{"id":"https://openalex.org/W7133202002","doi":"https://doi.org/10.1109/tmm.2026.3668365","title":"Text-Pass Filter: An Efficient Scene Text Detector","display_name":"Text-Pass Filter: An Efficient Scene Text Detector","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133202002","doi":"https://doi.org/10.1109/tmm.2026.3668365"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3668365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668365","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5077254624","display_name":"Chuang Yang","orcid":"https://orcid.org/0000-0002-4086-8387"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Yang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-4086-8387","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015343173","display_name":"Haozhao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhao Ma","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127853698","display_name":"Xu Han","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0005-6489-719X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127813041","display_name":"Yuan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127784059","display_name":"Qi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-7028-4956","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96591036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"5472","last_page":"5486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.7050999999046326,"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":0.7050999999046326,"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/T11439","display_name":"Video Analysis and Summarization","score":0.019200000911951065,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/filter","display_name":"Filter (signal processing)","score":0.6061999797821045},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.49140000343322754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4498000144958496},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4498000144958496},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4352000057697296},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4165000021457672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810999751091003},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.49140000343322754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C46416853","wikidata":"https://www.wikidata.org/wiki/Q254758","display_name":"Passband","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.2750000059604645},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3668365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668365","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1964179093","display_name":null,"funder_award_id":"U21B2041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2423766861","display_name":null,"funder_award_id":"62501511","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5992145127","display_name":null,"funder_award_id":"62471394","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"pursue":[1],"an":[2],"efficient":[3],"text":[4,25,40,53,59,74,95,160,201],"assembling":[5],"process,":[6],"existing":[7],"methods":[8],"detect":[9],"texts":[10,81,134,178,184],"via":[11],"the":[12,17,21,29,57,63,101,138,151,157,171,195,199,205,227,230,236,242,250],"shrink-mask":[13],"expansion":[14],"strategy.":[15],"However,":[16],"shrinking":[18],"operation":[19],"loses":[20],"visual":[22],"features":[23],"of":[24,111,176,198,244],"margins":[26],"and":[27,31,46,165,202,232,246],"confuses":[28],"foreground":[30,231],"background":[32],"difference,":[33],"which":[34,61,89,234],"brings":[35],"intrinsic":[36,64],"limitations":[37],"to":[38,182,193,203,209,222,225],"recognize":[39,183,211],"features.":[41,168],"We":[42],"follow":[43],"this":[44,124],"issue":[45],"design":[47],"Text-Pass":[48],"Filter":[49],"(TPF)":[50],"for":[51,93,131,147],"arbitrary-shaped":[52],"detection.":[54,96],"It":[55,66,126],"segments":[56],"whole":[58,73,133,212],"directly,":[60],"avoids":[62],"limitations.":[65],"is":[67,191,220],"noteworthy":[68],"that":[69,100],"different":[70],"from":[71],"previous":[72],"region-based":[75],"methods,":[76],"TPF":[77,141,224],"can":[78],"separate":[79],"adhesive":[80],"naturally":[82],"without":[83],"complex":[84],"decoding":[85],"or":[86,122],"post-processing":[87],"processes,":[88],"makes":[90,179],"it":[91,180],"possible":[92],"real-time":[94],"Concretely,":[97],"we":[98],"find":[99],"band-pass":[102,139],"filter":[103,155],"allows":[104],"through":[105],"components":[106,118],"in":[107],"a":[108,128,143,186,215],"specified":[109],"band":[110],"frequencies,":[112],"called":[113],"its":[114,163],"passband":[115],"but":[116],"blocks":[117],"with":[119],"frequencies":[120],"above":[121],"below":[123],"band.":[125],"provides":[127],"natural":[129],"idea":[130],"extracting":[132],"separately.":[135],"By":[136],"simulating":[137],"filter,":[140],"constructs":[142],"unique":[144],"feature-filter":[145,237],"pair":[146,238],"each":[148],"text.":[149],"In":[150],"inference":[152],"stage,":[153],"every":[154],"extracts":[156],"corresponding":[158],"matched":[159],"by":[161],"passing":[162],"pass-feature":[164],"blocking":[166],"other":[167],"Meanwhile,":[169],"considering":[170],"large":[172],"aspect":[173],"ratio":[174],"problem":[175],"ribbon-like":[177],"hard":[181],"wholly,":[185],"Reinforcement":[187],"Ensemble":[188],"Unit":[189,218],"(REU)":[190],"designed":[192],"enhance":[194],"feature":[196],"consistency":[197],"same":[200],"enlarge":[204],"filter's":[206],"recognition":[207],"field":[208],"help":[210],"texts.":[213],"Furthermore,":[214],"Foreground":[216],"Prior":[217],"(FPU)":[219],"introduced":[221],"encourage":[223],"discriminate":[226],"difference":[228],"between":[229],"background,":[233],"improves":[235],"quality.":[239],"Experiments":[240],"demonstrate":[241],"effectiveness":[243],"REU":[245],"FPU":[247],"while":[248],"showing":[249],"TPF's":[251],"superiority.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-03T06:15:21.484131","created_date":"2026-03-03T00:00:00"}