|
Next: Transformation Parameterization Up: Image Registration Previous: Unidirectional Linear-elastic Registration algorithm Consistent Linear-elastic Registration AlgorithmA common problem with unidirectional registration algorithms is that they rarely produce forward and reverse transformations that are inverses of one another. The consistent linear-elastic image registration algorithm[16,17] was developed to overcome this problem. In this approach the forward transformation that maps to and reverse transformation that maps to are jointly estimated subject to the constraint that and are inverses. The transformations are constructed as and where and are the associated deformation fields. The consistent linear-elastic image registration problem can be stated
as where and are estimated to transform image to and to , respectively. The first two integrals are equivalent to independently estimating the forward and reverse transformations between and as stated in Eq. 5. The third integral is referred to as the inverse consistency constraint. This constraint is minimized when the forward and reverse transformations are inverses of one another. This term also couples the estimation of the forward and reverse transformations together.
Next: Transformation Parameterization Up: Image Registration Previous: Unidirectional Linear-elastic Registration algorithm Gary E. Christensen 2002-07-04 |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Copyright © 2002 The University of Iowa. All rights reserved.
Iowa City, Iowa 52242 |
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||