A Two Stage Classification Approach for Handwritten Devnagari Characters

Author

Arora, Sandhya ; Bhatcharjee, Debotosh ; Nasipuri, Mita ; Malik, Latesh

Author_Institution

Meghnad Saha Inst. of Tech., Kolkata

Volume

2

fYear

2007

fDate

13-15 Dec. 2007

Firstpage

399

Lastpage

403

Abstract

The paper presents a two stage classification approach for handwritten Devanagari characters. The first stage is using structural properties like shirorekha, spine in character and second stage exploits some intersection features of characters which are fed to a feedforward neural network. Simple histogram based method does not work for finding shirorekha, vertical bar (spine) in handwritten Devnagari characters. So we designed a differential distance based technique to find a near straight line for shirorekha and spine. This approach has been tested for 50000 samples and we got 89.12% success.

Keywords

feedforward neural nets; handwritten character recognition; image classification; differential distance based technique; feedforward neural network; handwritten Devanagari characters; intersection features; shirorekha property; spine property; structural properties; two stage classification approach; Character recognition; Computational intelligence; Data preprocessing; Decision trees; Feedforward neural networks; Histograms; Image converters; Neural networks; Optical character recognition software; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on

Conference_Location

Sivakasi, Tamil Nadu

Print_ISBN

0-7695-3050-8

Type

conf

DOI

10.1109/ICCIMA.2007.254

Filename

4426729