{"id":"https://openalex.org/W4391093094","doi":"https://doi.org/10.1109/bigdata59044.2023.10386582","title":"Versatile Bengali OCR: Document Analysis Technique for Varied Document Styles and Content","display_name":"Versatile Bengali OCR: Document Analysis Technique for Varied Document Styles and Content","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093094","doi":"https://doi.org/10.1109/bigdata59044.2023.10386582"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386582","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","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/A5061996966","display_name":"AKM Shahariar Azad Rabby","orcid":"https://orcid.org/0000-0003-3994-3105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akm Shahariar Azad Rabby","raw_affiliation_strings":["Apurba Technologies Ltd,Dhaka,Bangladesh","Apurba Technologies Ltd, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apurba Technologies Ltd,Dhaka,Bangladesh","institution_ids":[]},{"raw_affiliation_string":"Apurba Technologies Ltd, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062682992","display_name":"Hasmot Ali","orcid":"https://orcid.org/0000-0002-8885-2501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasmot Ali","raw_affiliation_strings":["Apurba Technologies Ltd,Dhaka,Bangladesh","Apurba Technologies Ltd, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apurba Technologies Ltd,Dhaka,Bangladesh","institution_ids":[]},{"raw_affiliation_string":"Apurba Technologies Ltd, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103722669","display_name":"Md. Majedul Islam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Majedul Islam","raw_affiliation_strings":["Apurba Technologies Ltd,Dhaka,Bangladesh","Apurba Technologies Ltd, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apurba Technologies Ltd,Dhaka,Bangladesh","institution_ids":[]},{"raw_affiliation_string":"Apurba Technologies Ltd, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029426102","display_name":"Fuad Rahman","orcid":"https://orcid.org/0000-0002-8670-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuad Rahman","raw_affiliation_strings":["Apurba Technologies,CA,USA","Apurba Technologies, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apurba Technologies,CA,USA","institution_ids":[]},{"raw_affiliation_string":"Apurba Technologies, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17978084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1965","last_page":"1969"},"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":0.9965999722480774,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.861613929271698},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.8332117795944214},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.7818567752838135},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.758594274520874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6206483244895935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5795251727104187},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5083016753196716},{"id":"https://openalex.org/keywords/intelligent-word-recognition","display_name":"Intelligent word recognition","score":0.5069866180419922},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4963598847389221},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47086870670318604},{"id":"https://openalex.org/keywords/historical-document","display_name":"Historical document","score":0.4474683105945587},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.4395591616630554},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42653828859329224},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.42604172229766846},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.42297592759132385},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.4208782911300659},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4203934669494629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3984176516532898},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39608484506607056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3814515471458435},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.2800882160663605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2611902952194214},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18410760164260864},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13598507642745972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861613929271698},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.8332117795944214},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.7818567752838135},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.758594274520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6206483244895935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5795251727104187},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5083016753196716},{"id":"https://openalex.org/C17649283","wikidata":"https://www.wikidata.org/wiki/Q6044162","display_name":"Intelligent word recognition","level":5,"score":0.5069866180419922},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4963598847389221},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47086870670318604},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.4474683105945587},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.4395591616630554},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42653828859329224},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.42604172229766846},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.42297592759132385},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.4208782911300659},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4203934669494629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3984176516532898},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39608484506607056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3814515471458435},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.2800882160663605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2611902952194214},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18410760164260864},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13598507642745972},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386582","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1756033901","https://openalex.org/W1988520215","https://openalex.org/W1993557076","https://openalex.org/W2001642682","https://openalex.org/W2030881003","https://openalex.org/W2156279557","https://openalex.org/W2968868378","https://openalex.org/W3012078578","https://openalex.org/W3121289818","https://openalex.org/W4206118995","https://openalex.org/W4226051738","https://openalex.org/W4240329257","https://openalex.org/W4304080438","https://openalex.org/W4310501958"],"related_works":["https://openalex.org/W2218402054","https://openalex.org/W4384296853","https://openalex.org/W4309724674","https://openalex.org/W2811459303","https://openalex.org/W2335891253","https://openalex.org/W954954433","https://openalex.org/W54024203","https://openalex.org/W2891374022","https://openalex.org/W2682989974","https://openalex.org/W2183182603"],"abstract_inverted_index":{"In":[0],"our":[1],"research":[2],"paper,":[3],"we":[4],"introduce":[5],"a":[6,91,118],"distinctive":[7],"Bengali":[8,83],"OCR":[9],"system":[10,16,62,127],"that":[11],"boasts":[12],"impressive":[13],"capabilities.":[14],"This":[15],"excels":[17],"in":[18,81,131],"reconstructing":[19],"document":[20,50],"layouts":[21],"while":[22],"maintaining":[23],"the":[24,61,82,132],"integrity":[25],"of":[26,78,139],"structure,":[27],"alignment,":[28],"and":[29,36,57,65,94,100,117,123,134,137],"even":[30],"images.":[31],"It":[32],"integrates":[33],"advanced":[34],"image":[35],"signature":[37,109],"detection":[38],"for":[39,45,121],"precise":[40],"extraction.":[41],"Specifically,":[42],"tailored":[43],"models":[44],"word":[46,101],"segmentation":[47],"accommodate":[48],"various":[49],"types,":[51],"such":[52],"as":[53],"computer-compose,":[54],"letterpress,":[55],"typewritten,":[56],"handwritten":[58,67],"documents.":[59],"Notably,":[60],"handles":[63],"static":[64],"dynamic":[66],"inputs,":[68],"recognizing":[69],"diverse":[70,92],"writing":[71],"styles.":[72],"Additionally,":[73],"it":[74],"achieves":[75],"remarkable":[76],"recognition":[77],"compound":[79],"characters":[80],"language.":[84],"The":[85,126],"comprehensive":[86],"data":[87],"collection":[88],"contributes":[89],"to":[90],"corpus,":[93],"sophisticated":[95],"technical":[96],"components":[97],"enhance":[98],"character":[99],"recognition.":[102],"Other":[103],"notable":[104],"features":[105],"include":[106],"image,":[107],"logo,":[108],"recognition,":[110,112],"table":[111],"perspective":[113],"correction,":[114],"layout":[115],"reconstruction,":[116],"queuing":[119],"module":[120],"efficient":[122,133],"scalable":[124],"processing.":[125],"showcases":[128],"exceptional":[129],"performance":[130],"accurate":[135],"extraction":[136],"analysis":[138],"text.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}