Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

An Analysis on Bengali handwritten conjunct character recognition and prediction

Simple item page
bracu.degree.levelUndergraduate
bracu.type.groupStudent Works
datacite.rightsOpen Access
dc.contributor.advisorIslam, Md. Saiful
dc.contributor.authorMunawar, Maazin
dc.contributor.authorRoy, Yagghaseni Saha
dc.contributor.authorHussain, Mohammed Mudabbir
dc.contributor.departmentDepartment of Computer Science and Engineering
dc.date.accessioned2021-10-21T09:01:52Z
dc.date.available2021-10-21T09:01:52Z
dc.date.copyright2021
dc.date.issued2021-01
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 29-31).
dc.descriptionThis thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.en_US
dc.description.abstractIn the very active field of handwriting recognition, a lot of research can be found in the detection of the handwriting of various languages, especially English. However, for languages like Bengali, while they hold some success in handwritten character recognition, a big roadblock is Bengali conjunct characters or “Juktakkhor”. As Bengali conjunct characters are very complex, even today many institutions in Bangladesh still maintain documents as handwritten copies. In this paper, we will present a model that focuses on conjunct character recognition and conversion to textformat. OurproposedsystemwillbetrainedandtestedusingCNNmodelslike VGG19, ResNet-50, GoogleNet, LSTM, ShuffleNet etc. The results generated from preliminary analysis yield that ShuffleNet gives the most accurate results with an accuracy of 91.2% followed by GoogleNet with 73.3%.en_US
dc.description.degreeBachelor of Science in Computer Science
dc.description.statementofresponsibilityMaazin Munawar
dc.description.statementofresponsibilityYagghaseni Saha Roy
dc.description.statementofresponsibilityMohammed Mudabbir Hussain
dc.format.extent31 pages
dc.identifier.otherID 17101036
dc.identifier.otherID 17101019
dc.identifier.otherID 17101350
dc.identifier.urihttp://hdl.handle.net/10361/15514
dc.language.isoenen_US
dc.publisherBRAC Universityen_US
dc.rightsBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.
dc.subjectConjunct Charactersen_US
dc.subjectHandwrittenen_US
dc.subjectNeural Networksen_US
dc.subjectBengalien_US
dc.subjectSegmentationen_US
dc.subjectResNet-50en_US
dc.subjectShuffleNeten_US
dc.subjectLSTMen_US
dc.subjectGoogleNeten_US
dc.subject.lcshNeural Networks
dc.titleAn Analysis on Bengali handwritten conjunct character recognition and predictionen_US
dc.typeThesisen_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
17101036, 17101019, 17101350_CSE.pdf
Size:
4.44 MB
Format:
Adobe Portable Document Format
Description:
Download

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Thesis (Bachelor of Science in Computer Science)