An optimal control approach for the registration of image time-series

Abstract

This paper discusses an optimal control approach for the registration of image time-series (growth modeling). It combines and augments work on an optimal control formulation to optical flow with theory from large-displacement diffeomorphic image registration. The unification of the two viewpoints leads to (i) a more efficient computation of the gradient of the optimization problem, (ii) an easier numerical implementation, and (iii) an intuitive interpretation of the adjoint equation underlying the optimization problem. Further, a novel formulation for the unbiased estimation of image correspondences across time is proposed.