{"id":"https://openalex.org/W4393900071","doi":"https://doi.org/10.1117/12.3023176","title":"Threshold U-Net: speed up document binarization with adaptive thresholds","display_name":"Threshold U-Net: speed up document binarization with adaptive thresholds","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4393900071","doi":"https://doi.org/10.1117/12.3023176"},"language":"en","primary_location":{"id":"doi:10.1117/12.3023176","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.3023176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixteenth International Conference on Machine Vision (ICMV 2023)","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/A5094361754","display_name":"Konstantin Lihota","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Konstantin Lihota","raw_affiliation_strings":["Moscow Institute of Physics and Technology (Russian Federation)","Smart Engines Service LLC (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"Moscow Institute of Physics and Technology (Russian Federation)","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"Smart Engines Service LLC (Russian Federation)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061735569","display_name":"Alexander Gayer","orcid":"https://orcid.org/0000-0001-6268-2279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Gayer","raw_affiliation_strings":["Federal Research Center \u201cComputer Science and Control\u201d (Russian Federation)","Smart Engines Service LLC (Russian Federation)","Federal Research Center \"Computer Science and Control\" (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d (Russian Federation)","institution_ids":[]},{"raw_affiliation_string":"Smart Engines Service LLC (Russian Federation)","institution_ids":[]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\" (Russian Federation)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019711919","display_name":"Vladimir V. Arlazarov","orcid":"https://orcid.org/0000-0003-3260-9104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Arlazarov","raw_affiliation_strings":["Federal Research Center \u201cComputer Science and Control\u201d (Russian Federation)","Smart Engines Service LLC (Russian Federation)","Federal Research Center \"Computer Science and Control\" (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"Federal Research Center \u201cComputer Science and Control\u201d (Russian Federation)","institution_ids":[]},{"raw_affiliation_string":"Smart Engines Service LLC (Russian Federation)","institution_ids":[]},{"raw_affiliation_string":"Federal Research Center \"Computer Science and Control\" (Russian Federation)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5094361754"],"corresponding_institution_ids":["https://openalex.org/I153845743"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47452729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"abs/1804.03999","issue":null,"first_page":"3","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.9977999925613403,"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":0.9965000152587891,"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":0.8067935109138489},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6212036609649658},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.613189697265625},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5886222124099731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5760475993156433},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5556464195251465},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5525187253952026},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4670874774456024},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.41736680269241333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.416718065738678},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4101802706718445},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.399222731590271},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32110732793807983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11663994193077087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067935109138489},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6212036609649658},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.613189697265625},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5886222124099731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760475993156433},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5556464195251465},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5525187253952026},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4670874774456024},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.41736680269241333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.416718065738678},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4101802706718445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.399222731590271},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32110732793807983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11663994193077087},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.3023176","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.3023176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixteenth International Conference on Machine Vision (ICMV 2023)","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":25,"referenced_works":["https://openalex.org/W1491319300","https://openalex.org/W2085718867","https://openalex.org/W2133059825","https://openalex.org/W2747329762","https://openalex.org/W2751352153","https://openalex.org/W2922209834","https://openalex.org/W2988314300","https://openalex.org/W2998621280","https://openalex.org/W3045075905","https://openalex.org/W3048313648","https://openalex.org/W3088524643","https://openalex.org/W3119307990","https://openalex.org/W3202755389","https://openalex.org/W3209002923","https://openalex.org/W4221000591","https://openalex.org/W4239623876","https://openalex.org/W4293390340","https://openalex.org/W4294203757","https://openalex.org/W4312376588","https://openalex.org/W4312766223","https://openalex.org/W4379646224","https://openalex.org/W4385820433","https://openalex.org/W6691815588","https://openalex.org/W6783467810","https://openalex.org/W6855854313"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"U-Net":[0,40,76,85,137,147,165],"similar":[1],"architectures":[2,41],"are":[3],"widely":[4],"used":[5],"in":[6,68],"the":[7,15,43,48,60,81,94,104,111,149,153,158,161],"task":[8],"of":[9,18,39,63,79,106,140,142,160],"document":[10],"image":[11,96,117],"binarization.":[12],"However,":[13],"despite":[14],"good":[16],"quality":[17,139],"binarization,":[19],"they":[20],"also":[21],"have":[22],"high":[23],"computational":[24],"complexity,":[25],"which":[26,52,93],"greatly":[27],"limits":[28],"their":[29],"use":[30],"on":[31,54,66,123,148,157],"mobile":[32],"and":[33,47,58,133,178],"embedded":[34],"devices.":[35],"The":[36,99],"performance":[37],"bottleneck":[38],"is":[42,97,166],"first":[44],"encoder":[45],"layers":[46],"last":[49],"decoder":[50],"layers,":[51],"operate":[53],"high-resolution":[55],"input":[56,95],"data":[57],"contain":[59],"largest":[61],"number":[62],"operations.":[64],"Based":[65],"this,":[67],"this":[69],"paper":[70],"we":[71],"propose":[72],"a":[73,87,115,124,129],"new":[74],"Threshold":[75,84,136,164],"model:":[77],"instead":[78],"predicting":[80],"final":[82],"image,":[83],"predicts":[86],"low-resolution":[88],"adaptive":[89],"threshold":[90,113,162],"map,":[91,163],"with":[92,119,128],"binarized.":[98],"proposed":[100],"architecture":[101],"naturally":[102],"combines":[103],"ideas":[105],"classical":[107],"algorithms":[108],"that":[109],"calculate":[110],"binarization":[112,141],"for":[114],"specific":[116],"region":[118],"an":[120],"approach":[121],"based":[122],"deep":[125],"learning":[126],"model":[127],"large":[130],"receptive":[131],"field":[132],"context":[134],"understanding.":[135],"demonstrates":[138],"historical":[143],"documents":[144],"comparable":[145],"to":[146,168,174,181],"DIBCO-2017":[150],"dataset.":[151],"At":[152],"same":[154],"time,":[155],"depending":[156],"resolution":[159],"up":[167,173,180],"2":[169],"times":[170],"faster,":[171],"requires":[172],"26%":[175],"less":[176],"RAM":[177],"consists":[179],"10%":[182],"fewer":[183],"parameters.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}