Resumen
The paper deals with a definition of typicalstructure forms, which can be extracted from the surface of sedimentary grains. The co-occurrence features are used for this purpose. To find typical patterns, the K-means clustering technique is used to group related data in feature space. Then,it is visually investigated if related data in feature space are also related when being perceived by human. The scheme for a specific grain texture definition is proposed and three models of grain textures are experimentally created. The first model involves especially significant grain corners and edges, the second model involves homogeneous parts of a grain, the third model can be used for coarse and abraded surface recognition.