Application of independent component analysis to edge detection

It has been shown that a typical Independent Component Analysis (ICA) of an image provides a good estimation for the responses of the neurons of the visual cortex and their patterns of excitation. In this paper we apply ICA to obtain a decomposition of the image into a set of basis or features. These particular features can be used to develop a new algorithm for detecting the edges of the image. The performance of the proposed approach is demonstrated experimentally.