A robust and efficient universal CNN cell circuit using simplicial neuro-fuzzy inferences for fast image processing

Author

Dogaru, Radu ; Julián, Pedro ; Chua, Leon O.

Author_Institution

Dept. of Appl. Electron. & Inf. Eng., Politehnic Univ. of Bucharest, Romania

Volume

3

fYear

2001

fDate

6-9 May 2001

Firstpage

493

Abstract

This paper introduces a highly efficient yet easy to implement mixed-signal neural circuit. The structure combines a linear adaptive element (trained with the LMS algorithm) with a nonlinear preprocessor based on a set of fuzzy membership functions. The novelty consists in defining these functions based on the theory of simplicial decomposition, which leads to a very convenient circuit realization. The cell is particularly well suited for cellular neural networks (CNN), providing highly effective nonlinear image filters

Keywords

cellular neural nets; digital filters; fuzzy neural nets; image processing equipment; least mean squares methods; mixed analogue-digital integrated circuits; nonlinear filters; LMS algorithm; cellular neural networks; circuit realization; fast image processing; fuzzy membership functions; linear adaptive element; mixed-signal neural circuit; nonlinear image filters; nonlinear preprocessor; simplicial decomposition; simplicial neuro-fuzzy inferences; universal CNN cell circuit; Cellular neural networks; Circuits; Hypercubes; Image processing; Laboratories; Lattices; Least squares approximation; Pixel; Read only memory; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-6685-9

Type

conf

DOI

10.1109/ISCAS.2001.921355

Filename

921355