{"id":"https://openalex.org/W7204168937","doi":"https://doi.org/10.1007/978-3-032-36023-6_26","title":"Quality Prediction for Large Scale HTR Confidence Is All You Need","display_name":"Quality Prediction for Large Scale HTR Confidence Is All You Need","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204168937","doi":"https://doi.org/10.1007/978-3-032-36023-6_26"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-36023-6_26","doi":"https://doi.org/10.1007/978-3-032-36023-6_26","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-36023-6_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7204181497","display_name":"Document Analysis and Recognition \u2013 ICDAR 2026"},"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-36023-6_26","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107291084","display_name":"Erik Lenas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210154857","display_name":"National Archives of Sweden","ror":"https://ror.org/050j2px32","country_code":"SE","type":"other","lineage":["https://openalex.org/I4210154857"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Erik Lenas","raw_affiliation_strings":["Swedish National Archives, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swedish National Archives, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210154857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085824383","display_name":"Viktoria L\u00f6fgren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210154857","display_name":"National Archives of Sweden","ror":"https://ror.org/050j2px32","country_code":"SE","type":"other","lineage":["https://openalex.org/I4210154857"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Viktoria L\u00f6fgren","raw_affiliation_strings":["Swedish National Archives, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swedish National Archives, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210154857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083752513","display_name":"Olof Karsvall","orcid":"https://orcid.org/0000-0003-4350-7533","observed_orcids":["https://orcid.org/0000-0003-4350-7533"]},"institutions":[{"id":"https://openalex.org/I4210154857","display_name":"National Archives of Sweden","ror":"https://ror.org/050j2px32","country_code":"SE","type":"other","lineage":["https://openalex.org/I4210154857"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Olof Karsvall","raw_affiliation_strings":["Swedish National Archives, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swedish National Archives, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210154857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5107291084"],"corresponding_institution_ids":["https://openalex.org/I4210154857"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64495098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"450","last_page":"466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/quality-prediction","display_name":"quality prediction","score":0.7799999713897705},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.9860000014305115},{"id":"https://openalex.org/keywords/confidence-distributions","display_name":"confidence distributions","score":0.6420000195503235},{"id":"https://openalex.org/keywords/line-segmentation","display_name":"line segmentation","score":0.6269999742507935},{"id":"https://openalex.org/keywords/region-based-segmentation","display_name":"region-based segmentation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/n-gram-features","display_name":"n-gram features","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639000058174133},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187000274658203},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.492000013589859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4668000042438507},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C2909755999","wikidata":"https://www.wikidata.org/wiki/Q4751126","display_name":"Low Confidence","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-36023-6_26","doi":"https://doi.org/10.1007/978-3-032-36023-6_26","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-36023-6_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-36023-6_26","doi":"https://doi.org/10.1007/978-3-032-36023-6_26","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-36023-6_26","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2295598076","https://openalex.org/W2308839768","https://openalex.org/W2534524893","https://openalex.org/W3012289950","https://openalex.org/W3194594797","https://openalex.org/W4221148079","https://openalex.org/W4283065708","https://openalex.org/W4304014014","https://openalex.org/W4312233877","https://openalex.org/W4377197105","https://openalex.org/W4382202677","https://openalex.org/W4393677674","https://openalex.org/W4403770406","https://openalex.org/W4404514984","https://openalex.org/W4411132570","https://openalex.org/W7125207973"],"related_works":["https://openalex.org/W2308839768","https://openalex.org/W4416264777","https://openalex.org/W7128484237","https://openalex.org/W4377197105","https://openalex.org/W2119179626","https://openalex.org/W1575759921","https://openalex.org/W7100527127","https://openalex.org/W3167144764","https://openalex.org/W4385991115","https://openalex.org/W2160244865"],"abstract_inverted_index":{"Quality":[0],"prediction":[1,37,155,179],"of":[2,10,53,75],"handwritten":[3],"text":[4],"recognition":[5],"(HTR)":[6],"addresses":[7],"the":[8,50,54,116,165],"challenge":[9],"estimating":[11],"HTR":[12,25,55],"quality":[13,36,59,154,178],"in":[14,78],"production":[15],"where":[16],"no":[17],"ground-truth":[18],"data":[19],"are":[20],"available.":[21],"Focusing":[22],"on":[23],"pipeline-based":[24],"(instance":[26],"segmentation":[27,65,145],"for":[28],"regions/lines":[29],"followed":[30],"by":[31,168],"line-level":[32],"recognition),":[33],"we":[34],"formulate":[35],"as":[38],"a":[39,45,89],"supervised":[40],"page-level":[41],"regression":[42],"task:":[43],"given":[44],"single":[46],"document":[47,91],"image":[48,82],"and":[49,66,71,102,109,131,143,170],"runtime":[51],"outputs":[52],"pipeline,":[56],"predict":[57],"full-page":[58],"metrics":[60],"that":[61,149,175],"reflect":[62],"both":[63],"line/region":[64],"transcription":[67],"performance.":[68],"We":[69,147],"extract":[70],"investigate":[72],"four":[73],"families":[74],"features":[76,95,112,138],"available":[77],"production:":[79],"(i)":[80],"handcrafted":[81],"features,":[83,162],"(ii)":[84],"learned":[85],"document-image":[86],"embeddings":[87],"from":[88,96,115],"pretrained":[90],"transformer,":[92],"(iii)":[93],"text-based":[94],"external":[97],"resources,":[98],"including":[99],"lexicon":[100],"matching":[101],"character":[103],"n":[104],"-gram":[105],"language":[106],"model":[107,133],"coverage/perplexity,":[108],"(iv)":[110],"model-native":[111,186],"derived":[113],"directly":[114],"pipeline":[117],"outputs,":[118],"specifically":[119],"confidence":[120,130,134,150,161],"scores.":[121],"A":[122],"key":[123],"contribution":[124],"is":[125],"to":[126],"move":[127],"beyond":[128],"mean":[129],"instead":[132],"distributions":[135,151],"via":[136],"histogram":[137],"computed":[139],"over":[140],"tokens,":[141],"lines,":[142],"region/line":[144],"outputs.":[146],"find":[148],"consistently":[152],"improve":[153],"and,":[156],"when":[157],"combined":[158],"with":[159],"standard":[160],"largely":[163],"subsume":[164],"information":[166],"provided":[167],"image-":[169],"language-based":[171],"features.":[172,187],"This":[173],"implies":[174],"an":[176],"effective":[177],"system":[180],"can":[181],"be":[182],"built":[183],"using":[184],"low-cost":[185]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-26T00:00:00"}