Chaotic Brain Storm Optimization Algorithm in Objective Space for Medical Image Registration

Abstract

Image registration is the basis of medical image analysis whichhas profound significance in the field of medical image processing. In order to improve its accuracy, a method based on chaotic brain storm optimization algorithm in objective space(CBSO-OS) is proposed. The CBSO-OS increases its ability of global exploitation by replacing random function with guass map. Compared with other four optimization algorithms in image registration experiments, the root mean square error of the proposed algorithm is reduced by 0.69%, 2.26%, 3.54% and 1.37%, respectively. Meanwhile, the translation error of the proposed registration algorithm is the smallest. Experimental results show that the proposed registration algorithm effectively reduces the registration error of medical images so as to provide doctors with high-precision registered images.