Handwritten Bangla Character Recognition Using Artificial Neural Network

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 3

Abstract

 Abstract: This paper presents a system for recognizing Bangla handwritten characters using Artificial Neural Network based on Multi Layer Perceptron classifier. The Bangla alphabets Sorborno and Banjonborno have been chosen to test the recognition System. Character is recognized by analyzing its shape and comparing its features that differentiates each character. The required images are acquired using a digital camera. The color images are then cropped, resized, and converted to binary images. Finally, Multi Layer Perceptron (MLP) based classifier is used for recognition of candidate regions. Experimental results show the relatively high accuracy of the developed method on training and the test sets respectively.

Authors and Affiliations

Md. Azher Uddin

Keywords

Related Articles

 Cryptanalysis and Security Enhancement of a Khan et al.'sScheme

 Abstract: Remote user authentication, in which the resources are distributed among the recipients and theyare shared across the network in the form of network services provided by the remote systems. Before supplys...

 Improving Data Storage Security in Cloud Computing UsingElliptic Curve Cryptography

Abstract: Companies tends towards more availability, less cost, managed risk, agility- all of which areproviding by cloud computing. The cloud computing is a way to deliver IT services on demand and pay perusage, and it...

Service Level Management For it Ser-Vices in Small Settings: A Systematic Review

Abstract: This work presents the application of a systematic review protocol for Software Engineering. This protocol is used as a formal model by applying systematic review to Service Level Man-agement. The objective is...

Semantic based Automated Service Discovery

A vast majority of web services exist without explicit associated semantic descriptions. As a result,many services that are relevant to a specific user service request may not be considered during service discovery. In t...

Imaging of Intracranial Space Occupying Lesions: A Prospective Study in A Tertiary Care Centre in Northern India

 Introduction: The high morbidity & mortality associated with ICSOLs necessitates their early diagnosis so as to plan the required intervention. Intracranial Space occupying lesions (ICSOL) can be neoplastic,inf...

Download PDF file
  • EP ID EP110560
  • DOI 10.9790/0661-16333338
  • Views 111
  • Downloads 0

How To Cite

Md. Azher Uddin (2014).  Handwritten Bangla Character Recognition Using Artificial Neural Network. IOSR Journals (IOSR Journal of Computer Engineering), 16(3), 33-38. https://europub.co.uk/articles/-A-110560