DMCA
EURASIP Journal on Applied Signal Processing 2005:13, 2136–2145 c ○ 2005 Hindawi Publishing Corporation Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers (2004)
BibTeX
@MISC{Assaleh04eurasipjournal,
author = {Khaled Assaleh and M. Al-rousan},
title = {EURASIP Journal on Applied Signal Processing 2005:13, 2136–2145 c ○ 2005 Hindawi Publishing Corporation Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers},
year = {2004}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Building an accurate automatic sign language recognition system is of great importance in facilitating efficient communication with deaf people. In this paper, we propose the use of polynomial classifiers as a classification engine for the recognition of Arabic sign language (ArSL) alphabet. Polynomial classifiers have several advantages over other classifiers in that they do not require iterative training, and that they are highly computationally scalable with the number of classes. Based on polynomial classifiers, we have built an ArSL system and measured its performance using real ArSL data collected from deaf people. We show that the proposed system provides superior recognition results when compared with previously published results using ANFIS-based classification on the same dataset and feature extraction methodology. The comparison is shown in terms of the number of misclassified test patterns. The reduction in the rate of misclassified patterns was very significant. In particular, we have achieved a 36 % reduction of misclassifications on the training data and 57 % on the test data.
Keyphrases
eurasip journal applied signal processing hindawi publishing corporation recognition polynomial classifier deaf people efficient communication training data superior recognition result test data feature extraction methodology great importance anfis-based classification arabic sign language real arsl data iterative training misclassified test pattern proposed system classification engine arsl system several advantage
