We introduce an image model for color texture based on spatial correlation functions defined both within and between color bands. We show that three-dimensional geometric transformations of a surface in the scene produce corresponding transformations in these correlation functions. From this analysis we derive invariants of color correlation functions that can be computed efficiently and that can be used for geometry-invariant recognition. We show experimentally that these invariants are effective for recognition in situations in which neither color distributions nor gray-scale texture is sufficient. After recognition the estimated color correlation functions can be used to recover the three-dimensional location and orientation of surfaces. The color-texture invariants can be used in the recognition of three-dimensional objects, the segmentation of images of three-dimensional scenes, and the searching of image databases.

Back to the ICVL homepage