论文信息 - Non-Linear Image Registration on PC-Clusters Using Parallel FFT Techniques

Non-Linear Image Registration on PC-Clusters Using Parallel FFT Techniques

Reliable image registration is a key problem within the three-dimensional reconstruction of data obtained by two-dimensional image stacks. Here, a parallel implementation of the so-called elastic matching algorithm approach is presented. This algorithm is based on a fixpointtype iteration, where in each step a linear system of equations has to be solved. To compute the solution of the linear systems fast fourier techniques are used. The algorithm as well as some numerical examples are presented.

[1] U. Grenander,et al. Structural Image Restoration through Deformable Templates , 1991 .

[2] Gary E. Christensen,et al. Deformable Shape Models for Anatomy , 1994 .

[3] Jan Modersitzki,et al. Fast inversion of matrices arising in image processing , 1999, Numerical Algorithms.

[4] Karl Zilles,et al. Limitations of the principal-axes theory , 1997, IEEE Transactions on Medical Imaging.

[5] M. Boosten,et al. Performance Comparison of different High-Speed Networks with a Uniform Efficient Programming Interface , 1999 .

[6] T. Schormann,et al. Alignment of 3‐D brain data sets originating from MR and histology , 1993 .

[7] Jack Dongarra,et al. PVM: Parallel virtual machine: a users' guide and tutorial for networked parallel computing , 1995 .

[8] Gene H. Golub,et al. Matrix computations , 1983 .

[9] Corporate. IEEE Standard for Scalable Coherent Interface, Science: IEEE Std. 1596-1992 , 1993 .

[10] Jean-Philippe Thirion,et al. Non-rigid matching using demons , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11] Manfred Tasche,et al. Worst and Average Case Roundoff Error Analysis for FFT , 2001 .

[12] Charles L. Seitz,et al. Myrinet: A Gigabit-per-Second Local Area Network , 1995, IEEE Micro.