Wavelet-Based Recognition of Handwritten Characters Using Artificial Neural Network

Wavelet-Based Recognition of Handwritten Characters Using Artificial Neural Network

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)
DOI: 10.4018/978-1-4666-9798-0.ch022
OnDemand PDF Download:
$30.00
List Price: $37.50

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.
Chapter Preview
Top

Background

The history of HCR systems is incomplete without mentioning the OCR systems, which preceded them. OCR is a problem recognized as being as old as the computer itself. Simon (1992) and Suen et al. (1993). The researchers in the field of pattern recognition are referred to survey papers and text books for good exposure of the HCR system. In the earlier works, the automatic recognition of characters has been classified into two categories: recognition of the machine-printed characters and the recognition of handwritten characters. Arica et al. (2001). Machine-printed character recognition systems generally used template matching, in which an image is compared to a library of images. Handwritten characters used low-level image processing techniques on the binary image to extract the feature vectors, which are then fed to statistical classifiers. Arica et al. (2001). Now, writing has been the most natural mode of collecting, storing, and transmitting information in this world, it is used for communication among humans and also for communication of humans and computer systems. Arica et al. (2001).

Complete Chapter List

Search this Book:
Reset