根据图像灰度联合概率分布函数与图像相似程度之间的关系,提出了一种基于算术 几何均值距离的多模态图像配准新测度。与基于信息论的测度不同,新测度不再要求概率分布必须满足连续性的要求。实验结果表明,所提出的新测度比基于信息论的测度具有更强的噪声鲁棒性和计算量更小。 According to the relationship between the joint probability distribution function of image gray level and the degree of similarity of images, a new measure of multimodal image registration based on distance of arithmetic geometric mean is proposed. Unlike information theory-based measures, the new measure no longer requires that the probability distribution must satisfy continuity requirements. Experimental results show that the proposed new measure has more robustness and computational complexity than the information-based measure.