ECE
ABSTRACT
A novel method for image processing and pattern recognition using Discrete Fourier Transformations on the global pulse signal of a pulse-coupled neural network (PCNN) is presented in this paper.
The PCNN is an image transform that removes “unimportant” details while improving the overall quality of the image. It may also provides substantial noise smoothing without losing image pattern and shape information.
We describe the mathematical model of the PCNN and an original way of analyzing the pulse of the network in order to achieve better quality of the image ,scale and translation-independent recognition for isolated objects.
Click Here to Download