Multiresolution Search of the Rigid Motion Space for Intensity Based Registration
This work addresses efficiency challenges in image registration for applications like medical imaging or computer vision, though it appears incremental as it builds on existing multiresolution and optimization methods.
The paper tackled the problem of improving efficiency in intensity-based image registration by analyzing how low-resolution target values bound high-resolution functions for rigid transformations, and demonstrated that incorporating a multiresolution scheme into a Lipschitz global optimization framework results in large gains in efficiency for 2D and 3D registration and symmetry detection tasks.
We study the relation between the target functions of low-resolution and high-resolution intensity-based registration for the class of rigid transformations. Our results show that low resolution target values can tightly bound the high-resolution target function in natural images. This can help with analyzing and better understanding the process of multiresolution image registration. It also gives a guideline for designing multiresolution algorithms in which the search space in higher resolution registration is restricted given the fitness values for lower resolution image pairs. To demonstrate this, we incorporate our multiresolution technique into a Lipschitz global optimization framework. We show that using the multiresolution scheme can result in large gains in the efficiency of such algorithms. The method is evaluated by applying to 2D and 3D registration problems as well as the detection of reflective symmetry in 2D and 3D images.