eprintid: 2620
rev_number: 5
eprint_status: archive
userid: 6
dir: disk0/00/00/26/20
datestamp: 2015-02-23 11:04:02
lastmod: 2015-02-23 11:04:02
status_changed: 2015-02-23 11:04:02
type: article
metadata_visibility: show
creators_name: Abdelsamea, Mohammed
creators_name: Gnecco, Giorgio
creators_name: Gaber, Mohamed Medhat
creators_id: mohammed.abdelsamea@imtlucca.it
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
title: An efficient Self-Organizing Active Contour model for image segmentation 
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
keywords: Region-based segmentation; Variational level set method;
    Active contours; Self-organizing neurons; Region-based prior knowledge
abstract: Active Contour Models (ACMs) constitute a powerful energy-based minimization framework for image segmentation, based on the evolution of an active contour. Among ACMs, supervised {ACMs} are able to exploit the information extracted from supervised examples to guide the contour evolution. However, their applicability is limited by the accuracy of the probability models they use. As a consequence, effectiveness and efficiency of supervised {ACMs} are among their main real challenges, especially when handling images containing regions characterized by intensity inhomogeneity. In this paper, to deal with such kinds of images, we propose a new supervised ACM, named Self-Organizing Active Contour (SOAC) model, which combines a variational level set method (a specific kind of ACM) with the weights of the neurons of two Self-Organizing Maps (SOMs). Its main contribution is the development of a new {ACM} energy functional optimized in such a way that the topological structure of the underlying image intensity distribution is preserved – using the two {SOMs} – in a parallel-processing and local way. The model has a supervised component since training pixels associated with different regions are assigned to different SOMs. Experimental results show the superior efficiency and effectiveness of {SOAC} versus several existing ACMs. 
date: 2015-02
date_type: published
publication: Neurocomputing
volume: 149
number: Part B
publisher: Elsevier
pagerange: 820 - 835
id_number: 10.1016/j.neucom.2014.07.052
refereed: TRUE
issn: 0925-2312
official_url: http://www.sciencedirect.com/science/article/pii/S0925231214010042
citation:   Abdelsamea, Mohammed and Gnecco, Giorgio and Gaber, Mohamed Medhat  An efficient Self-Organizing Active Contour model for image segmentation.  Neurocomputing, 149 (Part B).  820 - 835.  ISSN 0925-2312      (2015)