{"id":"https://openalex.org/W7172009436","doi":"https://doi.org/10.1145/3774521.3774605","title":"SemiHastakshar: Generalizable Indic Handwritten OCR through Semi-Supervised Learning","display_name":"SemiHastakshar: Generalizable Indic Handwritten OCR through Semi-Supervised Learning","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7172009436","doi":"https://doi.org/10.1145/3774521.3774605"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774605","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144136458","display_name":"Lalitha Evani","orcid":"https://orcid.org/0009-0004-4195-1678"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lalitha Evani","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0004-4195-1678","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052301812","display_name":"Ajoy Mondal","orcid":"https://orcid.org/0000-0002-4808-8860"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ajoy Mondal","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0002-4808-8860","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jawahar C. V.","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.6686000227928162},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.546999990940094},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.49459999799728394},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48080000281333923},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.453000009059906},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.40059998631477356},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.38339999318122864},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.3833000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6902999877929688},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.49459999799728394},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4099000096321106},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.29899999499320984},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774605","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1966942993","https://openalex.org/W1992705268","https://openalex.org/W2048679005","https://openalex.org/W2064878315","https://openalex.org/W2108610317","https://openalex.org/W2116741014","https://openalex.org/W2122585011","https://openalex.org/W2359126565","https://openalex.org/W2573612273","https://openalex.org/W2573965845","https://openalex.org/W2790215293","https://openalex.org/W2890688138","https://openalex.org/W2903727039","https://openalex.org/W2967615747","https://openalex.org/W3118722186","https://openalex.org/W3177684257","https://openalex.org/W3197061335","https://openalex.org/W4234881927","https://openalex.org/W4287322212","https://openalex.org/W4312879041","https://openalex.org/W4372355580","https://openalex.org/W4391342156","https://openalex.org/W4403790045","https://openalex.org/W4413156663"],"related_works":[],"abstract_inverted_index":{"Handwritten":[0],"Text":[1],"Recognition":[2],"(HTR)":[3],"remains":[4],"a":[5,54,73,90,106,113],"challenging":[6],"task,":[7],"especially":[8],"in":[9,41,47,129],"Indic":[10,124],"languages,":[11],"due":[12],"to":[13,77,87,118],"varied":[14],"handwriting":[15,94],"styles,":[16],"complex":[17],"character":[18],"structures,":[19],"and":[20,96,135],"the":[21,69,85],"scarcity":[22],"of":[23,93,109],"annotated":[24],"data.":[25],"While":[26],"deep":[27],"learning":[28],"models":[29,122],"have":[30],"shown":[31],"promising":[32],"results":[33],"on":[34,79],"curated":[35],"benchmarks,":[36],"their":[37],"performance":[38],"often":[39],"degrades":[40],"real-world":[42],"scenarios":[43],"with":[44,112],"high":[45],"variability":[46],"writing.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"semi-supervised":[55],"approach,":[56],"SemiHastakshar,":[57],"that":[58,104],"leverages":[59],"large-scale":[60],"unlabeled":[61,80,115],"word-level":[62],"images":[63],"collected":[64],"from":[65,89],"diverse":[66],"sources":[67],"across":[68,99],"Internet.":[70],"We":[71],"employ":[72],"high-confidence":[74],"pseudo-labeling":[75],"strategy":[76],"train":[78],"samples":[81],"iteratively.":[82],"It":[83],"allows":[84],"model":[86],"learn":[88],"wider":[91],"distribution":[92],"styles":[95],"improve":[97],"generalization":[98],"writers.":[100],"Our":[101],"method":[102],"demonstrates":[103],"combining":[105],"small":[107],"amount":[108],"labeled":[110],"data":[111,136],"large":[114],"corpus":[116],"leads":[117],"more":[119],"robust":[120],"HTR":[121],"for":[123,141],"scripts,":[125],"advancing":[126],"scalable":[127],"recognition":[128],"low-resource":[130],"settings.":[131],"The":[132],"code,":[133],"model,":[134],"will":[137],"be":[138],"publicly":[139],"available":[140],"research.":[142]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}