{"id":"https://openalex.org/W1970246874","doi":"https://doi.org/10.1145/2432553.2432569","title":"Choice of recognizable units for URDU OCR","display_name":"Choice of recognizable units for URDU OCR","publication_year":2012,"publication_date":"2012-12-16","ids":{"openalex":"https://openalex.org/W1970246874","doi":"https://doi.org/10.1145/2432553.2432569","mag":"1970246874"},"language":"en","primary_location":{"id":"doi:10.1145/2432553.2432569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2432553.2432569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceeding of the workshop on Document Analysis and Recognition","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/A5025442453","display_name":"Gurpreet Singh Lehal","orcid":"https://orcid.org/0000-0001-6152-8050"},"institutions":[{"id":"https://openalex.org/I79161377","display_name":"Punjabi University","ror":"https://ror.org/00xdn8y92","country_code":"IN","type":"education","lineage":["https://openalex.org/I79161377"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gurpreet Singh Lehal","raw_affiliation_strings":["Punjabi University, Patiala"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Punjabi University, Patiala","institution_ids":["https://openalex.org/I79161377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025442453"],"corresponding_institution_ids":["https://openalex.org/I79161377"],"apc_list":null,"apc_paid":null,"fwci":3.3308,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.92879983,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9970999956130981,"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":0.9970999956130981,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9661999940872192,"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/urdu","display_name":"Urdu","score":0.8281528949737549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7138071656227112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849441885948181},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.518756628036499},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5085464715957642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48587435483932495},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47696220874786377},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45105233788490295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44828733801841736},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41901612281799316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21293601393699646},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16868329048156738},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11461380124092102},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07289600372314453}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.8281528949737549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138071656227112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849441885948181},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.518756628036499},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5085464715957642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48587435483932495},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47696220874786377},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45105233788490295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44828733801841736},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41901612281799316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21293601393699646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16868329048156738},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11461380124092102},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07289600372314453},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2432553.2432569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2432553.2432569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceeding of the workshop on Document Analysis and Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1876505772","https://openalex.org/W2040750724","https://openalex.org/W2077966050","https://openalex.org/W2337070345","https://openalex.org/W4240982680","https://openalex.org/W6639364484","https://openalex.org/W6703076633"],"related_works":["https://openalex.org/W1588484110","https://openalex.org/W1566901819","https://openalex.org/W604003083","https://openalex.org/W597280011","https://openalex.org/W4310798948","https://openalex.org/W642060233","https://openalex.org/W4389314469","https://openalex.org/W1991513203","https://openalex.org/W3197118814","https://openalex.org/W3178467699"],"abstract_inverted_index":{"There":[0],"has":[1,261],"been":[2,262],"considerable":[3],"work":[4,11],"on":[5,14,21],"Arabic":[6,22],"OCR.":[7],"However,":[8],"all":[9,109],"that":[10],"is":[12,19,72,82,96,106,152,240],"based":[13,20],"Naskh":[15],"style.":[16,27],"Urdu":[17,94,125,132,268],"script":[18],"alphabet,":[23],"but":[24],"uses":[25],"Nastalique":[26,29],"The":[28,134,194],"style":[30],"makes":[31],"OCR":[32,172],"in":[33,38,56,246],"general":[34],"and":[35,54,78,91,129,145,165,187,213,216,244,252],"character":[36,51,77],"segmentation":[37,52],"particular,":[39],"a":[40,83,121,149,154,176,253],"highly":[41],"challenging":[42],"task,":[43],"so":[44],"most":[45],"of":[46,60,86,98,108,124,136,147,174,201,256,267],"the":[47,50,64,131,162,198,202,205,211,221,225,228,249],"researchers":[48,71],"avoid":[49],"phase":[53],"go":[55],"for":[57,112,167],"higher":[58,66],"unit":[59,68],"recognition.":[61],"For":[62,115],"Urdu,":[63],"next":[65],"recognition":[67,113,146,169,259],"considered":[69],"by":[70],"ligature,":[73,203],"which":[74,264],"lies":[75],"between":[76],"word.":[79],"A":[80,103],"ligature":[81,177],"connected":[84,185,192,207],"component":[85,186,196,208],"one":[87,183],"or":[88,189],"more":[89,142,190],"characters":[90],"usually":[92],"an":[93],"word":[95],"composed":[97],"1":[99],"to":[100,127,140,160,210,242],"8":[101],"ligatures.":[102,133],"related":[104],"issue":[105],"identification":[107],"possible":[110],"ligatures":[111,138,229],"purpose.":[114],"this":[116],"purpose,":[117],"we":[118],"have":[119],"performed":[120,241],"statistical":[122,238],"analysis":[123,239],"corpus":[126],"collect":[128],"organise":[130],"number":[135],"unique":[137],"comes":[139],"be":[141,180],"than":[143],"26,000,":[144],"such":[148],"huge":[150],"class":[151,163,226,255],"again":[153],"Herculean":[155],"task.":[156],"It":[157],"becomes":[158],"necessary":[159],"reduce":[161,224],"count":[164,243],"look":[166],"alternative":[168],"unit.":[170],"From":[171],"point":[173],"view,":[175],"can":[178],"further":[179],"segmented":[181],"into":[182],"primary":[184,195,232,250],"zero":[188],"secondary":[191,206],"components.":[193],"represents":[197],"basic":[199],"shape":[200],"while":[204],"corresponds":[209],"dots":[212],"diacritics":[214],"marks":[215],"special":[217],"symbols":[218],"associated":[219],"with":[220,230],"ligature.":[222],"To":[223],"count,":[227],"similar":[231],"components":[233,251],"are":[234],"clubbed":[235],"together.":[236],"Further":[237],"arrange":[245],"descending":[247],"order":[248],"manageable":[254],"around":[257],"2300":[258],"units":[260],"generated,":[263],"covers":[265],"99%":[266],"corpus.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
