Artificial Neural Network For Recognition Of HandwrittenDevanagari Character

Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2015, Vol 17, Issue 1

Abstract

 Abstract: Information gathering is one of the most important thing in the digital world, manyorganizationsstill use handwritten documents for storing their information. So it is important task to convert this informationin to digital world. Handwritten character recognition helps user to convert their handwritten documents in todigital information. Purpose of this dissertation work is to implement zone based feature extraction methodwhich is combination of image centroid zone and zone centroid zone of individual character image. In featureextraction using zone based approach, individual character image is divided into n equal size zones thenaverage distance of all pixels with respect to image centroid or zone centroid is computed. In combination ofimage centroid and zone centroid approach it computes average distance of all pixels present in each zone withrespect to image centroid as well as zone centroid which gives feature vector of size 2Xn features. This featurevector is presented to feed forward neural network for recognition.

Authors and Affiliations

Ms. Seema A. Dongare , Prof. Dhananjay B. Kshirsagar , Mr. Nitin J. Khapale , Ms. Amruta D. Pawar

Keywords

Related Articles

 Development of a D.C Circuit Analysis Software Using MicrosoftVisual C#.Net

 Abstract: In this paper, the development of D.C circuit simulation software, using Microsoft visual C#.net, hasbeen achieved. This paper aims at (i) analysing a purely resistive planar circuit, (ii) displaying curr...

 Object Elimination and Reconstruction Using an Effective  Inpainting Method

 Three major problems have been found in the existing algorithms of image inpainting: Reconstruction of large regions, Preference of filling-in and Choice of best exemplars to synthesize the missing  reg...

HDL Design for Exa Hertz Clock based 2e23-1 Exa Bits Per Second (Ebps) PRBS Design for Ultra High Speed Applications/Products

Abstract: The Design is mainly Intended for HDL Design for Exa Hertz Clock based 2e23 -1 Exa Bits Per Second (Ebps) PRBS Design for Ultra High Speed Applications/Products the estimation of HIGH Speed in terms of Ebps(Exa...

 A review of Hierarchical energy Protocols in Wireless SensorNetwork

 Abstract: ​This paper attempts to provide an overview of various protocols used in wireless sensor networkwhich include data dissemination and data gathering protocols .Wireless network is any type of computernetwo...

Download PDF file
  • EP ID EP163283
  • DOI -
  • Views 92
  • Downloads 0

How To Cite

Ms. Seema A. Dongare, Prof. Dhananjay B. Kshirsagar, Mr. Nitin J. Khapale, Ms. Amruta D. Pawar (2015).  Artificial Neural Network For Recognition Of HandwrittenDevanagari Character. IOSR Journals (IOSR Journal of Computer Engineering), 17(1), 60-64. https://europub.co.uk/articles/-A-163283