Design of MIN/MAX cellular neural networks (MMCNNS) in CMOS technology

Author

Yen, Wen-Cheng ; Chen, Rong-Jian ; Lai, Jui-Lin

Author_Institution

Dept. of Electron. Eng., Nat. Lien-Ho Inst. of Technol., Miao Li, Taiwan

fYear

2002

fDate

22-24 Jul 2002

Firstpage

339

Lastpage

346

Abstract

The first VLSI implementation of the fuzzy cellular neural network (FCNN) structure is presented. The MIN/MAX CNN (MMCNN) is a special case of type-II FCNN, which consists only of local MIN and MAX operations. Due to the simple structure of the MMCNN, it is very suitable for VLSI implementation in image processing. Only one neuron cell, two multipliers, and nine min/max circuits realize the proposed MMCNN. Correct functions of the MMCNN in the erosion and dilation of the gray-scale mathematical morphology operation have been successfully verified in HSPICE simulation. FCNNs have great potential in the VLSI implementation of neural network systems in various signal processing applications.

Keywords

CMOS integrated circuits; SPICE; cellular neural nets; fuzzy neural nets; image processing; mathematical morphology; minimax techniques; CMOS technology; HSPICE simulation; MIN/MAX cellular neural networks; VLSI; fuzzy cellular neural network structure; gray-scale mathematical morphology operation dilation; gray-scale mathematical morphology operation erosion; image processing; min/max circuits; multipliers; neuron cell; signal processing; CMOS technology; Cellular neural networks; Circuit simulation; Fuzzy neural networks; Gray-scale; Image processing; Morphology; Neural networks; Neurons; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications, 2002. (CNNA 2002). Proceedings of the 2002 7th IEEE International Workshop on

Print_ISBN

981-238-121-X

Type

conf

DOI

10.1109/CNNA.2002.1035068

Filename

1035068