Information theoretical based feature selection approach for human skin detection

Chenaoua, K. S. and Bouridane, Ahmed (2010) Information theoretical based feature selection approach for human skin detection. In: Proceedings of the 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). IEEE, Piscataway, NJ, pp. 1122-1125. ISBN 978-1424442959

Full text not available from this repository. (Request a copy)

Abstract

Detection of human skin in colored images has always been performed in known standard color spaces. In this paper a new color space coordinate is proposed based on popular existing color spaces but taking into account the most representative ones. Selection of the best color components is based on the use of the mutual information and maximum relevance minimum redundancy technique. A Gaussian model based classifier is used to test the performance of the proposed color space transformation.

Item Type:	Book Section
Additional Information:	Presented at the ICASSP International Conference on Audio, Speech and Signal Processing held in Dallas, Texas from 14-19 March 2010.
Uncontrolled Keywords:	Gaussian model, mutual information
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Sarah Howells
Date Deposited:	12 Sep 2012 16:22
Last Modified:	12 Oct 2019 22:29
URI:	http://nrl.northumbria.ac.uk/id/eprint/8808

Downloads