Image skin segmentation based on multi-agent learning Bayesian and neural network

Skin colour is considered to be a useful and discriminating spatial feature for many skin detectionrelated applications, but it is not sufﬁciently robust to address complex image environments because of light-changing conditions, skin-like colours and reﬂective glass or water. These factors can crea...

Full description

Bibliographic Details
Main Authors:	Aos Alaa, Zaidan, Ahmad, Nurul Nadia, Hezerul, Abdul Karim, M. Larbani, Moussa, Bilal Bahaa, Zaidan, Aduwati, Sali
Format:	Article
Language:	English
Published:	Elsevier 2014
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://irep.iium.edu.my/41558/ http://irep.iium.edu.my/41558/ http://irep.iium.edu.my/41558/1/Aws_paper_2.pdf

id	iium-41558
recordtype	eprints
spelling	iium-415582015-10-13T06:02:17Z http://irep.iium.edu.my/41558/ Image skin segmentation based on multi-agent learning Bayesian and neural network Aos Alaa, Zaidan Ahmad, Nurul Nadia Hezerul, Abdul Karim M. Larbani, Moussa Bilal Bahaa, Zaidan Aduwati, Sali QA75 Electronic computers. Computer science Skin colour is considered to be a useful and discriminating spatial feature for many skin detectionrelated applications, but it is not sufﬁciently robust to address complex image environments because of light-changing conditions, skin-like colours and reﬂective glass or water. These factors can create major difﬁculties in face pixel-based skin detectors when the colour feature is used. Thus, this paper proposes a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces, respectively, to improve skin detection performance. The ﬁndings from this study have shown that the proposed multi-agent learning for skin detector has produced signiﬁcant true positive (TP) and true negative (TN) average rates (i.e. 98.44% and 99.86% respectively). In addition, it has achieved a signiﬁcantlylower averagerate for the false negative (FN) and false positive (FP) (i.e. only 1.56% and 0.14% respectively). The experimental results show that multiagent learning in the skin detector is more efﬁcient than other approaches. & 2014 Elsevier Ltd. All rights reserved Elsevier 2014 Article PeerReviewed application/pdf en http://irep.iium.edu.my/41558/1/Aws_paper_2.pdf Aos Alaa, Zaidan and Ahmad, Nurul Nadia and Hezerul, Abdul Karim and M. Larbani, Moussa and Bilal Bahaa, Zaidan and Aduwati, Sali (2014) Image skin segmentation based on multi-agent learning Bayesian and neural network. Engineering Applications of Artiﬁcial Intelligence , 32. pp. 136-150. ISSN 0952-1976 http://www.elsevier.com/locate/engappai
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Aos Alaa, Zaidan Ahmad, Nurul Nadia Hezerul, Abdul Karim M. Larbani, Moussa Bilal Bahaa, Zaidan Aduwati, Sali Image skin segmentation based on multi-agent learning Bayesian and neural network
description	Skin colour is considered to be a useful and discriminating spatial feature for many skin detectionrelated applications, but it is not sufﬁciently robust to address complex image environments because of light-changing conditions, skin-like colours and reﬂective glass or water. These factors can create major difﬁculties in face pixel-based skin detectors when the colour feature is used. Thus, this paper proposes a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces, respectively, to improve skin detection performance. The ﬁndings from this study have shown that the proposed multi-agent learning for skin detector has produced signiﬁcant true positive (TP) and true negative (TN) average rates (i.e. 98.44% and 99.86% respectively). In addition, it has achieved a signiﬁcantlylower averagerate for the false negative (FN) and false positive (FP) (i.e. only 1.56% and 0.14% respectively). The experimental results show that multiagent learning in the skin detector is more efﬁcient than other approaches. & 2014 Elsevier Ltd. All rights reserved
format	Article
author	Aos Alaa, Zaidan Ahmad, Nurul Nadia Hezerul, Abdul Karim M. Larbani, Moussa Bilal Bahaa, Zaidan Aduwati, Sali
author_facet	Aos Alaa, Zaidan Ahmad, Nurul Nadia Hezerul, Abdul Karim M. Larbani, Moussa Bilal Bahaa, Zaidan Aduwati, Sali
author_sort	Aos Alaa, Zaidan
title	Image skin segmentation based on multi-agent learning Bayesian and neural network
title_short	Image skin segmentation based on multi-agent learning Bayesian and neural network
title_full	Image skin segmentation based on multi-agent learning Bayesian and neural network
title_fullStr	Image skin segmentation based on multi-agent learning Bayesian and neural network
title_full_unstemmed	Image skin segmentation based on multi-agent learning Bayesian and neural network
title_sort	image skin segmentation based on multi-agent learning bayesian and neural network
publisher	Elsevier
publishDate	2014
url	http://irep.iium.edu.my/41558/ http://irep.iium.edu.my/41558/ http://irep.iium.edu.my/41558/1/Aws_paper_2.pdf
first_indexed	2023-09-18T20:59:30Z
last_indexed	2023-09-18T20:59:30Z
_version_	1777410527995101184

Image skin segmentation based on multi-agent learning Bayesian and neural network

Similar Items