19 February 2013 A stochastic approach for non-rigid image registration
Author Affiliations +
This note describes a non-rigid image registration approach that parametrizes the deformation field by an additive composition of a similarity transformation and a set of Gaussian radial basis functions. The bases’ centers, variances, and weights are determined with a global optimization approach that is introduced in this work. This approach consists of simulated annealing with a particle filter based generator function to perform the optimization. Additionally, a local refinement is performed to capture the remaining misalignment. The deformation is constrained to be physically meaningful (i.e., invertible). Results on 2D and 3D data sets demonstrate the algorithm’s robustness to large deformations.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ivan Kolesov, Ivan Kolesov, Jehoon Lee, Jehoon Lee, Patricio Vela, Patricio Vela, Allen Tannenbaum, Allen Tannenbaum, } "A stochastic approach for non-rigid image registration", Proc. SPIE 8655, Image Processing: Algorithms and Systems XI, 86550U (19 February 2013); doi: 10.1117/12.2004400; https://doi.org/10.1117/12.2004400

Back to Top