Handwritten character recognition based on moment features derived from image partition

Author

Tsang, I.J. ; Tsang, I.R. ; Van Dyck, D.

Author_Institution

VisionLab, Antwerp Univ., Belgium

Volume

2

fYear

1998

fDate

4-7 Oct 1998

Firstpage

939

Abstract

In this work we present a novel approach to handwritten character recognition which is based on the intuitive way in which characters are written as one or a few continuous lines. Therefore we calculate the zeroth, first and second radial moment as a function of the angle. In practice this is done by dividing the character into 32 angular sections. The three obtained curves can be used for pattern recognition using statistical analysis. The method has been evaluated using the NIST handwritten character data set. At first, a simple chi-square test gave a result of 80.81% recognition rate at zero rejection rate for digits. Using a back-propagation algorithm the recognition rate obtained was 87.54% also at zero rejection rate, showing that the features are sufficient to discriminate the characters

Keywords

backpropagation; feature extraction; handwritten character recognition; image segmentation; pattern classification; statistical analysis; NIST handwritten character data set; angular partition; back-propagation algorithm; chi-square test; feature extraction; first radial moment; handwritten character recognition; image partition; moment features; pattern recognition; recognition rate; second radial moment; statistical analysis; zero rejection rate; zeroth radial moment; Character recognition; Feature extraction; Fingerprint recognition; Handwriting recognition; Image recognition; Image segmentation; Partitioning algorithms; Pattern recognition; Physics; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.723709

Filename

723709