TY  - JOUR
EP  -  835
PB  - Elsevier
VL  - 149
IS  - Part B
JF  - Neurocomputing
N2  - 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. 
KW  - Region-based segmentation; Variational level set method;
    Active contours; Self-organizing neurons; Region-based prior knowledge
UR  - http://www.sciencedirect.com/science/article/pii/S0925231214010042
A1  - Abdelsamea, Mohammed
A1  - Gnecco, Giorgio
A1  - Gaber, Mohamed Medhat
TI  - An efficient Self-Organizing Active Contour model for image segmentation 
Y1  - 2015/02//
ID  - eprints2620
SP  - 820 
SN  - 0925-2312
AV  - none
ER  -