Gradient based nonuniform subsampling for information-theoretic alignment methods

We examine the computation of information-theoretic image registration metrics and propose two (deterministic and stochastic) nonuniform subsampling methods for improving the efficiency. The proposed schemes attempt to use only the most relevant information as the basis of the computation. Both methods are shown to yield considerable improvement over the current practice of uniform subsampling. Theoretical and experimental evidence is provided.

[1]  Guy Marchal,et al.  Multi-modality image registration by maximization of mutual information , 1996, Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis.

[2]  L. Györfi,et al.  Nonparametric entropy estimation. An overview , 1997 .

[3]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[4]  H. Krim,et al.  An information divergence measure for ISAR image registration , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[5]  Paul A. Viola,et al.  Multi-modal volume registration by maximization of mutual information , 1996, Medical Image Anal..

[6]  Alfred O. Hero,et al.  Applications of entropic spanning graphs , 2002, IEEE Signal Process. Mag..

[7]  Alfred O. Hero,et al.  Image registration with minimum spanning tree algorithm , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[8]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[9]  Mert R. Sabuncu,et al.  Fast alignment of digital images using a lower bound on an entropy metric , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..