Multiresolution image modelling
R. Wilson · Electronics & Communications Engineering Journal · 1997
A novel approach to the statistical modelling of images based on widely used multiresolution image representations, such as pyramids and wavelets, is presented. It is shown how models which are causal in the scale dimension provide an effective way of expressing the concept of successive approximation, or coarse-fine refinement, by the addition of details to the coarse structure of images. The ideas are illustrated using applications including image enhancement, data compression and segmentation.