{"id":"https://openalex.org/W4411516626","doi":"https://doi.org/10.1007/s44163-025-00251-7","title":"A hybrid approach to Bangla handwritten OCR: combining YOLO and an advanced CNN","display_name":"A hybrid approach to Bangla handwritten OCR: combining YOLO and an advanced CNN","publication_year":2025,"publication_date":"2025-06-21","ids":{"openalex":"https://openalex.org/W4411516626","doi":"https://doi.org/10.1007/s44163-025-00251-7"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-025-00251-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00251-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00251-7.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00251-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114713105","display_name":"Aye Aye Maung","orcid":null},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]},{"id":"https://openalex.org/I4210144275","display_name":"Dhaka University of Engineering & Technology","ror":"https://ror.org/03qxvyy35","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210144275"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Aye T. Maung","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh","institution_ids":["https://openalex.org/I183697816","https://openalex.org/I4210144275"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114713106","display_name":"Sumaiya Salekin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144275","display_name":"Dhaka University of Engineering & Technology","ror":"https://ror.org/03qxvyy35","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210144275"]},{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sumaiya Salekin","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh","institution_ids":["https://openalex.org/I183697816","https://openalex.org/I4210144275"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016222651","display_name":"Mohammad A. Haque","orcid":"https://orcid.org/0000-0001-5613-2190"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]},{"id":"https://openalex.org/I4210144275","display_name":"Dhaka University of Engineering & Technology","ror":"https://ror.org/03qxvyy35","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210144275"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad A. Haque","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology,  Dhaka, Bangladesh","institution_ids":["https://openalex.org/I183697816","https://openalex.org/I4210144275"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114713105"],"corresponding_institution_ids":["https://openalex.org/I183697816","https://openalex.org/I4210144275"],"apc_list":{"value":990,"currency":"EUR","value_usd":1067},"apc_paid":{"value":990,"currency":"EUR","value_usd":1067},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":"1","first_page":null,"last_page":null},"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":0.996399998664856,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.8382613658905029},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.7213969826698303},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7167606353759766},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7027167081832886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6348880529403687},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6018399000167847},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5678635835647583},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5572670102119446},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.5043646097183228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49157437682151794},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4457458257675171},{"id":"https://openalex.org/keywords/intelligent-word-recognition","display_name":"Intelligent word recognition","score":0.4295366406440735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3571586310863495},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.26033324003219604},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.22269782423973083},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14219024777412415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382613658905029},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.7213969826698303},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7167606353759766},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7027167081832886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6348880529403687},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6018399000167847},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5678635835647583},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5572670102119446},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.5043646097183228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49157437682151794},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4457458257675171},{"id":"https://openalex.org/C17649283","wikidata":"https://www.wikidata.org/wiki/Q6044162","display_name":"Intelligent word recognition","level":5,"score":0.4295366406440735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3571586310863495},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.26033324003219604},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.22269782423973083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14219024777412415},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-025-00251-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00251-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00251-7.