{"id":"https://openalex.org/W2115542396","doi":"https://doi.org/10.1109/dial.2004.1263244","title":"Tools for enabling digital access to multi-lingual indic documents","display_name":"Tools for enabling digital access to multi-lingual indic documents","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2115542396","doi":"https://doi.org/10.1109/dial.2004.1263244","mag":"2115542396"},"language":"en","primary_location":{"id":"doi:10.1109/dial.2004.1263244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","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/A5020354604","display_name":"Venu Govindaraju","orcid":"https://orcid.org/0000-0002-5318-7409"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Govindaraju","raw_affiliation_strings":["Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","institution_ids":[]},{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109220916","display_name":"S. Khedekar","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Khedekar","raw_affiliation_strings":["Center of Excellence for Document Analysis and Recognition, State University of New York, University at Buffalo, NY, USA","University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Excellence for Document Analysis and Recognition, State University of New York, University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737","https://openalex.org/I57206974"]},{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018306721","display_name":"Suryaprakash Kompalli","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Kompalli","raw_affiliation_strings":["Center of Excellence for Document Analysis and Recognition, State University of New York, University at Buffalo, NY, USA","University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Excellence for Document Analysis and Recognition, State University of New York, University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737","https://openalex.org/I57206974"]},{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025508406","display_name":"Faisal Farooq","orcid":"https://orcid.org/0000-0002-3551-7371"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. Farooq","raw_affiliation_strings":["Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","institution_ids":[]},{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036052557","display_name":"Srirangaraj Setlur","orcid":"https://orcid.org/0000-0002-7118-9280"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Setlur","raw_affiliation_strings":["Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Excellence for Document Analysis and Recognition, University of Buffallo, NY, USA","institution_ids":[]},{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5097749560","display_name":"R. Vemulapti","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Vemulapti","raw_affiliation_strings":["University at Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.105,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79873097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"122","last_page":"133"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.903288722038269},{"id":"https://openalex.org/keywords/devanagari","display_name":"Devanagari","score":0.7929425239562988},{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.7859069108963013},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.6952946186065674},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.646882951259613},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.6132374405860901},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.610444188117981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5670007467269897},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.561956524848938},{"id":"https://openalex.org/keywords/simple-api-for-xml","display_name":"Simple API for XML","score":0.5310514569282532},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.49245771765708923},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4540945887565613},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.4511135220527649},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.44907480478286743},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.4434036612510681},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24989727139472961},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1972961127758026},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1456441879272461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.903288722038269},{"id":"https://openalex.org/C2780144916","wikidata":"https://www.wikidata.org/wiki/Q38592","display_name":"Devanagari","level":4,"score":0.7929425239562988},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.7859069108963013},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.6952946186065674},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.646882951259613},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.6132374405860901},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.610444188117981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5670007467269897},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.561956524848938},{"id":"https://openalex.org/C8595896","wikidata":"https://www.wikidata.org/wiki/Q577094","display_name":"Simple API for XML","level":5,"score":0.5310514569282532},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.49245771765708923},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4540945887565613},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.4511135220527649},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.44907480478286743},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.4434036612510681},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24989727139472961},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1972961127758026},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1456441879272461},{"id":"https://openalex.org/C34330436","wikidata":"https://www.wikidata.org/wiki/Q979532","display_name":"XML Signature","level":4,"score":0.0},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dial.2004.1263244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dial.2004.1263244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1986216697","https://openalex.org/W2004593540","https://openalex.org/W2022485710","https://openalex.org/W2035575611","https://openalex.org/W2065357722","https://openalex.org/W2075721397","https://openalex.org/W2093402801","https://openalex.org/W2107918262","https://openalex.org/W2128458196","https://openalex.org/W2151537777","https://openalex.org/W2160545881","https://openalex.org/W4205869515","https://openalex.org/W4239875977","https://openalex.org/W6669156104"],"related_works":["https://openalex.org/W2249080376","https://openalex.org/W2131203198","https://openalex.org/W1906114358","https://openalex.org/W4200604753","https://openalex.org/W3004347971","https://openalex.org/W4226502442","https://openalex.org/W111898796","https://openalex.org/W2547590408","https://openalex.org/W2058941326","https://openalex.org/W2605223516"],"abstract_inverted_index":{"We":[0,50,95],"present":[1],"methodologies":[2],"for":[3,32,39,109],"three":[4],"important":[5],"tasks":[6],"that":[7,72],"will":[8],"eventually":[9],"enable":[10],"digital":[11],"access":[12],"of":[13,47,76,106,117,137],"multilingual":[14,113],"Indian":[15,64,81,107],"document":[16,22,30,77,130],"images.":[17],"First,":[18],"we":[19,67],"describe":[20,51,68],"several":[21],"image":[23],"analysis":[24],"techniques":[25],"necessary":[26],"to":[27,62,86,92,134,149,180],"prepare":[28],"Devanagari":[29,42],"images":[31,78],"OCR.":[33],"The":[34,112,175],"second":[35],"task":[36],"is":[37,59,165],"OCR":[38,53],"machine":[40],"printed":[41],"words":[43],"without":[44],"the":[45,52,88,93,118,159,163,184],"help":[46],"a":[48,69,104,127,146],"lexicon.":[49],"methodology":[54],"and":[55,83,100,120,154,172],"show":[56],"how":[57],"it":[58],"being":[60,166],"extended":[61],"other":[63,143],"languages.":[65],"Finally,":[66],"versatile":[70],"platform":[71],"facilitates":[73],"automatic":[74],"segmentation":[75],"in":[79,103,139,142,158],"multiple":[80],"languages":[82,108,144],"an":[84],"interface":[85],"capture":[87],"ground":[89],"truth":[90],"corresponding":[91],"text.":[94],"use":[96],"transliterated":[97],"English":[98],"text":[99,138,164],"virtual":[101],"keyboards":[102],"range":[105],"this":[110],"purpose.":[111],"data":[114,124],"entry":[115],"capabilities":[116],"tool":[119],"its":[121],"underlying":[122],"UNICODE":[123],"representation":[125],"within":[126],"structured":[128],"XML":[129,176],"also":[131],"allow":[132],"users":[133,170],"annotate":[135],"passages":[136],"one":[140],"language":[141],"using":[145],"markup":[147],"scheme":[148],"switch":[150],"between":[151],"scripts.":[152],"Text":[153],"annotations":[155],"are":[156],"rendered":[157],"appropriate":[160],"scripts":[161],"as":[162],"annotated,":[167],"thus":[168],"providing":[169],"prompt":[171],"natural":[173],"feedback.":[174],"back-end":[177],"allows":[178],"meta-data":[179],"be":[181],"recorded":[182],"describing":[183],"annotated":[185],"document.":[186]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
