Summary

Proceedings of the 2012 International Symposium on Nonlinear Theory and its Applications

2012

Session Number:C3L-B

Session:

Number:707

Image Compression and Regeneration based on Different Type of Neurons of Cellular Neural Network

Aya Takahashi,  Shintaro Maezawa,  Daiki Goto,  Masatoshi Sato,  Hisashi Aomori,  Mamoru Tanaka,  

pp.707-710

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.1.707

PDF download (1.5MB)

Summary:
This paper describes Dynamical image compression and regeneration with LIFN (Leaky Integrated Fire Neuron) and FitzHugh-Nagumo (FHN) models in Cellular Neural Network(CNN). The models are action potential of neurons. These models are simplified version of the Hodgkin-Huxley (HH) model which is model in a detailed manner activation and deactivation dynamics of a spiking neuron. If a group of spikes is considered as a pulse train, it is possible to introduce the biological models for CNN instead of ΣΔ modulation.

References:

[1] L.O. Chua and L. Yang, “Cellular Neural Networks: Theory”, IEEE Trans. Circuits Syst., vol.35, no.10, pp.1257-1272, Oct. 1988.

[2] H. Harrer and J. A. Nossek, “Discrete-time cellular neur-al networks”, Int. J. Circuits Theory Applicat., vol.20, pp.453-467, 1994.

[3] JACEK FLAK, DENSE IMPLEMENTATIONS OF BINARY CELLULAR NONLINEAR NEURAL NETWORKS; FROM CMOS TO NANOTECHNOLOGY, TKK Dissertation 79 Espoo 2007, 2007.

[4] M.Tanaka, and K.Kenya, “Conversion of Resolution and Intensity using Cellular Neural Networks”, Research report of Grant-in-Aid for Scientific Research (KAKENHI)., 49, pp. 1-22, Oct 2010.

[5] S. Maezawa, H. Aomori and M. Tanaka, ”Image Processings of a Leaky Integrated-and-Fire Neuron by Cellular Neural Network”, NLP, vol. 111, no. 106, pp. 113-118, 2011.

[6] H. Aomori, T. Otake, N. Takahashi and M. Tanaka, ”A Spatial Domain Sigma-Delta Modulation via Discrete-Time Cellular Neural Network”, Neural Networks, vol. 21, pp.349-357, 2008.