Model-Based Segmentation of Surfaces Using Illumination Series

Automated visual inspection of surfaces plays an important role in the context of industrial production. Segmentation is a key method in image processing of such surfaces. The appearance of structured surfaces depends very much on their illumination. Hence, we apply an illumination that is variable in its direction and in its shape. Image series are taken by varying the direction of the illumination pattern. The segmentation is performed on this data basis. We present an approach that utilizes the Torrance and Sparrow model to estimate the local reflection properties of the surface. The parameters of this model are then used as features to classify each surface point individually.