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cbc52f1873054901ab8ecabba8a24a6e","is_oa":true,"landing_page_url":"https://doaj.org/article/cbc52f1873054901ab8ecabba8a24a6e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Discover Artificial Intelligence, Vol 5, Iss 1, Pp 1-26 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-025-00251-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-025-00251-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-025-00251-7.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411516626.pdf","grobid_xml":"https://content.openalex.org/works/W4411516626.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1989725585","https://openalex.org/W2031094399","https://openalex.org/W2116741014","https://openalex.org/W2138299629","https://openalex.org/W2162433034","https://openalex.org/W2548218270","https://openalex.org/W2600236781","https://openalex.org/W2963123666","https://openalex.org/W2967615747","https://openalex.org/W3097599302","https://openalex.org/W3200650723","https://openalex.org/W4200220722","https://openalex.org/W4206284999","https://openalex.org/W4288754176","https://openalex.org/W4308160480","https://openalex.org/W4383503605","https://openalex.org/W4402978612","https://openalex.org/W4403790900","https://openalex.org/W6887886470","https://openalex.org/W6920785558","https://openalex.org/W6944093749","https://openalex.org/W6949449287"],"related_works":["https://openalex.org/W4317914684","https://openalex.org/W4225540279","https://openalex.org/W3212830933","https://openalex.org/W294193597","https://openalex.org/W655009047","https://openalex.org/W2218402054","https://openalex.org/W145261646","https://openalex.org/W3163533264","https://openalex.org/W4287183825","https://openalex.org/W3162332277"],"abstract_inverted_index":{"Abstract":[0],"Optical":[1],"Character":[2,153],"Recognition":[3],"(OCR)":[4],"plays":[5],"a":[6,20,62,112,146],"vital":[7],"role":[8],"in":[9,24,34,41],"automating":[10],"data":[11,165],"entry":[12],"from":[13,45,157],"handwritten":[14,32,70],"forms":[15],"into":[16],"digital":[17],"systems.":[18],"However,":[19],"significant":[21],"gap":[22],"exists":[23],"the":[25,46,80,104,107,140,152,168,175,184,192,196,205,208],"research":[26,60],"on":[27,129,163],"OCR":[28,66],"techniques":[29],"tailored":[30],"for":[31,68,87,117,121,126,136,211],"texts":[33],"complex":[35],"languages":[36],"such":[37],"as":[38],"Bangla.":[39],"Challenges":[40],"Bangla":[42,69,212],"script":[43],"arise":[44],"presence":[47],"of":[48,115,207],"modifiers,":[49],"compound":[50],"characters,":[51],"and":[52,64,96,124,134,179,200],"diacritic":[53],"marks,":[54],"making":[55],"accurate":[56],"recognition":[57,113],"difficult.":[58],"Our":[59],"introduces":[61],"scalable":[63],"effective":[65],"pipeline":[67,78,105,170],"documents":[71],"that":[72,167],"addresses":[73],"these":[74],"complexities.":[75],"The":[76],"proposed":[77,169,209],"leverages":[79],"YOLO":[81],"(You":[82],"Only":[83],"Look":[84],"Once)":[85],"model":[86],"character":[88,102],"detection,":[89],"accurately":[90],"isolating":[91],"base":[92],"alphabets,":[93],"consonant":[94,127],"conjuncts,":[95],"characters":[97],"with":[98,171],"modifiers":[99],"(matras).":[100],"For":[101],"recognition,":[103],"utilizes":[106],"EfficientNet-B4":[108],"model,":[109],"which":[110],"demonstrated":[111],"accuracy":[114],"93.87%":[116],"grapheme":[118],"roots,":[119],"98.22%":[120],"vowel":[122],"diacritics,":[123],"98.0%":[125],"diacritics":[128],"publicly":[130],"available":[131],"datasets,":[132],"combined":[133],"adapted":[135],"our":[137],"use.":[138],"Additionally,":[139],"system\u2019s":[141],"resilience":[142],"was":[143],"enhanced":[144],"using":[145],"Word2Vec-based":[147],"spelling":[148,172],"correction":[149,173],"layer,":[150],"reducing":[151],"Error":[154],"Rate":[155],"(CER)":[156],"10.37%":[158],"to":[159],"2.47%.":[160],"Comparative":[161],"evaluations":[162],"in-house":[164],"show":[166],"achieves":[174],"highest":[176,197],"precision":[177,202],"(0.9701)":[178],"lowest":[180],"CER":[181,198],"(0.0247),":[182],"outperforming":[183],"Google":[185],"Cloud":[186],"Vision":[187,193],"API\u2019s":[188],"OCR.":[189,213],"In":[190],"contrast,":[191],"API":[194],"has":[195],"(0.1389)":[199],"lower":[201],"(0.8220),":[203],"highlighting":[204],"effectiveness":[206],"approach":[210]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
