{"id":"https://openalex.org/W4224305666","doi":"https://doi.org/10.1145/3511807","title":"A Deep OCR for Degraded Bangla Documents","display_name":"A Deep OCR for Degraded Bangla Documents","publication_year":2022,"publication_date":"2022-04-20","ids":{"openalex":"https://openalex.org/W4224305666","doi":"https://doi.org/10.1145/3511807"},"language":"en","primary_location":{"id":"doi:10.1145/3511807","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511807","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5027556687","display_name":"Ayan Chaudhury","orcid":"https://orcid.org/0000-0002-6474-5090"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["FR","IN"],"is_corresponding":false,"raw_author_name":"Ayan Chaudhury","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, France and IIT Kharagpur, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0002-6474-5090","affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, France and IIT Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101478043","display_name":"Partha Sarathi Mukherjee","orcid":"https://orcid.org/0000-0002-9254-5416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Partha Sarathi Mukherjee","raw_affiliation_strings":["Tatras Data, New Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-9254-5416","affiliations":[{"raw_affiliation_string":"Tatras Data, New Delhi, Delhi, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022451403","display_name":"Sudip Das","orcid":"https://orcid.org/0000-0001-6069-0240"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudip Das","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0001-6069-0240","affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, West Bengal, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037394429","display_name":"C. Biswas","orcid":"https://orcid.org/0000-0003-4468-7396"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandan Biswas","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, West Bengal, India"],"raw_orcid":"https://orcid.org/0000-0003-4468-7396","affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, West Bengal, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090127362","display_name":"Ujjwal Bhattacharya","orcid":"https://orcid.org/0000-0002-8546-6453"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ujjwal Bhattacharya","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-8546-6453","affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5669,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.61645852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"5","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9923999905586243,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9878000020980835,"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":0.8583464622497559},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7474084496498108},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7467912435531616},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.7321525812149048},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5649469494819641},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.48513326048851013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4793151617050171},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.4439897835254669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4397527575492859},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43819770216941833},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43728089332580566},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.42739999294281006},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42350390553474426},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4225088357925415},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25302523374557495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8583464622497559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7474084496498108},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7467912435531616},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.7321525812149048},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5649469494819641},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.48513326048851013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4793151617050171},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.4439897835254669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4397527575492859},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43819770216941833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43728089332580566},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.42739999294281006},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42350390553474426},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4225088357925415},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25302523374557495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511807","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