Skip to Main Content
In the last few decades, image registration (IR) has been established as a very active research area in computer vision. Over the years, IR's applications cover a broad range of real-world problems including remote sensing, medical imaging, artificial vision, and computer-aided design. In particular, medical IR is a mature research field with theoretical support and two decades of practical experience. Traditionally, medical IR has been tackled by iterative approaches considering numerical optimization methods which are likely to get stuck in local optima. Recently, a large number of medical IR methods based on the use of metaheuristics such as evolutionary algorithms have been proposed providing outstanding results. The success of the latter modern search methods is related to their ability to perform an effective and efficient global search in complex solution spaces like those tackled in the IR discipline. In this contribution, we aim to develop an experimental survey of the most recognized feature-based medical IR methods considering evolutionary algorithms and other metaheuristics. To do so, the generic IR framework is first presented by providing a deep description of the involved components. Then, a large number of the latter proposals are reviewed. Finally, the most representative methods are benchmarked on two real-world medical scenarios considering two data sets of three-dimensional images with different modalities.