Comparison of shape features for the classification of wear particles

Wear particle shapes are divided into four classes: Regular; irregular Circular and Elongated. They have been classified here using back-propagation neural networks which have been trained using different see of rotation-, scale-and translation-invariant shape features derived from particle boundaries. The features include: Fourier coefficients based on either boundary curvature analysis or XY co-ordinates of boundary points; statistical moments of the curvature distribution including standard deviation, skewness and kurtosis; and two general shape descriptions, aspect ratio and roundness. In order to evaluate the performances of the features, a series of tests have been carried out on a wear particle database, and the results are compared. The boundary-curvature-based Fourier descriptors produce a shape classifier with the highest performance. The neural network trained by the Fourier features derived from the boundary data provides a slightly lower classification rate which is similar to that achieved using three statistical moments combined with the two general shape features. (C) 1997 Elsevier Science Ltd. All rights reserved.