In this paper we describe a feature-based approach to object recogniti
on. The correspondence problem is solved by optimization of an energy
function. While similar approaches suffer from local minima, we derive
an energy function suitable for minimizing by deterministic annealing
. Hereby global optimization can be achieved. Algorithms matching mode
l features to image features in a coarse-to-fine manner are described.
(C) 1997 Elsevier Science B.V.