Cellular neural network based weighted median filter for real time image processing
Jacek M. Kowalski, T. Kacprzak · 2002
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 /spl mu/m CYE.