Performance analysis of flexible zone based features to classify Hindi numerals

Author

Singh, Pratibha ; Verma, Ajay ; Chaudhari, Narendra S.

Author_Institution

Inst. of Eng. & Technol., DAVV Indore, Indore, India

Volume

6

fYear

2011

fDate

8-10 April 2011

Firstpage

292

Lastpage

296

Abstract

Various parameters available for human identification but hand written documents always proven its importance. Although many pieces of work had been done for recognition of roman script but only few attempts have been tried for Indian scripts. Hindi is the most popular language of India which is written and encoded using Devnagri script. Zoning is basically the superimposition of nxn grid on the image of character. In this paper we have compared the various zoning alternatives. The performance of fixed boundary and flexible boundary is evaluated. The average distance and average angle of black pixel of the skeleton of the image pattern is used as feature. For recognition of the digits MLP based classifier SVM based classifier is used. Performance for SVM is better than SVM.

Keywords

character recognition; document image processing; handwriting recognition; multilayer perceptrons; natural languages; support vector machines; Devnagri script; Hindi numeral classification; Indian script; MLP based classifier; Roman script recognition; SVM based classifier; digits recognition; fixed boundary; flexible boundary; flexible zone based feature; zoning; Accuracy; Artificial neural networks; Character recognition; Feature extraction; Handwriting recognition; Support vector machines; Feature extraction; Fuzzy Zoning; Multi-layer Perceptron; Optical character recognition; Support vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics Computer Technology (ICECT), 2011 3rd International Conference on

Conference_Location

Kanyakumari

Print_ISBN

978-1-4244-8678-6

Electronic_ISBN

978-1-4244-8679-3

Type

conf

DOI

10.1109/ICECTECH.2011.5942101

Filename

5942101