On the CNN template design for Gabor-type filters based on Pade approximation

Abstract

Gabor filters are widely used in various image processing and computer-vision applications. Being computationally intensive, analog implementation using Cellular Neural Networks (CNN) can be an attractive solution. In this communication is presented a method for CNN template design of Gabor like filters, based on Pade approximation of Gaussian filters. The errors of approximation are evaluated for various neighborhood radii.