REPRESENTATION AND THREE-DIMENSIONAL INTERPRETATION OF IMAGE TEXTURE: AN INTEGRATED APPROACH.

A perspective view of a slanted textured surface shows systematic changes in the density, area and aspect-ratio of texture elements. These apparent changes in texture element properties can be analyzed to recover information about the physical layout of the scene. However, in practice it is difficult to identify texture elements, especially in images where the texture elements are partially occluded or are themselves textured at a finer scale. To solve this problem, it is necessary to integrate the extraction of texture elements with the recognition of scene layout. A method for recovering the orientation of textured surfaces, while simultaneously identifying texture elements is presented. A multiscale region detector, based on measurements in a DEL **2G (Laplacian-of-Gaussian) scale-space, is used to construct a set of candidate texture elements. True texture elements are selected from the set of candidate texture elements by finding the planar surface that best predicts the observed properties of the candidate texture elements. Results are shown for a variety of natural textures, including waves, flowers, rocks, clouds, and dirt clods.