{"id":"https://openalex.org/W3088664074","doi":"https://doi.org/10.1109/dsmp47368.2020.9204229","title":"Acquiring Custom OCR System with Minimal Manual Annotation","display_name":"Acquiring Custom OCR System with Minimal Manual Annotation","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3088664074","doi":"https://doi.org/10.1109/dsmp47368.2020.9204229","mag":"3088664074"},"language":"en","primary_location":{"id":"doi:10.1109/dsmp47368.2020.9204229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsmp47368.2020.9204229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Third International Conference on Data Stream Mining & Processing (DSMP)","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/A5076891199","display_name":"Jan H\u016fla","orcid":"https://orcid.org/0000-0001-7639-864X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Hula","raw_affiliation_strings":["Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065303754","display_name":"David Moj\u017e\u00ed\u0161ek","orcid":"https://orcid.org/0000-0002-3867-644X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Mojzisek","raw_affiliation_strings":["Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023110882","display_name":"David Adamczyk","orcid":"https://orcid.org/0000-0002-7794-104X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Adamczyk","raw_affiliation_strings":["Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003891531","display_name":"Radek \u010cech","orcid":"https://orcid.org/0000-0002-4412-4588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radek Cech","raw_affiliation_strings":["Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Research and Applications of Fuzzy Modeling, Ostrava, Czechia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1958,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50473275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"59","issue":null,"first_page":"231","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9926999807357788,"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/annotation","display_name":"Annotation","score":0.8992050290107727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7981729507446289},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6725518107414246},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6051326990127563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5592538118362427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5558261275291443},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.414591908454895},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17005136609077454},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15819895267486572}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8992050290107727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981729507446289},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6725518107414246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6051326990127563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5592538118362427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5558261275291443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.414591908454895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17005136609077454},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15819895267486572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsmp47368.2020.9204229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsmp47368.2020.9204229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Third International Conference on Data Stream Mining & Processing (DSMP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1993557076","https://openalex.org/W2001642682","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2487365028","https://openalex.org/W2588463901","https://openalex.org/W2605102758","https://openalex.org/W2614598271","https://openalex.org/W2777421064","https://openalex.org/W2786672974","https://openalex.org/W2795889831","https://openalex.org/W2896182651","https://openalex.org/W2962899390","https://openalex.org/W2963351448","https://openalex.org/W2968088687","https://openalex.org/W2972006294","https://openalex.org/W2973047034","https://openalex.org/W3097176321","https://openalex.org/W3101442004","https://openalex.org/W3122950209","https://openalex.org/W4289763240","https://openalex.org/W6748816842","https://openalex.org/W6752823856","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2556260348"],"abstract_inverted_index":{"We":[0,49],"describe":[1,51],"a":[2,5,14,66],"development":[3],"of":[4,17,30,54,65],"custom":[6],"OCR":[7],"system,":[8],"which":[9,58],"is":[10],"designed":[11],"specifically":[12],"for":[13],"linguistic":[15],"analysis":[16,26],"texts":[18],"printed":[19],"during":[20],"the":[21],"early":[22],"modern":[23],"period.":[24],"This":[25],"requires":[27],"precise":[28],"detection":[29],"individual":[31],"graphemes,":[32],"and":[33],"we,":[34],"therefore,":[35],"could":[36],"not":[37],"apply":[38],"standard":[39],"approaches":[40],"that":[41],"transcribe":[42],"whole":[43],"lines":[44],"in":[45],"an":[46],"end-to-end":[47],"fashion.":[48],"also":[50],"our":[52],"use":[53],"synthetically":[55],"generated":[56],"images,":[57],"allow":[59],"us":[60],"to":[61],"avoid":[62],"manual":[63],"annotation":[64],"large":[67],"training":[68],"set.":[69]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}