Registration and segmentation are the two most prominent applications in computer vision. Traditional techniques aim to recover transformations or segmentation maps that create correspondence between images & delineate structures of interest. Despite enormous progress of these areas, in particular due to domain-knowledge still the number of methods that encode uncertainties of the estimation process are limited. In this talk, we present a rather comprehensive tutorial to image segmentation and object extraction through implicit representations. We will start with presenting model-free methods purely based on the observed image and we will converge towards more and more complicated statistical representations of prior knowledge. We will conclude with new techniques aiming to introduce estimations of the uncertainty associated with the obtained solution are presented. Such measures can be used wi thin non-parametric statistical prior shape models to induce constraints in the segmentation process where uncertainties determine the local importance of the model. Therefore we are able to relax constraints in a qualitative fashion according to the nature of the data support while we are able to provide matching measures that account in an implicit fashion for the segmentation errors. Promising results demonstrate the potentials or our method.