Selective Metamorphosis for Growth Modelling with Applications to Landmarks

Andreas Bock, Alexis Arnaudon, Colin J. Cotter

Abstract: We present a framework for shape matching in computational anatomy allowing users control of the degree to which the matching is diffeomorphic. The control is a function defined over the domain describing where to violate the diffeomorphic constraint. The location can either be specified from prior knowledge of the growth location or learned from data. We consider landmark matching and infer the distribution of a finite dimensional parameterisation of the control via Markov chain Monte Carlo. Preliminary analytical and numerical results are shown and future paths of investigation are laid out.