Improving Image Segmentation by Chaotic Neurodynamics

Kazuyuki AIHARA

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E79-A    No.10    pp.1630-1637
Publication Date: 1996/10/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications (NOLTA))
Category: Neural Nets and Human Being
chaos,  combinatorial optimization problems,  image segmentation,  variable-shape-block-segmentation,  

Full Text: PDF>>
Buy this Article

We propose a novel segmentation algorithm which combines an image segmentation method into small regions with chaotic neurodynamics that has already been clarified to be effective for solving some combinatorial optimization problems. The basic algorithm of an image segmentation is the variable-shape-bloch-segmentation (VB) which searches an opti-mal state of the segmentation by moving the vertices of quadran-gular regions. However, since the algorithm for moving vertices is based upon steepest descent dynamics, this segmentation method has a local minimum problem that the algorithm gets stuck at undesirable local minima. In order to treat such a problem of the VB and improve its performance, we introduce chaotic neurodynamics for optimization. The results of our novel method are compared with those of conventional stochastic dynamics for escaping from undesirable local minima. As a result, the better results are obtained with the chaotic neurodynamical image segmentation.