Improved Flower Pollination Algorithm and its Application in Medical Image Registration

Abstract:
Aiming at the problems of poor accuracy, easy to fall into local maximum and slow convergence in existing medical image registration method. Puts forward an improved flower pollination algorithm and in application in medical image registration, redefined the global and local pollination iterative formula of basic flower pollination algorithm, increased the diversity of population and the ability of local exploration, better balance the global search and local search of algorithm. Compared with the basic flower pollination algorithm, cuckoo search algorithm and Powell algorithm, Simulation experiments of different image sizes show that the improved flower pollination algorithm has good robustness and can accomplish the medical image registration task quickly and accurately. Moreover, the larger the image, the more obvious the advantage, providing a high efficiency and high precision method for medical image registration.