Microscope images of marble thin sections can be used to determine their geographical origin by means of the shapes, sizes, and spatial distribution of their grains. In this paper, we present a method that is the first step towards an automatic origin determination, namely, the segmentation of grains in digital images of thin marble sections. Each grain has a preferred direction, different from the one of its neighbors, that rules its behavior when illuminated with polarized light. Firstly, we perform an oversegmentation of the image in regions, each one corresponding only to a grain, although this one can be partitioned into several regions. Afterwards, from a sequence of images of the same sample, obtained with polarized light, we compute for each region two parameters which depend on the preferred direction of the grain to which it belongs. Finally, the set of parameter values for all the regions is the input to a region-merging procedure which achieves the final segmentation. We present the results for samples from six quarries, each one with different visual features. Copyright © 1996 Elsevier Science Ltd.
- Mathematical morphology