lmproving Image Segmentation by Chaotic Neurodynamics (Special Section on Nonlinear Theory and its Applications)
スポンサーリンク
概要
- 論文の詳細を見る
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 a1gorithm of an image segmentation is the variable-shape-block-segmentation (VB) which searches an optimal state of the segmentation by moving the vertices of quadrangular 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.
- 社団法人電子情報通信学会の論文
- 1996-10-25
著者
-
Aihara K
Univ. Tokyo Tokyo Jpn
-
Aihara K
Department Of Complexity Science And Engineering Graduate School Frontier Sciences The University Of
-
HASEGAWA Mikio
the Faculty of Industrial Science and Technology, Science University of Tokyo
-
IKEGUCHI Tohru
the Faculty of Industrial Science and Technology, Science University of Tokyo
-
MATOZAKI Takeshi
the Faculty of Industrial Science and Technology, Science University of Tokyo
-
AIHARA Kazuyuki
the Faculty of Engineering, The University of Tokyo
-
Ikeguchi T
Department Of Information And Numerical Sciences Graduate School Of Science And Engineering Saitama
-
Hasegawa Mikio
Wireless Networks Integration Group. Wireless Communications Division Communications Research Labora
-
Matozaki T
Musashi Inst. Technol. Tokyo Jpn
関連論文
- Prediction of Chaotic Time Series with Noise
- Solving large scale traveling salesman problems by chaotic neuodynamics
- An Analysis on Additive Effects of Nonlinear Dynamics for Combinatorial Optimization
- lmproving Image Segmentation by Chaotic Neurodynamics (Special Section on Nonlinear Theory and its Applications)
- Nonlinear Modeling by Radial Basis Function Networks (Special Section on Nonlinear Theory and its Applications)
- Solving the binding problem of the brain with bi-directional functional connectivity
- Pulse-Type Bursting Neuron Model Using Enhancement Mode MOSFETs
- Analog Hardware Implementation of a Mathematical Model of an Asynchronous Chaotic Neuron(Special Section on Analog Circuit Techniques and Relate)
- Noise-Enhanced Neuronal Coding of Chaotic Dynamics
- Pulse-Type Hardware Neuron Model for Future IC Design Based on the Modified BVP Equations
- Global Bifurcation Structure of Chaotic Neural Networks and its Application to Traveling Salesman Problems
- Emergence of Global Optimization Dynamics in Chaotic Neural Networks
- Global Bifurcation Structure of Chaotic Neural Networks and its Application to Optimization Problems
- A Current-Mode Implementation of a Chaotic Neuron Model Using a SI Integrator
- A Current-Mode Circuit of a Chaotic Neuron Model
- アルゴリズムから見た確率、カオス、アナログ計算 (特集 カオスコンピュータ--カオスを利用する情報処理)
- インタビュ- 合成による解析-2-カオス脳を創る (特集 脳科学とコンピュ-タ--情報処理の新しいメカニズム)
- インタビュ-:合成による解析--ニュ-ロン研究からのアプロ-チ (特集 脳とコンピュ-タ--新しい脳の研究とコンピュ-タ)
- 生命・カオス・工学 (生命とカオス)
- カオスとその電力分野への応用
- 非線形工学--21世紀の科学技術へ向けて (非線形構造の数理--非線形工学の展開)
- An Automatic Algorithm for Extracting Brain Tissues : Non-parametric Region Growing Method