Show simple item record

AuthorKhan, Sulaiman
AuthorKhan, Habib Ullah
Available date2022-12-30T15:55:21Z
Publication Date2021
Publication NameInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2021
Identifierhttp://dx.doi.org/10.1109/ICECET52533.2021.9698788
CitationKhan, S., & Khan, H. U. (2021, December). Isolated Handwritten Pashto Characters Recognition using KNN classifier. In 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET) (pp. 1-5). IEEE.
ISBN9781665442312
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85127071774&origin=inward
URIhttp://hdl.handle.net/10576/37878
AbstractRegional and cultural diversities around the world and especially in Pakistan has given birth to a large number of writing systems and scripts consists of varying character sets. Developing an optimal OCR system for such a varying and large character set is a challenging task. Unlimited variations in handwritten texts due to mood swings, varying writing styles, changes in medium of writing, etc. puzzles the research community. Slight change in character shapes for various scripts acts as a big barrier in developing the character recognition (CR) systems for cursive scripts. Unavailability of benchmark results and corpora for cursive scripts CR impedes the researchers in the development of an optimal CR systems. To efficiently address these issues, the proposed research work aims to develop an optimum OCR system for the recognition of handwritten Pashto characters. Also the unavailability of a standard corpora of the handwritten Pashto characters is addressed by developing a medium sized corpus of the handwritten Pashto characters (14784 handwritten samples). K nearest neighbor is adapted for the recognition of the Pashto characters based on the zoning technique. After testing the proposed OCR system for varying training and test sets an overall accuracy of 85.31% is calculated.
SponsorQatar University [QUHI-CBE-21/22-1].
Languageen
PublisherIEEE
SubjectK nearest neighbor
OCR
Pashto
zoning technique
TitleIsolated Handwritten Pashto Characters Recognition using KNN classifier
TypeArticle
Pagination1-5
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record