Landmark-based elastic registration using approximating thin-plate splines

By Karl Rohr, H. Siegfried Stiehl, Rainer Sprengel, Thorsten M. Buzug, Jürgen Weese, M. Kuhn. IEEE Transactions on Medical Imaging, 2001

495 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5bece5eb196ec55a1b1db469d747ff4d61935108

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

A Review of Geometric Transformations for Nonrigid Body Registration (2008, background): “[78], [79] proposed an approximating rather than interpolating TPS that is more robust to outliers which occur because of errors in feature (landmark) localization.”
Deformable Medical Image Registration: A Survey (2013, background): “Furthermore, TPS do not take into consideration possible errors in the estimation of the displacements in the landmark positions [110].”
Medical image registration: a review (2014, background): “Some authors, as in Rohr et al. (2001), Serifovic-Trbalic et al. (2008), have used approximating TPS rather than interpolating TPS, since the former are more robust to the outliers which can occur in the landmark or point localisations.”
Elastic registration of biological images using vector-spline regularization (2005, background): “A number of landmark-only registration algorithms have been developed because landmarks are essential in applications where images show very little information, or where the information in the target image is not the same as in the source images [8], [9], [10], [23].”
Deformable medical image registration: setting the state of the art with discrete methods. (2011, methodology): “(18) in a more efficient way solely based on the landmarks as”
Non-rigid image registration: theory and practice. (2004, background): “prominences of the ventricular system), or geometrically [29–32] by analysing how voxel intensity varies across an image.”
DRAMMS: Deformable Registration via Attribute Matching and Mutual-Saliency Weighting (2009, methodology): “Existing deformable registration methods can be generally classified into two main categories: voxel-wise methods (e.g., [1,2,3,4,5,6,7]) and landmark/feature-based methods (e.g., [8,9, 10 ,11,12,13,14]).”
Completing 3D object shape from one depth image (2015, background): “The usual approximation TPS deformation model [31] regresses the parameters of a function f which maps every source point u to an approximation of their target location v within a certain tolerance to the bending energy involved.”
A new point matching algorithm for non-rigid registration (2003, background): “We are currently looking at the work in [32] for ways of introducing regularization parameters on both the affine and the deformation in a principled way.”