JournalTOCs

Publisher: International Computer Science and Engineering Society (ICSES) (Total: 2 journals) [Sort alphabetically]

Showing 1 - 2 of 2 Journals sorted by number of followers
	ICSES Transactions on Computer Networks and Communications
	ICSES Transactions on Image Processing and Pattern Recognition

Most Followed Journals

Top Publishers

Top Subjects

Similar Journals

ICSES Transactions on Image Processing and Pattern Recognition
Number of Followers: 0

Full-text available via subscription

Subscription journal
ISSN (Online) 2645-8071
Published by International Computer Science and Engineering Society (ICSES)

[2 journals]

A Slice-based Character Recognition Technique for Handwritten Devanagari
Script
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Haque; Md. Asraful
  Pages: 1 - 7
  Abstract: The conventional Character Recognition for English character has been widely analyzed in the last few decades and now highly advanced for creating different technology driven applications. Indian languages which are relatively complicated in terms of geometrical shape are far behind from this perspective. Government office, library, bank and publishing houses now prefer digital document processing to make their services fast and economical. Devanagari is the official script (Hindi language) of India, and spoken by major population of the country. Many researchers have shown interest mainly on recognition of digitally printed Devanagari character. However, very little work has been done in the area of handwritten Devanagari character recognition. Therefore, there is a need to focus in this handwritten Devanagari character recognition as it will help in solving many real life problems like bank check processing, post offices and government offices in India where most of the applications and documents are written in Devanagari characters. In this paper, we have suggested a handwritten Devanagari character recognition method using the topological and geometrical features of the character. First, we cut the characters into slices and then with the help of a slice or a set of slices a feature set is formed to uniquely identify a character. The experimental result shows that the proposed method provides more than 82% accuracy which is quite better than many existing methods.
  Citation: ITIPPR, 6, 1 (2020)
  PubDate: 2020-04-30
  Issue No: Vol. 6, No. 1 (2020)