By Topic

A Handwriting Numeral Character Recognition System

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Zili Chen ; Coll. of Inf. Sci. & Eng., ChongQing Normal Univ., Chongqing, China ; Zuxue Wei

This paper presents a novel handwriting numeral recognition system based on wavelet and neural network. In the first part, we describe a general Optical Character Recognition (OCR) system and point out that selection of a feature extraction method and design of classifier are the most important factor in achieving high recognition performance in character recognition system. In the Second part, we present a feature extraction method based on ring-projection and wavelet transform, this approach is closely related to feature extraction methods by Fourier Series expansion. The objective to use an orthonormal wavelet basis rather than the Fourier basis is that wavelet coefficients provide localized frequency information. In the third part, we design a back propagation neural network (BPN) classifier, which has three layer perceptrons, the number of neurons of input layer corresponds to the dimension of the feature vector space, the number of neurons of output layer corresponds to the number of characters to be recognized. In the last part, we offer an overall scheme for this recognition system based on wavelet transform and neural network.

Published in:

Multimedia Technology (ICMT), 2010 International Conference on

Date of Conference:

29-31 Oct. 2010