Multifractal Spectrum and their Applications in Metal Fracture Surface Images Identification

Based on the physical sense of multifractal spectrum, classification of the typical morphology of the metal fracture surface by obtaining the images character based on the multifractal spectrum will be described. The methods have unchangeable characteristic of the multifractal spectrum. Then the images can be classified by using artificial neural network. In this paper, 20 images of ductile fracture, stream design fracture, intergranular cracking fracture and crack propagation are used as a study samples and 20 images are used as a test samples. The data of the experiment explains the feasibility of the method.