Registering a Non-Rigid Multi-Sensor Ensemble of Images

Abstract

Image registration is the task of aligning two or more images into the same reference frame to compare or distinguish the images. The majority of registration methods deal with registering only two images at a time. Recently, a clustering method that concurrently registers more than two multi-sensor images was proposed, dubbed ensemble clustering. In this thesis, we apply the ensemble clustering method to deformable registration scenario for the first time. Non-rigid deformation is implemented by a FFD model based on B-splines. A regularization term is added to the cost function of the method to limit the topology and degree of the allowable deformations. However, the increased degrees of freedom in the transformations caused the Newton-type optimization process to become ill-conditioned. This made the registration process unstable. We solved this problem by using the matrix approximation afforded by the singular value decomposition (SVD). Experiments showed that the method is successfully applied to non-rigid multi-sensor ensembles and overall yields better registration results than methods that register only 2 images at a time. In addition, we parallelized the ensemble clustering method to accelerate the performance of the method. The parallelization was implemented on GPUs using CUDA (Compute Unified Device Architecture) programming model. The GPU implementation greatly reduced the running time of the method.