RECOGNITION OF DIFFERENT FRACTURE SURFACE MORPHOLOGIES USING COMPUTERIMAGE-PROCESSING TECHNIQUE

The software which enables us to classify six typically different frac ture surface morphologies, such as striations, equiaxed dimples, elong ated dimples, transgranular failures, intergranular failures, and clea vage failures, has been developed based upon computer image processing and pattern recognition. The texture analyses used here are the Fouri er power spectrum, generalized co-occurrence matrices, and three-dimen sional fracture surface topographies. Fourier power spectrum analyses are very powerful for recognizing striations and intergranular failure s, whereas a generalized co-occurrence matrix and fracture surface are a ratio are suitable for cleavage failures. We also point out that the membership values based upon a soft clustering method, a fuzzy C-mean s algorithm, allow the system an uncertain fracture surface. This incr eases the precision of recognition.