Cellular neural network based weighted median filter for real time image processing

Author

Kowalski, Jacek ; Kacprzak, Tomasz

Author_Institution

Inst. of Electron., Tech. Univ. Lodz, Poland

Volume

1

fYear

2001

fDate

6/23/1905 12:00:00 AM

Firstpage

545

Abstract

This paper describes a VLSI implementation of an analog image weighted median filter based on a cellular neural network (CNN) architecture for real-time applications. This filter consists of feedforward nonlinear template B operating within the window of 3 by 3 pixels around the central pixel being filtered. The basic block of this filter is a nonlinear coupler circuit, which realizes a nonlinear template B of the CNN. A technology for implementation is CMOS AMS 0.8 μm CYE

Keywords

CMOS integrated circuits; VLSI; analogue processing circuits; cellular neural nets; coupled circuits; feedforward neural nets; image processing; median filters; nonlinear network synthesis; real-time systems; 0.8 micron; CMOS AMS CYE technology; VLSI implementation; analog image weighted median filter; cellular neural network architecture; feedforward nonlinear template; nonlinear coupler circuit; nonlinear template; pixels; real time image processing; real-time applications; Brightness; Cellular neural networks; Circuits; Digital filters; Equations; Image processing; Information filtering; Information filters; Nonlinear filters; Steady-state;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.959074

Filename

959074