Small-World Cellular Neural Networks for Image Processing Applications

In this paper, we propose a Small-World Cellular Neural Network (SWCNN) model, which is constructed by introducing some random couplings between cells to adding to the original Chua-Yang CNN. Applying this SWCNN model to some ap- plications of image processing such as small object remover, edge detecttiom, etc. are investigated. We found from numerical simulations that the SWCNN can improve the results of the image output in a certain content.

[1]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[2]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[3]  Valeri Mladenov,et al.  Cellular Neural Networks: Theory And Applications , 2004 .

[4]  Leon O. Chua,et al.  Autonomous cellular neural networks: a unified paradigm for pattern formation and active wave propagation , 1995 .

[5]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[6]  Beom Jun Kim,et al.  Synchronization on small-world networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  A. Mikhailov,et al.  Mutual synchronization and clustering in randomly coupled chaotic dynamical networks. , 1999, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[8]  Leon O. Chua,et al.  Analogic CNN algorithms for some image compression and restoration tasks , 1995 .

[9]  Mauricio Barahona,et al.  Synchronization in small-world systems. , 2002, Physical review letters.

[10]  Tamás Roska,et al.  CNN software library (Templates and algorithms.) Version 7.2 , 1998 .

[11]  Akio Ushida,et al.  Image Processing of Two-Layer CNNs-Applications and Their Stability- , 2002, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[12]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.