{"id":"https://openalex.org/W6944784367","doi":"https://doi.org/10.21227/656q-hc18","title":"MDIW-13 MultiScript Document Database","display_name":"MDIW-13 MultiScript Document Database","publication_year":2019,"publication_date":"2019-10-25","ids":{"openalex":"https://openalex.org/W6944784367","doi":"https://doi.org/10.21227/656q-hc18"},"language":"en","primary_location":{"id":"doi:10.21227/656q-hc18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/656q-hc18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/656q-hc18","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ferrer, Miguel A","orcid":"https://orcid.org/0000-0002-2924-1225"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ferrer, Miguel A","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Das, Abhijit","orcid":"https://orcid.org/0000-0002-6793-0582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Abhijit","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Diaz, Moises","orcid":"https://orcid.org/0000-0003-3878-3867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diaz, Moises","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Carmona-Duarte, Cristina","orcid":"https://orcid.org/0000-0002-4441-6652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carmona-Duarte, Cristina","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Pal, Umapada","orcid":"https://orcid.org/0000-0002-5426-2618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pal, Umapada","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8360000252723694},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.6043999791145325},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5817999839782715},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.510699987411499},{"id":"https://openalex.org/keywords/document-processing","display_name":"Document processing","score":0.3801000118255615},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.3652999997138977}],"concepts":[{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8360000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154000043869019},{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.6043999791145325},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4871000051498413},{"id":"https://openalex.org/C67905146","wikidata":"https://www.wikidata.org/wiki/Q5287646","display_name":"Document processing","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C2778371909","wikidata":"https://www.wikidata.org/wiki/Q3771738","display_name":"Historical document","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2988504005","wikidata":"https://www.wikidata.org/wiki/Q379942","display_name":"Document image processing","level":4,"score":0.2685000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/656q-hc18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/656q-hc18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.21227/656q-hc18","is_oa":true,"landing_page_url":"https://doi.org/10.21227/656q-hc18","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8419045209884644,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wide":[0],"varieties":[1],"of":[2,30,61,120,141,168],"scripts":[3,25],"are":[4,65,73,158],"used":[5,26],"in":[6,27,50,175],"writing":[7],"languages":[8],"throughout":[9],"the":[10,23,35,51,176],"world.":[11],"In":[12],"a":[13,31,90,105,117,165],"multiscript":[14,106],"and":[15,53,67,70,87,112,136,153,162,170,173],"multi-language":[16],"environment,":[17],"it":[18],"is":[19,95],"necessary":[20],"to":[21,33],"know":[22],"different":[24,85],"every":[28],"part":[29],"document":[32,37],"apply":[34],"appropriate":[36],"analysis":[38],"algorithm.":[39],"Consequently,":[40],"several":[41],"approaches":[42],"for":[43,164],"automatic":[44],"script":[45,88],"identification":[46],"have":[47,81],"been":[48,82],"proposed":[49],"literature,":[52],"can":[54],"be":[55],"broadly":[56],"classified":[57],"under":[58],"two":[59],"categories":[60],"techniques:":[62],"those":[63,71],"that":[64,72],"structure":[66],"visual":[68],"appearance-based":[69],"deep":[74],"learning-based.":[75],"Incidentally,":[76],"since":[77],"most":[78],"existing":[79],"techniques":[80],"tested":[83],"using":[84],"datasets":[86],"combinations,":[89],"fair":[91],"comparison":[92],"between":[93],"them":[94],"difficult.":[96],"To":[97],"alleviate":[98],"this":[99,101],"drawback,":[100],"paper":[102],"therefore":[103],"introduces":[104],"database,":[107],"which":[108],"contains":[109],"both":[110],"printed":[111],"handwritten":[113,151],"documents":[114,143,157],"obtained":[115],"from":[116,145],"wide":[118],"variety":[119],"scripts,":[121],"such":[122],"as":[123,148,150],"Arabic,":[124],"Bengali,":[125],"Gujarati,":[126],"Gurmukhi,":[127],"Devanagari,":[128],"Japanese,":[129],"Kannada,":[130],"Malayalam,":[131],"Oriya,":[132],"Roman,":[133],"Tamil,":[134],"Telugu":[135],"Thai.":[137],"The":[138],"dataset":[139],"consists":[140],"1137":[142],"scanned":[144],"local":[146],"newspapers,":[147],"well":[149],"letters":[152],"notes.":[154],"Further,":[155],"these":[156],"segmented":[159],"into":[160],"lines":[161,172],"words,":[163],"total,":[166],"respectively,":[167],"13,983":[169],"86,675":[171],"words":[174],"dataset.":[177]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
