Color image registration under illumination changes

Abstract

The estimation of parametric global motion has had a significant attention during the last two decades, but despite the great efforts invested, there are still open issues. One of the most important ones is related to the ability to recover large deformation between images in the presence of illumination changes while kipping accurate estimates. Illumination changes in color images are another important open issue. In this paper, a Generalized least squared-based motion estimator is used in combination with color image model to allow accurate estimates of global motion between two color images under the presence of large geometric transformation and illumination changes. Experiments using challenging images have been performed showing that the presented technique is feasible and provides accurate estimates of the motion and illumination parameters