973297119,"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":0.8483592867851257},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7446552515029907},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7062541246414185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6596072912216187},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5962790846824646},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.567220151424408},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.55979323387146},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5083169341087341},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4697053134441376},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46252259612083435},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46002569794654846},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4425172209739685},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4202212989330292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39938676357269287},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2948276400566101},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10411286354064941},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06519126892089844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483592867851257},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7446552515029907},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7062541246414185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6596072912216187},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5962790846824646},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.567220151424408},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.55979323387146},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5083169341087341},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4697053134441376},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46252259612083435},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46002569794654846},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4425172209739685},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4202212989330292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39938676357269287},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2948276400566101},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10411286354064941},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06519126892089844},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/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.2008.4517870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4517870","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W173561343","https://openalex.org/W1508883895","https://openalex.org/W1571931074","https://openalex.org/W1904457459","https://openalex.org/W2050036944","https://openalex.org/W2090874155","https://openalex.org/W2103127925","https://openalex.org/W2918078540","https://openalex.org/W4285719527","https://openalex.org/W6607114211","https://openalex.org/W6631036137"],"related_works":["https://openalex.org/W2106922437","https://openalex.org/W2807901368","https://openalex.org/W2158491338","https://openalex.org/W2149402184","https://openalex.org/W2013767392","https://openalex.org/W2892857623","https://openalex.org/W3190162935","https://openalex.org/W2595338207","https://openalex.org/W1973075426","https://openalex.org/W2997809463"],"abstract_inverted_index":{"Optical":[0],"character":[1,141],"recognition":[2,94],"(OCR)":[3],"of":[4,21,67,102],"overlaid":[5,37],"text":[6,38,104],"in":[7,108,152],"video":[8,29],"streams":[9],"is":[10,114,128],"a":[11,35,77,103,123,162],"challenging":[12],"problem":[13],"due":[14],"to":[15,75,95,121],"various":[16],"factors":[17],"including":[18],"the":[19,47,87,109,153],"presence":[20],"dynamic":[22],"backgrounds,":[23],"color,":[24],"and":[25],"low":[26],"resolution.":[27],"In":[28,54],"feeds":[30],"such":[31,64],"as":[32],"Broadcast":[33],"News,":[34],"particular":[36],"region":[39],"usually":[40],"persists":[41],"for":[42,81,92,157],"multiple":[43,73],"frames":[44,101],"during":[45],"which":[46,137],"background":[48],"may":[49,51],"or":[50],"not":[52],"vary.":[53],"this":[55],"paper":[56],"we":[57],"explore":[58],"two":[59],"innovative":[60],"techniques":[61],"that":[62],"exploit":[63],"multi-frame":[65,158],"persistence":[66],"videotext.":[68],"The":[69,83,126],"first":[70],"technique":[71,85],"uses":[72,86],"instances":[74],"generate":[76],"single":[78,124,163],"enhanced":[79],"image":[80],"recognition.":[82],"second":[84],"NIST":[88],"ROVER":[89,118],"algorithm":[90],"developed":[91],"speech":[93],"combine":[96],"1-best":[97],"hypotheses":[98,133],"from":[99,134],"different":[100,145],"region.":[105],"Significant":[106],"improvement":[107],"word":[110],"error":[111],"rate":[112],"(WER)":[113],"obtained":[115],"by":[116,131],"using":[117,140],"when":[119],"compared":[120],"recognizing":[122],"instance.":[125,165],"WER":[127,154],"further":[129],"reduced":[130],"combining":[132],"frame":[135,164],"instances,":[136],"were":[138],"generated":[139],"models":[142],"trained":[143],"with":[144],"binarization":[146],"thresholds.":[147],"A":[148],"20%":[149],"relative":[150],"reduction":[151],"was":[155],"achieved":[156],"combination":[159],"over":[160],"decoding":[161]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}