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

 Effect of Thermal Radiation on Unsteady Gravity Flow of a Power-Law Fluid with Viscous Dissipation through a Porous Medium

 Abstract:In this work, we studied the effect of thermal radiation on unsteady gravity flow of a power-law fluid with viscous dissipation through a porous medium. The modified Darcy’s law is considered together with...

 Natural Language Query Processing on Dynamic Databases Using Semantic Grammar

 Abstract: Ease and effectiveness of Information Retrieval from Structured Database through Natural Language provides high utility value. The main purpose of Natural Language Query Processing is that an English...

 Exponential software reliability using SPRT: MLE

 In Classical Hypothesis testing volumes of data is to be collected and then the conclusions are drawn, which may need more time. But, Sequential Analysis of Statistical science could be adopted in order to  ...

 Privacy Preserving and Load Balancing For Secure Cloud Storage

 Using Cloud Storage, users can remotely store their data and enjoy the on-demand high quality applications and services from a shared pool of configurable computing resources, without the burden of local data sto...

 Energy Consumption of Intermediate node in AODV

 Abstract: An A MANET(Mobile Ad-Hoc NETwork)is a network of wireless mobile nodes,without a centralizedcontrol.MANET can be characterized as unstructured Ad-Hoc,mobile nodes with limited resources includingenergy.AO...

Download PDF file
  • EP ID EP163283
  • DOI -
  • Views 75
  • 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