Please use this identifier to cite or link to this item:
https://elibrary.khec.edu.np:8080/handle/123456789/668Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Er. Shree Ram Khaitu | - |
| dc.contributor.author | Anastu Kayastha (750304) | - |
| dc.contributor.author | Rohan Kaju (750330) | - |
| dc.contributor.author | Rukesh Shrestha (750335) | - |
| dc.contributor.author | Sujan Khusu (750344) | - |
| dc.date.accessioned | 2023-09-20T06:59:24Z | - |
| dc.date.available | 2023-09-20T06:59:24Z | - |
| dc.date.issued | 2023-08 | - |
| dc.identifier.uri | https://elibrary.khec.edu.np/handle/123456789/668 | - |
| dc.description.abstract | Nepali LanguageusesDevanagariscriptwhichisbeingusedbeyondparticularlanguageas officialscriptinIndiansubcontinent.CharacterclassificationaccuracyisstillanissuetoDe- vanagariScriptdespiteofmanyresearcheshadbeenconducted.Throughmanyresearches conducted, itisidentifiedthatpoorsegmentationisthekeytolowaccuracy.Manyresearch worksusedholisticapproachtoimproveclassificationresult. DevanagariisthemostextensivelyusedscriptinNepal.Textdetectionandextractionfromthe images/photos havebeenutilizedinavarietyofapplications.Characterrecognitionpossessthe greater levelofpotentialtoleadtotechnologicallyadvancedapplications.However,duetothe structure’scomplexity,thesametechniquecannotbeusedforalllanguagesandscripts.The OCR methodstransformsthescannedimagesofprintedorhandwrittendocumentintothedig- ital text.Languages,includingNepali,Hindi,Marathi,andothers,usetheDevanagariscript. The majorgoaloftheproposedwork/studyistodetectNepali(Devanagari)scriptusingCNN utilizing themostappropriatestrategiestoboosttherecognitionrateofDevanagariHandwrit- ten TextRecognitionwithaviewtoeffectivelyrecognizeDevanagariTextfromthescanned images. OCRbeginswiththeinputandpreprocessingofscannedpicturesofprintedorhand- written text.Classifiersareusedtocategorizethepreprocessedpicture,whichisseparatedinto wordsandthencharactersbyutilizingprofilingprojectiontechnique.Finally,post-processing involvestheprocessoftransformingdetectedcharactersintotext. This projectsalsorepresentsthemethodofskew-correctionforcorrectingtheskewofthewords for theactualprediction.OCRmodelpresentedinthisresearchprojectusesprofileprojection (Horizontal andVertical)ofthepurposeofsegmentationofcore,lowermodifiersandupper modifiers. | en_US |
| dc.language.iso | en | en_US |
| dc.subject | OCR,Devanagari,Segmentation,DHTR,Skew-Correction,Modifiers. | en_US |
| dc.title | OCR OF HANDWRITTEN DEVANAGARI TEXT USING SEGMENTATION AND CNN | en_US |
| dc.type | Technical Report | en_US |
| local.college.name | Khwopa Engineering College | - |
| local.degree.department | Department of Computer | - |
| local.degree.name | BE Computer | - |
| local.degree.level | Bachelor's Degree | - |
| local.item.accessionnumber | D.1364 | - |
| Appears in Collections: | Computer Report | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Devnagari-OCR.pdf Restricted Access | 2.46 MB | Adobe PDF |  View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.