{"id":"https://openalex.org/W3021342370","doi":"https://doi.org/10.3390/sym12050715","title":"Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing","display_name":"Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing","publication_year":2020,"publication_date":"2020-05-02","ids":{"openalex":"https://openalex.org/W3021342370","doi":"https://doi.org/10.3390/sym12050715","mag":"3021342370"},"language":"en","primary_location":{"id":"doi:10.3390/sym12050715","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12050715","pdf_url":"https://www.mdpi.com/2073-8994/12/5/715/pdf?version=1589784669","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/12/5/715/pdf?version=1589784669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031653681","display_name":"Dan Sporici","orcid":"https://orcid.org/0000-0001-7777-1928"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Sporici","raw_affiliation_strings":["Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania"],"raw_orcid":"https://orcid.org/0000-0001-7777-1928","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043111578","display_name":"Elena Cu\u0219nir","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Elena Cu\u0219nir","raw_affiliation_strings":["Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031177491","display_name":"Costin-Anton Boiangiu","orcid":"https://orcid.org/0000-0002-2987-4022"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Costin-Anton Boiangiu","raw_affiliation_strings":["Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania"],"raw_orcid":"https://orcid.org/0000-0002-2987-4022","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Faculty of Automatic Control and Computers, Politehnica University of Bucharest, Splaiul Independen\u021bei 313, 060042 Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031177491"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":3.2737,"has_fulltext":true,"cited_by_count":71,"citation_normalized_percentile":{"value":0.93000473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"12","issue":"5","first_page":"715","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9757999777793884,"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/preprocessor","display_name":"Preprocessor","score":0.8705106377601624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8332964181900024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7360657453536987},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7220428586006165},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6614687442779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6179702281951904},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5059942603111267},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5024769306182861},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4439907371997833},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.44190749526023865},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41939759254455566},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2879257798194885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13624140620231628},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12941747903823853}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8705106377601624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332964181900024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7360657453536987},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7220428586006165},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6614687442779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6179702281951904},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5059942603111267},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5024769306182861},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4439907371997833},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.44190749526023865},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41939759254455566},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2879257798194885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13624140620231628},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12941747903823853},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym12050715","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12050715","pdf_url":"https://www.mdpi.com/2073-8994/12/5/715/pdf?version=1589784669","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2703254dfb724596ac9b1f54396fda36","is_oa":true,"landing_page_url":"https://doaj.org/article/2703254dfb724596ac9b1f54396fda36","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 12, Iss 5, p 715 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/12/5/715/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym12050715","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym12050715","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym12050715","pdf_url":"https://www.mdpi.com/2073-8994/12/5/715/pdf?version=1589784669","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1910611889","display_name":null,"funder_award_id":"PN-III-P1-1.2-PCCDI-2017-0689","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G4864199281","display_name":null,"funder_award_id":"PN- III -P1-1","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"},{"id":"https://openalex.org/G788691142","display_name":null,"funder_award_id":"PN-III-P1-1.2-PCCDI","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"},{"id":"https://openalex.org/F4320336189","display_name":"Colegiul Consultativ pentru Cercetare-Dezvoltare \u015fi Inovare","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3021342370.pdf","grobid_xml":"https://content.openalex.org/works/W3021342370.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2011164422","https://openalex.org/W2058333183","https://openalex.org/W2082163619","https://openalex.org/W2133059825","https://openalex.org/W2140485652","https://openalex.org/W2168445392","https://openalex.org/W2249248087","https://openalex.org/W2288418054","https://openalex.org/W2605432808","https://openalex.org/W2768817781","https://openalex.org/W2774927939","https://openalex.org/W2785954209","https://openalex.org/W2787791489","https://openalex.org/W2913957924","https://openalex.org/W2981379022","https://openalex.org/W3003508901","https://openalex.org/W3106148001","https://openalex.org/W4230800876","https://openalex.org/W4253948120","https://openalex.org/W6680994997","https://openalex.org/W6729756640","https://openalex.org/W6736115937"],"related_works":["https://openalex.org/W4295532600","https://openalex.org/W2063823869","https://openalex.org/W2047973478","https://openalex.org/W3204576215","https://openalex.org/W4295934125","https://openalex.org/W3160316822","https://openalex.org/W1581784047","https://openalex.org/W4283017656","https://openalex.org/W2904147048","https://openalex.org/W2774927939"],"abstract_inverted_index":{"Optical":[0],"Character":[1],"Recognition":[2],"(OCR)":[3],"is":[4,74,106,141],"the":[5,29,32,94,98,102,113,127],"process":[6],"of":[7,31,63,116],"identifying":[8,67],"and":[9,66,101,126],"converting":[10],"texts":[11],"rendered":[12],"in":[13,69],"images":[14,73],"using":[15,45],"pixels":[16],"to":[17,26,92,121,132],"a":[18,58,86,138],"more":[19,70],"computer-friendly":[20],"representation.":[21],"The":[22,76],"presented":[23],"work":[24],"aims":[25],"prove":[27],"that":[28,108,140],"accuracy":[30,115],"Tesseract":[33,49,117],"4.0":[34,50,118],"OCR":[35],"engine":[36],"can":[37,111],"be":[38],"further":[39],"enhanced":[40],"by":[41,85,144],"employing":[42],"convolution-based":[43],"preprocessing":[44,82],"specific":[46],"kernels.":[47],"As":[48],"has":[51],"proven":[52],"great":[53],"performance":[54],"when":[55],"evaluated":[56],"against":[57],"favorable":[59],"input,":[60],"its":[61,145],"capability":[62],"properly":[64],"detecting":[65],"characters":[68],"realistic,":[71],"unfriendly":[72],"questioned.":[75],"article":[77],"proposes":[78],"an":[79],"adaptive":[80],"image":[81],"step":[83],"guided":[84],"reinforcement":[87],"learning":[88],"model,":[89],"which":[90],"attempts":[91],"minimize":[93],"edit":[95],"distance":[96],"between":[97],"recognized":[99],"text":[100],"ground":[103],"truth.":[104],"It":[105],"shown":[107],"this":[109],"approach":[110],"boost":[112],"character-level":[114],"from":[119,130],"0.134":[120],"0.616":[122],"(+359%":[123],"relative":[124,135],"change)":[125,136],"F1":[128],"score":[129],"0.163":[131],"0.729":[133],"(+347%":[134],"on":[137],"dataset":[139],"considered":[142],"challenging":[143],"authors.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-10-10T00:00:00"}