Segmenting Textured 3D Surfaces Using the Space/Frequency Representation

Abstract

Segmenting 3D textured surfaces is critical for general image understanding. Unfortunately, current efforts at automatically understanding image texture are based on assumptions that make this goal impossible. Texture segmentation research assumes that the textures are flat and viewed from the front, while shape-from-texture work assumes that the textures have already been segmented. This deadlock means that none of these algorithms will work reliably on images of 3D textured surfaces. We have developed an algorithm that can segment an image containing nonfrontally viewed, planar, periodic textures. We use the spectrogram (local power spectrum) to compute local surface normals from small regions of the image. This algorithm does not require unreliable image feature detection. Based on these surface normals, we compute a "frontalized" version of the local power spectrum which shows what the region's power spectrum would look like if viewed from the front. If neighboring regions have similar frontalized power spectra, they are merged. The merge criteria is based on a description length formula. We demonstrate the segmentation on images with real textures. To our knowledge, this is the first program that can segment 3D textured surfaces by explicitly accounting for shape effects.