Highlight separation and surface orientations for 3-D specular objects

The authors present a normal vector equalization method for separating probable highlights and obtaining surface orientations of 3-D specular objects. Based on the simplified Torrance-Sparrow model of specular reflection and the empirical Lambertian reflection model, this method uses a set of three monochromatic images taken from three different illumination directions, separates probable highlights from those images, and generates a set of three Lambertian (highlight-free) images and a set of three specular (highlight-only) images. Surface orientations are obtained using the Lambertian images by solving an imaging equation for a Lambertian surface. Computer simulations and experiments with real objects have been performed. The theoretical framework for measuring surface parameters which represent optical characteristics of the surface is also discussed