Building a color classification system for textured and hue homogeneous surfaces: system calibration and algorithm

We present a system for classifying the color aspect of textured surfaces h aving a nearly constant hue (such as wooden boards, textiles, wallpaper, et c.). The system is designed to compensate for small fluctuations (over time ) of the light source and for inhomogeneous illumination conditions (shadin g correction). This is an important feature because even in industrial envi ronments where the lighting conditions are controlled, a constant and homog eneous illumination cannot be guaranteed. Together with an appropriate came ra calibration (which includes a periodic update), our approach offers a ro bust system which is able to "distinguish" (i.e., classify correctly) betwe en surface classes which exhibit visually barely perceptible color variatio ns. In particular, our approach is based on relative (not absolute) color m easurements. In this paper, we outline the classification algorithm while f ocusing in detail on the camera calibration and a method for compensating f or fluctuations of the light source.