Non-parametric registration of medical image data using Schatten-q-NormsMS28

One keytask in modern medical imaging is image registration. It is the task of spatially aligning two or more images. A major problem is the similarity of images. To measure similarity, so-called distance measures are applied. We present a novel measure using Schatten-q-Quasinorms which are based on Singular Value Decompositions of a matrix of the images' gradients. The theoretical background is discussed and promising results are presented.

This presentation is part of Minisymposium “MS28 - Diffeomorphic Image Registration: Numerics, Applications, and Theory (2 parts)
organized by: Andreas Mang (Department of Mathematics, University of Houston) , George Biros (Institute for Computational Engineering and Sciences, University of Texas at Austin) .

Kai Brehmer (Institute of Mathematics and Image Computing, University of Lübeck)
Benjamin Wacker (University of Lübeck)
Jan Modersitzki (University of Luebeck)
image registration, inverse problems