{"id":"https://openalex.org/W2119179626","doi":"https://doi.org/10.1109/icdar.2015.7333866","title":"Document image OCR accuracy prediction via latent Dirichlet allocation","display_name":"Document image OCR accuracy prediction via latent Dirichlet allocation","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2119179626","doi":"https://doi.org/10.1109/icdar.2015.7333866","mag":"2119179626"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2015.7333866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","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/A5102329211","display_name":"Xujun Peng","orcid":"https://orcid.org/0000-0001-9373-7092"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xujun Peng","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108504544","display_name":"Huaigu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaigu Cao","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Natarajan","raw_affiliation_strings":["ISI Univ. of Southern California, Marina del Rey, CA","ISI, Univ. of Southern California, Marina del Rey, 90292, USA"],"affiliations":[{"raw_affiliation_string":"ISI Univ. of Southern California, Marina del Rey, CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"ISI, Univ. of Southern California, Marina del Rey, 90292, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102329211"],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86815406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"771","last_page":"775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition 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/T12357","display_name":"Digital Media Forensic Detection","score":0.9896000027656555,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9894000291824341,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8772314786911011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8324925303459167},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7890548706054688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6753168106079102},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.5795842409133911},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5166078209877014},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4718603789806366},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.47066864371299744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45586398243904114},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.42788994312286377},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37104135751724243},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3344506025314331}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8772314786911011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324925303459167},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7890548706054688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6753168106079102},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.5795842409133911},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5166078209877014},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4718603789806366},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.47066864371299744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45586398243904114},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.42788994312286377},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37104135751724243},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3344506025314331}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdar.2015.7333866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2015.7333866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 13th International Conference on Document Analysis and Recognition (ICDAR)","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":22,"referenced_works":["https://openalex.org/W615588766","https://openalex.org/W1575759921","https://openalex.org/W1880262756","https://openalex.org/W1946768312","https://openalex.org/W1965285802","https://openalex.org/W1971155098","https://openalex.org/W1984309565","https://openalex.org/W2001082470","https://openalex.org/W2007246825","https://openalex.org/W2009826797","https://openalex.org/W2018918151","https://openalex.org/W2065998534","https://openalex.org/W2071203921","https://openalex.org/W2088326204","https://openalex.org/W2110029947","https://openalex.org/W2142731874","https://openalex.org/W2144468361","https://openalex.org/W2160244865","https://openalex.org/W2169602116","https://openalex.org/W6634441671","https://openalex.org/W6639619044","https://openalex.org/W6640274004"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W2131730163","https://openalex.org/W3046471831"],"abstract_inverted_index":{"Optical":[0],"character":[1],"recognition":[2],"(OCR)":[3],"accuracy":[4,81],"of":[5,15,49,142],"document":[6,17,26,30,74,155],"images":[7,102],"is":[8,69,108,116],"an":[9],"important":[10],"factor":[11],"for":[12,23,58],"the":[13,41,45,54,60,79,95,120,150],"success":[14],"many":[16],"processing":[18],"and":[19,103],"analysis":[20],"tasks,":[21],"especially":[22],"unconstraint":[24],"captured":[25,135],"images.":[27],"Although":[28],"several":[29],"image":[31,50,75,156],"OCR":[32,61,80,122],"capability":[33],"assessment":[34,158],"methods":[35,86],"are":[36,98],"proposed,":[37],"they":[38],"mostly":[39],"model":[40,68,107],"problem":[42],"based":[43,110],"on":[44,111,128],"empirically":[46],"defined":[47],"rules":[48],"degradation,":[51],"which":[52,115,132],"cause":[53],"existing":[55],"approaches":[56],"infeasible":[57],"predicting":[59],"scores.":[62],"In":[63],"this":[64],"paper,":[65],"a":[66,104,129],"computational":[67],"presented":[70],"to":[71,118],"automatically":[72],"predict":[73],"quality":[76,106,157],"towards":[77],"facilitating":[78],"without":[82],"references.":[83],"Unlike":[84],"conventional":[85],"that":[87,149],"use":[88],"heuristically":[89],"designed":[90],"features,":[91],"in":[92],"our":[93],"work":[94],"raw":[96],"features":[97],"learned":[99],"from":[100],"training":[101],"generative":[105],"built":[109],"latent":[112],"Dirichlet":[113],"allocation,":[114],"used":[117],"assess":[119],"document's":[121],"capability.":[123],"We":[124],"present":[125],"evaluation":[126],"results":[127,147],"public":[130],"dataset":[131],"have":[133],"been":[134],"using":[136],"digital":[137],"cameras":[138],"with":[139],"different":[140],"level":[141],"blur":[143],"degradation.":[144],"The":[145],"experimental":[146],"show":[148],"proposed":[151],"method":[152],"outperforms":[153],"traditional":[154],"approaches.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}