A texture analysis approach to corrosion image classification

Abstract

A method is described for the classification of corrosion images using texture analysis methods. Two morphologies are considered: pit formation and cracking. The analysis is done by performing a wavelet decomposition of the images, from which energy feature sets are computed. A transform that turns the wavelet features into rotation invariant ones is introduced. The classification is performed with a Learning Vector Quantization network and comparison is made with Gaussian and k-NN classifiers. The effectivity of the method is shown by tests on a set of 398 images.