MULTIDIMENSIONAL ALIGNMENT USING THE EUCLIDEAN DISTANCE TRANSFORM

We present a methodology for alignment of multidimensional data sets t hat is based on the Euclidean distance transform and the Marquardt-Lev enberg optimization algorithm. The proposed approach operates on pixel or voxel descriptions of objects to be matched and estimates the para meters of a space transformation for optimal alignment of objects. The computational cost of an algorithm developed with this method is esti mated. The methodology is tested by developing an algorithm for rigid body transformation alignment of three-dimensional data sets. Tests wi th synthetic and real objects indicate that the method is accurate, re liable, and robust. (C) 1997 Academic Press.