In this paper we compare different ways of representing the global photometric changes in image intensities caused by changes in illumination and viewpoint, aiming at a balance between goodness-of-fit and low complexity. A series of model selection tests are performed for the case of outdoor imagery consisting of several views of several instances of billboards taken under different viewing angles and different illumination (natural light). Possible candidates for a transformation model on (R,G,B) color space are investigated and different approaches for the model selection problem are considered.

The results are used within ongoing research into computation of new invariant features for planar color patterns, as the model choice is an important issue to decide on when extracting invariants. These results can be of benefit to other areas of research into color pattern or object recognition, which motivated us to report here in detail about the model selection work.