Project

Image Registration using Differential Evolution Based Algorithm Portfolios

The proposed system is based on Differential Evolution based Algorithm portfolios to automatically register medical images which is designed, implemented and tested through a set of 3D brain images. Image Registration is performed by searching the best affine transformation in terms of maximization of the mutual information between the first image and the transformation of the second one, and no control points are needed in this approach.For carrying out effective image registration two choices have to be made. The first choice is the type of geometric transformation to be considered to find correlations between the given images, while the second one involves finding the measure of match i.e. the feature on the value of which the effectiveness of the registration is evaluated. Once these choices are made, the measure of match can be maximized by using suitable optimization algorithms