Multistable Cellular Neural Networks and Their Application to Image Decomposition

被引:0
作者
Medina Hernandez, Jose Antonio [1 ]
Gomez Castaneda, Felipe [1 ]
Moreno Cadenas, Jose Antonio [1 ]
机构
[1] IPN, CINVESTAV, Dept Elect Engn, Mexico City 07360, DF, Mexico
来源
2009 52ND IEEE INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2 | 2009年
关键词
CNN; stable state; phase line; image segmentation; image processing; K-means algorithm; DESIGN;
D O I
10.1109/MWSCAS.2009.5235905
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Traditional cellular neural networks are arrays of coupled processing cells, where every uncoupled cell has two stationary stable states. In this paper an oscillatory function is used to define a cellular neural network whose uncoupled cells have a number of stable stationary states larger than two, so the output image has three or more grey levels. The proposed dynamics is applied to the decomposition of images with multiple gray levels.
引用
收藏
页码:873 / 876
页数:4
相关论文
共 14 条
[1]  
Chua L.O., 1998, CNN: A Paradigm for Complexity, V31
[2]   CELLULAR NEURAL NETWORKS - THEORY [J].
CHUA, LO ;
YANG, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272
[3]  
*CSW, 2007, CSW12007
[4]   Fault-tolerant design of analogic CNN templates and algorithms -: Part I:: The binary output case [J].
Földesy, P ;
Kék, L ;
Zarándy, A ;
Roska, T ;
Bártfai, G .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (02) :312-322
[5]   GENETIC ALGORITHM FOR CNN TEMPLATE LEARNING [J].
KOZEK, T ;
ROSKA, T ;
CHUA, LO .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1993, 40 (06) :392-402
[6]  
MEDINA JA, 2007, P 2007 4 INT C EL EL
[7]  
MEDINA JA, 2008, P IEEE 11 INT WORKSH, P230
[8]  
Nagle R.K., 2000, Fundamentals of Differential Equations and Boundary Value Problems
[9]  
Nossek JA, 1996, INT J CIRC THEOR APP, V24, P15, DOI 10.1002/(SICI)1097-007X(199601/02)24:1<15::AID-CTA900>3.0.CO
[10]  
2-5