A Probabilistic Neural Network Edge detector for 2 Dimensional Gray Scale Images

A Probabilistic Neural NEtwork (PNN) classifier is used to design an edge detection algorithm for 2 dimensional gray scale images of rocks. It is shown hos a very sparse training set made up of a small number of example vectors is sufficient to generalise the edge detection around each and every rock. The data is also applied to the Backpropagation Neural Network (BON) classifier for comparison. Many industrial image processing problems for which it is difficult to develop a priori processing rules can be solved conveniently in a similar way.