Multi-image registration based on entropy of normalized mutual information vector 基于归一化互信息(NMI)向量熵的多幅图像配准方法
Further, studies the method of normalized mutual information. 在此基础上对比研究了归一化互信息(NMI)配准法。
Normalized mutual information was adopted as the similarity measure. 使用归一化互信息(NMI)作为相似性量度。
In order to improve precision and speed up the convergence of image registration, we focus on image registration optimization algorithm based on the normalized mutual information, also summarize the advantages and disadvantages of classic algorithm, then propose an improved algorithm, and simulation experiment. 为提高图像配准精度,加快收敛速度,本文以归一化互信息(NMI)为基础,重点对图像配准中优化算法进行研究,通过总结对比经典算法的优势和不足,提出了改进算法,并进行了仿真实验。
The normalized mutual information is based on the ratio of the combined entropy and abundance entropy, which makes getting the optimal result easily. 归一化互信息(NMI)进行配准时,考虑了边缘熵和联合熵的比值,配准结果容易得到最优。