{"id":"https://openalex.org/W2401776823","doi":"https://doi.org/10.1145/2846093","title":"Printed Text Image Database for Sindhi OCR","display_name":"Printed Text Image Database for Sindhi OCR","publication_year":2016,"publication_date":"2016-05-16","ids":{"openalex":"https://openalex.org/W2401776823","doi":"https://doi.org/10.1145/2846093","mag":"2401776823"},"language":"en","primary_location":{"id":"doi:10.1145/2846093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2846093","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/A5042990967","display_name":"Dil Nawaz Hakro","orcid":"https://orcid.org/0000-0001-9532-4013"},"institutions":[{"id":"https://openalex.org/I126131087","display_name":"University of Sindh","ror":"https://ror.org/01d692d57","country_code":"PK","type":"education","lineage":["https://openalex.org/I126131087"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Dil Nawaz Hakro","raw_affiliation_strings":["University of Sindh, Jamshoro, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sindh, Jamshoro, Pakistan","institution_ids":["https://openalex.org/I126131087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023964721","display_name":"Abdullah Zawawi Talib","orcid":"https://orcid.org/0000-0002-9610-4060"},"institutions":[{"id":"https://openalex.org/I139322472","display_name":"Universiti Sains Malaysia","ror":"https://ror.org/02rgb2k63","country_code":"MY","type":"education","lineage":["https://openalex.org/I139322472"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Abdullah Zawawi Talib","raw_affiliation_strings":["Universiti Sains Malaysia, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universiti Sains Malaysia, Malaysia","institution_ids":["https://openalex.org/I139322472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042990967"],"corresponding_institution_ids":["https://openalex.org/I126131087"],"apc_list":null,"apc_paid":null,"fwci":0.6758,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.76623633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"4","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9954000115394592,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.993399977684021,"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/cursive","display_name":"Cursive","score":0.9206489324569702},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8412030935287476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689383864402771},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6031153202056885},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.5856552720069885},{"id":"https://openalex.org/keywords/arabic-script","display_name":"Arabic script","score":0.5246517658233643},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4938698410987854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4494955241680145},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3968769311904907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36945149302482605},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.3503747284412384},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26200786232948303},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2434326708316803},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10729649662971497}],"concepts":[{"id":"https://openalex.org/C2778943297","wikidata":"https://www.wikidata.org/wiki/Q1079418","display_name":"Cursive","level":2,"score":0.9206489324569702},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8412030935287476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689383864402771},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6031153202056885},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.5856552720069885},{"id":"https://openalex.org/C2777323237","wikidata":"https://www.wikidata.org/wiki/Q1828555","display_name":"Arabic script","level":3,"score":0.5246517658233643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4938698410987854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4494955241680145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3968769311904907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36945149302482605},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3503747284412384},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26200786232948303},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2434326708316803},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10729649662971497},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2846093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2846093","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1973279663","https://openalex.org/W1987122909","https://openalex.org/W1993312227","https://openalex.org/W2123191374","https://openalex.org/W2156928014","https://openalex.org/W2169849667","https://openalex.org/W2278589493","https://openalex.org/W2520933715","https://openalex.org/W2522933863","https://openalex.org/W2889784708"],"related_works":["https://openalex.org/W2188440461","https://openalex.org/W2120407907","https://openalex.org/W2557740161","https://openalex.org/W3035903760","https://openalex.org/W2016860631","https://openalex.org/W1985694112","https://openalex.org/W4309734222","https://openalex.org/W1996264080","https://openalex.org/W3108981824","https://openalex.org/W3087330769"],"abstract_inverted_index":{"Document":[0,6],"Image":[1],"Understanding":[2],"(DIU)":[3],"and":[4,19,60,72,77,138,146,163,175,189,210,220],"Electronic":[5],"Management":[7],"are":[8,52,125],"active":[9],"fields":[10],"of":[11,21,31,79,91,148,239],"research":[12,39,137],"involving":[13],"image":[14,201],"understanding,":[15],"interpretation,":[16],"efficient":[17],"handling,":[18],"routing":[20],"documents":[22],"as":[23,25,227],"well":[24],"their":[26],"retrieval.":[27],"Research":[28],"on":[29,40,55],"most":[30],"the":[32,41,56,66,70,88,92,99,111,122,240],"noncursive":[33],"scripts":[34,44,58,62,81],"(Latin)":[35],"has":[36,87],"matured,":[37],"whereas":[38],"cursive":[42,57],"(connected)":[43],"is":[45,142,224],"still":[46],"moving":[47],"toward":[48],"perfection.":[49],"Many":[50],"researchers":[51],"currently":[53],"working":[54],"(Arabic":[59],"other":[61],"adopting":[63,98],"it)":[64],"around":[65],"world":[67],"so":[68],"that":[69,206],"difficulties":[71],"challenges":[73],"in":[74,110,115,167,171],"document":[75,205],"understanding":[76],"handling":[78],"these":[80],"can":[82],"be":[83],"overcome.":[84],"Sindhi":[85,135,149],"script":[86],"largest":[89],"extension":[90],"original":[93,112],"Arabic":[94,100,113],"alphabet":[95],"among":[96],"languages":[97],"script;":[101],"it":[102],"contains":[103],"52":[104],"characters,":[105,216],"compared":[106],"to":[107,117,197,237],"28":[108],"characters":[109,128,166,217],"alphabet,":[114],"order":[116],"accommodate":[118],"more":[119],"sounds":[120],"for":[121,144],"language.":[123],"There":[124],"24":[126],"differentiating":[127],"with":[129,218],"some":[130],"possessing":[131],"four":[132,172,176],"dots.":[133],"For":[134],"OCR":[136],"development,":[139],"a":[140,155,199,203,228],"database":[141,157,179,213,223,232],"needed":[143],"training":[145],"testing":[147],"text":[150,200,204],"images.":[151],"We":[152],"have":[153],"developed":[154,196],"large":[156],"containing":[158],"over":[159],"4":[160],"billion":[161,165],"words":[162],"15":[164],"150":[168],"various":[169,184,208],"fonts":[170,209],"font":[173],"weights":[174],"styles.":[177],"The":[178,212,222],"contents":[180],"were":[181],"collected":[182],"from":[183,202],"sources":[185],"including":[186],"websites,":[187],"books,":[188],"theses.":[190],"A":[191],"custom-built":[192],"application":[193],"was":[194],"also":[195],"create":[198],"supports":[207],"sizes.":[211],"considers":[214],"words,":[215],"spaces,":[219],"lines.":[221],"freely":[225],"available":[226],"partial":[229],"or":[230],"full":[231],"by":[233],"sending":[234],"an":[235],"email":[236],"one":[238],"authors.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
