Generation of three-dimensional random rotations in fitting and matching problems

An algorithm is developed to generate random rotations in three-dimensional space that follow a probability distribution arising in fitting and matching problems. The rotation matrices are orthogonally transformed into an optimal basis and then parameterized using Euler angles. The conditional distributions of the three Euler angles have a very simple form: the two azimuthal angles can be decoupled by sampling their sum and difference from a von Mises distribution; the cosine of the polar angle is exponentially distributed and thus straighforward to generate. Simulation results are shown and demonstrate the effectiveness of the method. The algorithm is compared to other methods for generating random rotations such as a random walk Metropolis scheme and a Gibbs sampling algorithm recently introduced by Green and Mardia. Finally, the algorithm is applied to a probabilistic version of the Procrustes problem of fitting two point sets and applied in the context of protein structure superposition.

[1]  J. A. Hartigan,et al.  Invariant Prior Distributions , 1964 .

[2]  Edwin R. Hancock,et al.  Recovering facial pose with the EM algorithm , 2002, Pattern Recognit..

[3]  N. Higham.  Applications of matrix theory , edited by M. J. C. Gover and S. Barnett. Pp 324. £40. 1989. ISBN 0-19-853625-9 (Oxford University Press) , 1990, The Mathematical Gazette.

[4]  Joseph G. Ibrahim,et al.  Monte Carlo Methods in Bayesian Computation , 2000 .

[5]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[7]  W. Kabsch.  A solution for the best rotation to relate two sets of vectors , 1976 .

[8]  Charles R. Johnson,et al.  Topics in Matrix Analysis , 1991 .

[9]  L. Devroye.  Non-Uniform Random Variate Generation , 1986 .

[10]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[11]  Peter J. Green,et al.  Bayesian alignment using hierarchical models, with applications in protein bioinformatics , 2005 .

[12]  N. Higham.  MATRIX NEARNESS PROBLEMS AND APPLICATIONS , 1989 .

[13]  R. E. Miles.  On random rotations in R3 , 1965 .

[14]  D. Theobald,et al.  Empirical Bayes hierarchical models for regularizing maximum likelihood estimation in the matrix Gaussian Procrustes problem , 2006, Proceedings of the National Academy of Sciences.