Feature-based image registration by means of the CHC evolutionary algorithm

Image registration has been a very active research area in the computer vision community. In the last few years, there is an increasing interest on the application of evolutionary computation in this field and several evolutionary approaches have been proposed obtaining promising results. In this contribution we introduce the use of an advanced evolutionary algorithm, CHC, to solve the 3D image registration problem. The new proposal will be validated using different shapes (both synthetic and magnetic resonance images, and with several of the latter affected by noise and occlusion), considering four different transformations for each of them, and comparing the results with those from ICP, from the usually applied binary-coded genetic algorithms, and from real-coded genetic algorithms.