Skin detection using the EM algorithm with spatial constraints

Reference : Skin detection using the EM algorithm with spatial constraints


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/11058

Title :	Skin detection using the EM algorithm with spatial constraints
Language :	English
Author, co-author :	Diplaros, A. [> >]
	Gevers, T. [> >]
	Vlassis, Nikos [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Publication date :	2004
Main document title :	Proc. Int. Conf. on Systems, Man and Cybernetics
Peer reviewed :	Yes
City :	The Hague, The Netherlands
Event name :	Systems, Man and Cybernetics, 2004 IEEE International Conference on
Event date :	2004
Abstract :	[en] In this paper, we propose a color-based method for skin detection and segmentation, which also takes into account the spatial coherence of the skin pixels. We treat the problem of skin detection as an inference problem. We assume that each pixel in an image has a hidden binary label associated with it, that specifies if it is skin or not. In order to solve the inference problem, we use a variational EM algorithm, which incorporates the spatial constraints with just a small computational overhead in the E-step. Finally, we show that our method provides better results than the standard EM algorithm and a state-of-art skin-detection method from the literature of Jones, M. J. and Rehg, J. M. (2002).
Permalink :	http://hdl.handle.net/10993/11058

There is no file associated with this reference.

All documents in ORBi^lu are protected by a user license.