An edge detection scheme using radial basis function networks

A new edge detection scheme based on radial basis function networks is proposed. It is a two-tiered scheme where, in the first stage, each pixel in the input image is classified according to its potential for being part of an edge. The second stage then combines these pixels into true edges in the input image. Both stages use radial basis function networks. The scheme illustrates how the input space of edge patterns can be used to train the neural network with a minimum number of parameters. Compared with other neural network paradigms, the proposed scheme is simpler in terms of network size and computational requirements, and provides better results even in low-contrast images