基于继承PSO算法的动态脑磁共振图像配准

Dynamic Brain Magnetic Resonance Image Registration Based on Adopted PSO Algorithm

提出了一种用于动态图像配准的混合角点继承PSO算法。该方法采用混合角点检测算子来提取角点,并将继承最优种群的思想引入到PSO优化算法中,即对当前图像配准得到的最优种群进行动态继承与变化后,再用于指导后续图像的配准。实验表明:所提出的算法不仅克服了传统的随机重启方式的脑磁共振图像配准算法中随机设定参数导致配准速度慢的问题,而且提高了图像的配准精度和稳定性。

An algorithm, based on hybrid corner adopted PSO algorithm, is proposed in this paper to achieve dynamic image registration. It extracts comers with a mixed corner detection factor and introduces the idea of inheriting the best population to PSO algorithm, i.e. inheriting and changing the best population from current image registered, and then uses it to guide subsequent image registering. The experimental results show that the new method overcomes the disadvantage of long computing time when registering many images continuously caused by the parameter generated randomly by the traditional manner and improves the registration accuracy and stability.