A new approach to image registration is proposed. The approach enables the proper segregation of the transformation space into a low dimensional so-called coarse space and a remaining non-linear so- called fine part. The segregation concept is combined with a multilevel approach, where the two parts are treated simultaneously. Modeling and computation issues are discussed. Finally, we present a highly non-linear real life example.
|Title of host publication||Real-Time PDE-Constrained Optimization|
|Number of pages||13|
|Publication status||Published - 01.01.2007|