511807","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W154676388","https://openalex.org/W974261621","https://openalex.org/W1877461882","https://openalex.org/W1998157976","https://openalex.org/W2038037829","https://openalex.org/W2078831724","https://openalex.org/W2083970667","https://openalex.org/W2090665535","https://openalex.org/W2095428880","https://openalex.org/W2113137767","https://openalex.org/W2124351162","https://openalex.org/W2127141656","https://openalex.org/W2128060444","https://openalex.org/W2133059825","https://openalex.org/W2133564696","https://openalex.org/W2135306864","https://openalex.org/W2143516773","https://openalex.org/W2172987025","https://openalex.org/W2273972066","https://openalex.org/W2506392221","https://openalex.org/W2554423077","https://openalex.org/W2577946330","https://openalex.org/W2594443378","https://openalex.org/W2731900166","https://openalex.org/W2751352153","https://openalex.org/W2759766068","https://openalex.org/W2767609405","https://openalex.org/W2775587054","https://openalex.org/W2781914340","https://openalex.org/W2891730703","https://openalex.org/W2898250319","https://openalex.org/W2945259612","https://openalex.org/W2950534334","https://openalex.org/W2963746531","https://openalex.org/W3021084640","https://openalex.org/W3126614186","https://openalex.org/W3134079985","https://openalex.org/W3155464240","https://openalex.org/W3171213534","https://openalex.org/W3180901325","https://openalex.org/W3183743448","https://openalex.org/W4206209937","https://openalex.org/W4239510810","https://openalex.org/W4297734170","https://openalex.org/W4302061398","https://openalex.org/W6679351980","https://openalex.org/W6729856380","https://openalex.org/W6734555034","https://openalex.org/W6745535286","https://openalex.org/W6745903366"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2511246383","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2403176590"],"abstract_inverted_index":{"Despite":[0],"the":[1,71,76,82,92,101,129,160,166,194,218,272,277,280,283],"significant":[2],"success":[3],"of":[4,14,26,70,81,100,154,168,220,271,276,282],"document":[5,16,33,102,121,249,261],"image":[6,250,262],"analysis":[7],"techniques,":[8],"efficient":[9],"Optical":[10],"Character":[11],"Recognition":[12],"(OCR)":[13],"degraded":[15,32,55,118,157,247,258],"images":[17,181],"still":[18],"remains":[19],"an":[20,65,208],"open":[21],"problem.":[22],"Although":[23],"a":[24,54,59,109,134,171,185,201,212,232,244,256,269],"body":[25],"work":[27],"has":[28,41,217,265],"been":[29,42,266],"reported":[30],"on":[31,52,243,255],"recognition":[34,80],"for":[35,57,117,151],"English":[36],"language,":[37],"only":[38],"little":[39],"attention":[40],"paid":[43],"to":[44,90,97,170,190,199,211],"Indic":[45],"scripts.":[46],"In":[47,63,104,128,159,193],"this":[48,105,229],"work,":[49],"we":[50,107,132,147,164,197],"focus":[51],"developing":[53],"OCR":[56,66,111],"Bangla,":[58],"major":[60],"Indian":[61],"language.":[62],"general,":[64],"system":[67,112],"includes":[68],"segmentation":[69,87,153],"foreground":[72,93,152,186],"text":[73,86],"part":[74,270],"from":[75,156],"background":[77,95,188],"followed":[78],"by":[79],"extracted":[83],"text.":[84,158],"The":[85,123],"module":[88],"aims":[89],"assign":[91,184],"or":[94,187],"label":[96,189],"each":[98,191],"pixel":[99],"image.":[103],"paper,":[106],"present":[108,273],"new":[110,202,257],"which":[113,216,264],"is":[114,125],"particularly":[115],"suitable":[116],"quality":[119],"Bangla":[120,248],"images.":[122],"contribution":[124],"two":[126],"fold.":[127],"first":[130],"phase,":[131,196],"use":[133,200],"semi-supervised":[135],"Markov":[136],"Random":[137],"Field":[138],"(MRF)-":[139],"based":[140,204,234],"Generative":[141],"Adversarial":[142],"Network":[143],"(GAN)":[144],"model":[145],"(which":[146],"call":[148],"MRF-GAN":[149,162],")":[150],"texts":[155],"proposed":[161,284],",":[163],"extend":[165],"concept":[167],"GAN":[169],"multitask":[172],"learning":[173],"mechanism":[174],"where":[175],"discriminator-classifier":[176],"networks":[177],"differentiate":[178],"between":[179],"real/fake":[180],"and":[182],"also":[183],"pixel.":[192],"second":[195],"propose":[198],"encoder-decoder":[203],"recognizer":[205],"that":[206],"incorporates":[207],"attention-based":[209],"character":[210],"word":[213],"prediction":[214],"model,":[215],"capability":[219],"minimizing":[221],"Word":[222],"Error":[223],"Rate":[224],"(WER)":[225],".":[226,239],"We":[227,240],"optimize":[228],"network":[230],"using":[231],"Multitask":[233],"Transfer":[235],"Learning":[236],"scheme":[237],"(MTTL)":[238],"perform":[241],"experiments":[242],"publicly":[245],"available":[246],"dataset":[251],"as":[252,254,268],"well":[253],"printed":[259],"Hindi":[260],"dataset,":[263],"created":[267],"study.":[274],"Results":[275],"experimentations":[278],"demonstrate":[279],"efficacy":[281],"OCR.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}