Reflection-based Surface Segmentation using Active Illumination

Segmentation plays an important role in image processing. Its goal is to divide an image into disjoint parts by defined rules. We present a method to accomplish an illumination-based segmentation of structured surfaces based on surface properties. To this end, an illumination series - i.e. a series of images taken with directional light from different directions - is recorded. For each location of the surface, a signal is extracted which describes the intensity of the corresponding point depending on the illumination angle. From this signal, features are extracted that enable a pointwise segmentation of the surface. Aided by suitable parametric models, the surface reflectance is described, and the corresponding parameters are estimated from the intensity signal. Moreover, the effect of sampling the illumination space is discussed. On the one hand, it is desirable to keep the number of illumination angles as small as possible. On the other hand, a minimum number of images is needed to achieve a reliable segmentation. The performance of the proposed approach is demonstrated with real images. They prove that the higher data acquisition expense is compensated by a significant increase of both the spatial resolution and the robustness