Title

A Novel Electromyography (EMG) Based Classification Approach for Arabic Handwriting

Document Type

Conference Proceeding

Source of Publication

Proceedings of the International Joint Conference on Neural Networks

Publication Date

9-24-2003

Abstract

In this paper, a novel classification approach for handwritten Arabic characters is proposed. Features for classification are extracted from electromygraphic (EMG) signals detected on two forearm muscles. Noise cancellations in conjunction with a process parameter estimator for feature identification are proposed. Neural networks using a potentially damped least mean squared algorithm is used at the classification stage. The proposed new classification technique is used on handwritten Arabic characters.

Publisher

IEEE

Volume

3

First Page

2193

Last Page

2196

Disciplines

Computer Sciences

Keywords

Algorithms; Feature extraction; Muscle; Neural networks; Neural disorders; Electromyography

Scopus ID

0141857585

Indexed in Scopus

yes

Open Access

no

Share

COinS