An Approach to 3D Medical Image Registration Using Group Search Optimizer
Chao Zeng -, Hongli Lin -, Min Gang Xu · Journal of Convergence Information Technology · 2013
Image registration has become a hot topic in compute vision and shown its variety applications in medical areas. The best alignment of images could be estimated by maximization a cost function using an iterative optimization, and thus optimization is one of the most important parts in an image registration method. Local optimizations, such as Powell’s method, frequently failed due to the existence of local minima in the cost function, and therefore, global methods are required. In this paper, a new evolutionary algorithm, group search optimizer is introduced to solve rigid registration problems for 3D biomedical images. A two stage schema, in which group search optimizer is used in the first stage for a coarse registration and Powell’s method is used in the following stage for a refine registration, is proposed. Eleven image registration methods are studied and compared, and the results demonstrate that group search optimizer is useful to solve the image registration problems with high accuracy in our proposed schema.