Wavelet-Based Recognition of Handwritten Characters Using Artificial Neural Network

View Sample PDF

Author(s): D. K. Patel (Indian Institute of Technology (BHU), India), T. Som (Indian Institute of Technology (BHU), India)and M. K. Singh (Banaras Hindu University, India)
Copyright: 2016
Pages: 17
Source title: Handbook of Research on Generalized and Hybrid Set Structures and Applications for Soft Computing
Source Author(s)/Editor(s): Sunil Jacob John (National Institute of Technology Calicut, India)
DOI: 10.4018/978-1-4666-9798-0.ch022

Keywords: Artificial Intelligence / Information Science Reference / Library & Information Science / Theoretical Studies

Purchase

View Wavelet-Based Recognition of Handwritten Characters Using Artificial Neural Network on the publisher's website for pricing and purchasing information.

Abstract

In the present chapter, the widely common problem of handwritten character recognition has been tackled with multiresolution technique using discrete wavelet transform and artificial neural networks. The technique has been tested and found to be more accurate and economic in respect of the recognition process time of the system. Features of the handwritten character images are extracted by discrete wavelet transform used with appropriate level of multiresolution technique, then the artificial neural networks is trained by extracted features. The unknown input handwritten character images are recognized by trained artificial neural networks system. The proposed method provides good recognition accuracy for handwritten characters with less training time, less no. of samples and less no. of iterations.

The IRMA Community

Research IRM

Wavelet-Based Recognition of Handwritten Characters Using Artificial Neural Network

Purchase

Abstract

Related Content

IRMA Sponsors