Title :
On the CNN template design for Gabor-type filters based on Pade approximation
Author :
David, E. ; Ungureanu, Paul ; Ansorge, M. ; Goras, Liviu
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.
Keywords :
Gaussian distribution; approximation theory; cellular neural nets; filters; image processing; CNN template design; Gabor-type filters; Gaussian filters; Pade approximation; cellular neural networks; computer-vision applications; image processing;
Conference_Titel :
Signals, Circuits and Systems, 2003. SCS 2003. International Symposium on
Print_ISBN :
0-7803-7979-9
DOI :
10.1109/SCS.2003.1226982
