Analysis of neural networks for edge detection

Abstract — This paper illustrates a novel method to an-alyze artificial neural networks so as to gain insight into their internal functionality. To this purpose, the elements of a feedforward-backpropagation neural network, that has been trained to detect edges in images, are described in terms of differential operators of various orders and with various angles of operation. Keywords—Neural networks, rule extraction, edge detec-tion, digital image processing, gradient filters. I