{"id":"https://openalex.org/W4413468805","doi":"https://doi.org/10.31449/inf.v49i28.8341","title":"Gujarati Optical Character Recognition Using Efficient Text Feature Extraction Approaches","display_name":"Gujarati Optical Character Recognition Using Efficient Text Feature Extraction Approaches","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4413468805","doi":"https://doi.org/10.31449/inf.v49i28.8341"},"language":"en","primary_location":{"id":"doi:10.31449/inf.v49i28.8341","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v49i28.8341","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/8341/4640","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.informatica.si/index.php/informatica/article/download/8341/4640","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084400392","display_name":"Avani Samir Bhuva","orcid":null},"institutions":[{"id":"https://openalex.org/I2802985673","display_name":"Cooper Hospital","ror":"https://ror.org/02ry07h90","country_code":"IN","type":"healthcare","lineage":["https://openalex.org/I2802985673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avani Samir Bhuva","raw_affiliation_strings":["opp. Cooper Hospital , Navpada , Suvarna Nagar , Vile Parle West , Mumbai , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"opp. Cooper Hospital , Navpada , Suvarna Nagar , Vile Parle West , Mumbai , India","institution_ids":["https://openalex.org/I2802985673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054217809","display_name":"Dhirendra Mishra","orcid":"https://orcid.org/0000-0002-2864-7354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhirendra Mishra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.89416263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"49","issue":"28","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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":0.989799976348877,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9431999921798706,"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/gujarati","display_name":"Gujarati","score":0.9177481532096863},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7651557922363281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6269475817680359},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.6071892380714417},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6065398454666138},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5982862710952759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5803120732307434},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5282765030860901},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5171874761581421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40108722448349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17829570174217224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11809346079826355},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10241377353668213}],"concepts":[{"id":"https://openalex.org/C2779296024","wikidata":"https://www.wikidata.org/wiki/Q5137","display_name":"Gujarati","level":2,"score":0.9177481532096863},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7651557922363281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269475817680359},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.6071892380714417},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6065398454666138},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5982862710952759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5803120732307434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5282765030860901},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5171874761581421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40108722448349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17829570174217224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11809346079826355},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10241377353668213},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31449/inf.v49i28.8341","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v49i28.8341","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/8341/4640","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31449/inf.v49i28.8341","is_oa":true,"landing_page_url":"https://doi.org/10.31449/inf.v49i28.8341","pdf_url":"https://www.informatica.si/index.php/informatica/article/download/8341/4640","source":{"id":"https://openalex.org/S4210173311","display_name":"Informatica","issn_l":"0350-5596","issn":["0350-5596","1854-3871"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310314525","host_organization_name":"Slovenian Society Informatika","host_organization_lineage":["https://openalex.org/P4310314525"],"host_organization_lineage_names":["Slovenian Society Informatika"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Informatica","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413468805.pdf","grobid_xml":"https://content.openalex.org/works/W4413468805.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4318570590","https://openalex.org/W2766784770","https://openalex.org/W2140481866","https://openalex.org/W3124581537","https://openalex.org/W1991513203","https://openalex.org/W2892704491","https://openalex.org/W3178467699","https://openalex.org/W4312612713","https://openalex.org/W4408696804","https://openalex.org/W2794921479"],"abstract_inverted_index":{"India":[0],"isthe":[1],"most":[2],"populous":[3],"country,":[4],"with":[5,74,139,144,169],"22":[6],"official":[7],"regional":[8,14],"languages.":[9],"Retrieving":[10],"information":[11],"from":[12,45,58],"these":[13],"languages":[15],"is":[16],"a":[17,119,130,175,185],"challenging":[18],"task.":[19],"Approximately":[20],"62":[21],"million":[22],"people":[23],"worldwide":[24],"speak":[25],"the":[26,37,42,46,59,69,92,109,152,199,202,212,217],"Gujarati":[27,43,48,60,132,221],"language.":[28],"This":[29,50,80],"research":[30,51],"paper":[31],"aims":[32],"to":[33,197],"understand":[34],"and":[35,72,77,99,115,167,178,191,214],"extract":[36],"meaningful":[38,55],"text":[39,44,56,86,204],"features":[40,57,90,107,117,126],"of":[41,85,101,216],"OCR":[47,61,148,222],"dataset.":[49],"focuses":[52],"on":[53,146],"extracting":[54],"dataset,":[62],"which":[63],"comprises":[64],"23,100":[65],"samples":[66],"generated":[67],"using":[68,91,172,180],"TERAFONT-VARUN":[70],"font":[71],"augmented":[73],"horizontal/vertical":[75],"shifts":[76],"rotational":[78],"transformations.":[79],"study":[81],"explores":[82],"three":[83],"levels":[84],"feature":[87,177,223],"extraction:":[88],"Mid-level":[89],"Integrated":[93],"Shape":[94],"Numeric":[95],"Encoding":[96],"Approach":[97,113],"(ISNEA)":[98],"Fusion":[100],"Region":[102],"Geometric":[103],"Features":[104],"(FRGF),":[105],"Mid-high-level":[106],"via":[108],"One-Bit":[110],"Frequency":[111],"Count":[112],"(OBFCA),":[114],"High-level":[116],"through":[118],"deep":[120],"learning-based":[121],"CNN":[122],"model.":[123],"The":[124,188],"extracted":[125,203],"were":[127,194],"stored":[128],"in":[129,220],"structured":[131],"Text":[133],"Feature":[134],"Vector":[135],"Dictionary.":[136],"ISNEA":[137,166],"struggles":[138],"characters":[140],"containing":[141],"maatra\u2019s":[142,153],"modifiers,":[143],"87.5%":[145],"standardized":[147],"images.":[149],"OBFCA":[150],"resolves":[151],"issue":[154],"by":[155],"row-wise":[156],"binary":[157],"frequency":[158],"computation,":[159],"yielding":[160],"90.11%":[161],"accuracy.":[162],"FRGF":[163],"significantly":[164],"outperforms":[165],"OBFCA,":[168],"93.5%":[170],"accuracy":[171],"Eccentricity":[173,181],"as":[174,184],"single":[176],"92.75%":[179],"+":[182],"Perimeter":[183],"fused":[186],"feature.":[187],"Euclidean":[189],"distance":[190],"cosine":[192],"similarities":[193,200],"also":[195],"used":[196],"measure":[198],"between":[201],"features.":[205],"Comparative":[206],"analysis":[207],"against":[208],"existing":[209],"methods":[210],"confirms":[211],"superiority":[213],"robustness":[215],"proposed":[218],"approaches":[219],"extraction.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
