The RGF pandemonium: a low-level representational model for images

In this work, we have reformulated the selection of a few responding units tuned to patterns of activity from the Fourier spectrum as a multilayer system composed of four stages of different kinds of feature detectors. The system output is a sparse representation for images that produces an organization according to object power discrimination. The resultant multilayer system provides a more efficient representation for later stages of processing because it possesses a higher degree of perceptual independence among its outputs.