{"id":"https://openalex.org/W4390533099","doi":"https://doi.org/10.1145/3632410.3632502","title":"IndicOCR: A Pipeline for Recognizing Printed Documents for Indian Languages","display_name":"IndicOCR: A Pipeline for Recognizing Printed Documents for Indian Languages","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390533099","doi":"https://doi.org/10.1145/3632410.3632502"},"language":"en","primary_location":{"id":"doi:10.1145/3632410.3632502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science &amp; Management of Data (11th ACM IKDD CODS and 29th COMAD)","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/A5058942781","display_name":"Krishna Tulsyan","orcid":"https://orcid.org/0000-0003-0177-588X"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Krishna Tulsyan","raw_affiliation_strings":["International Institute of Information Technology, India"],"raw_orcid":"https://orcid.org/0000-0003-0177-588X","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093643283","display_name":"Tessy Flemin","orcid":"https://orcid.org/0009-0001-1674-9759"},"institutions":[{"id":"https://openalex.org/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tessy Flemin","raw_affiliation_strings":["International Institute of Information Technology, India"],"raw_orcid":"https://orcid.org/0009-0001-1674-9759","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]},{"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/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ajoy Mondal","raw_affiliation_strings":["International Institute of Information Technology, India"],"raw_orcid":"https://orcid.org/0000-0002-4808-8860","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]},{"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/I188963388","display_name":"International Institute of Information Technology","ror":"https://ror.org/02dernx73","country_code":"IN","type":"education","lineage":["https://openalex.org/I188963388"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C V Jawahar","raw_affiliation_strings":["International Institute of Information Technology, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, India","institution_ids":["https://openalex.org/I188963388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058942781"],"corresponding_institution_ids":["https://openalex.org/I188963388"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44122314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"519","last_page":"522"},"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":0.9926000237464905,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9918000102043152,"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/bridging","display_name":"Bridging (networking)","score":0.778907299041748},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6913663148880005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6364014148712158},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6236593723297119},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5363290309906006},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.4673234522342682},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.44318264722824097},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.42329761385917664},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4188094735145569},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35882705450057983},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35659587383270264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35462796688079834},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3228534460067749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30091768503189087},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.2593556344509125},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.19088423252105713},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11592823266983032},{"id":"https://openalex.org/keywords/anthropology","display_name":"Anthropology","score":0.10464510321617126},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09070208668708801},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08647114038467407}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.778907299041748},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6913663148880005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6364014148712158},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6236593723297119},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5363290309906006},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.4673234522342682},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.44318264722824097},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.42329761385917664},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4188094735145569},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35882705450057983},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35659587383270264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35462796688079834},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3228534460067749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30091768503189087},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2593556344509125},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.19088423252105713},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11592823266983032},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.10464510321617126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09070208668708801},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08647114038467407},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3632410.3632502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3632410.3632502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Joint International Conference on Data Science &amp; Management of Data (11th ACM IKDD CODS and 29th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3083907077","https://openalex.org/W3197061335"],"related_works":["https://openalex.org/W2344247273","https://openalex.org/W2780279436","https://openalex.org/W2786752243","https://openalex.org/W1512334992","https://openalex.org/W4290785358","https://openalex.org/W2387970992","https://openalex.org/W2724898345","https://openalex.org/W2566805851","https://openalex.org/W907309559","https://openalex.org/W1561849055"],"abstract_inverted_index":{"India\u2019s":[0,78],"linguistic":[1,79],"diversity":[2],"is":[3,44,47,88],"a":[4,89,98],"testament":[5],"to":[6,38,55,62],"the":[7,11,28,39,66,75,82],"cultural":[8],"richness":[9],"of":[10,41,68],"subcontinent,":[12],"with":[13],"22":[14],"officially":[15],"recognized":[16],"languages,":[17],"each":[18],"possessing":[19],"its":[20,71],"unique":[21],"script":[22],"and":[23,81,95],"identity.":[24],"In":[25],"this":[26,57],"context,":[27],"need":[29],"for":[30,92],"efficient":[31],"Optical":[32],"Character":[33],"Recognition":[34],"(OCR)":[35],"tools":[36],"tailored":[37],"complexities":[40],"these":[42],"languages":[43],"paramount.":[45],"IndicOCR":[46],"introduced":[48],"as":[49],"an":[50],"innovative":[51],"OCR":[52],"pipeline":[53],"designed":[54],"address":[56],"challenge.":[58],"This":[59],"paper":[60],"aims":[61],"shed":[63],"light":[64],"on":[65],"capabilities":[67],"IndicOCR,":[69],"underlining":[70],"role":[72],"in":[73,97],"bridging":[74],"gap":[76],"between":[77],"heritage":[80],"ever-expanding":[83],"digital":[84],"world.":[85],"Finally,":[86],"IndicOCR1":[87],"powerful":[90],"tool":[91],"inclusivity,":[93],"preservation,":[94],"progress":[96],"linguistically":[99],"diverse":[100],"society.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
