Template synthesis of cellular neural networks for information coding and decoding

Mamoru Tanaka, K. R. Crounse, T. Roska

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

This paper describes the nse of analog Cellular Neural Networks (CNNs) for information coding and decoding - especially for the case of moving images. The dynamics of the coding (C-) and decoding (D-) CNNs are described by generalised CNN state eqnations. The C-CNN encodes the image by structural compression and halftoning. The D-CNN decodes the received data through a reconstruction process so as to almost recognise the original input to the C-CNN. The importance of our compression and quantisation technique lies in the ability to make the computations with only local connections. A dynamic quantitation is performed in the C-CNN to decide the binary value of each pixel from the neighboring values. In order to reduce the error between the original gray image and reconstructed halftone image, the template synthesis problem is addressed from the viewpoint of energy minimisation. The structural compression template synthesis problem is discussed from the viewpoints of topological and regnlarization theories. The structurally compressed image is regenerated in the D-CNN by a dynamic current distribution. The communication system in which the C- and D-CNNs are embedded consists of a differential transmitter with an internal receiver model in the feedback loop. Examples of the performance of the complete system are given.

Original languageEnglish
Title of host publicationProceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages29-35
Number of pages7
ISBN (Electronic)0780308751, 9780780308756
DOIs
Publication statusPublished - Jan 1 1992
Event2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 - Munich, Germany
Duration: Oct 14 1992Oct 16 1992

Publication series

NameProceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992

Conference

Conference2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992
CountryGermany
CityMunich
Period10/14/9210/16/92

    Fingerprint

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Tanaka, M., Crounse, K. R., & Roska, T. (1992). Template synthesis of cellular neural networks for information coding and decoding. In Proceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 (pp. 29-35). [274331] (Proceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CNNA.1992.274331