GLOBAL COLOR CONSTANCY - RECOGNITION OF OBJECTS BY USE OF ILLUMINATION-INVARIANT PROPERTIES OF COLOR DISTRIBUTIONS

Color pixel distributions provide a useful cue for object recognition but are dependent on scene illumination. We develop an algorithm that assigns color descriptors to an object that depend on the surface prop erties of the object and not on the illumination. An object is defined by a set of possibly textured surfaces and gives rise to a color pixe l distribution. For a trichromatic system, the algorithm assumes a thr ee-dimensional linear model for surface spectral reflectance. There ar e no assumptions about the contents of the scene and only weak constra ints on the illumination. The global color invariants can be computed in an amount of time that is proportional to the number of pixels that define an object. A set of experiments on complex scenes under variou s illuminants demonstrates that the global color constancy algorithm p erforms significantly better than previous recognition algorithms base d on color distribution.