非刚体图像配准中点对应关系的模糊分配技术  

Fuzzy Assignment of Point Correspondence in Non-rigid Image Registration

作　　者：上官晋太[1] 刘丽丽[1] SHANGGUAN Jintai;LIU Lili(Department of Computer Science and Technology,Changzhi College,Changzhi Shanxi 046011)

机构地区：[1]长治学院计算机系,山西长治046011

出　　处：《长治学院学报》2024年第5期69-76,共8页Journal of Changzhi University

基　　金：山西省高等学校教学改革创新项目(J20231289;J20231287);长治学院优秀课程“电子技术基础”。

摘　　要：非刚体图像配准中经常会用到基于特征的配准法,其中以基于点特征的联合估计法最为常用。为了解决传统的基于迭代最近点的联合估计法易陷入局部最小值点的问题,提出了模糊分配技术。利用点对之间的距离产生对应矩阵,此矩阵的取值随点集之间相对位置的变化连续改变,代替传统算法中对应矩阵的0-1取值模式。这样可以避免过早地排除掉潜在的对应点,从而可以最大概率地收敛于全局最优点,同时在迭代配准过程中逐步减小距离控制系数,以实现由粗到细的配准过程。仿真实验表明,和形状上下文、中心预对齐及传统方法相比,此方法可以使配准误差分别减小到77.5%、32.6%和23.2%左右。Feature-based registration methods are often used in non-rigid image registration,among which joint estimation method based on point features is the most commonly used.The traditional joint estimation method based on the iterative closest point is easy to fall into the local optimum.To address this problem,in this paper,a fuzzy assignment algorithm is proposed,with which the distance between point pairs is used to generate the corresponding matrix,and the value of this matrix changes continuously with the change of the relative positions between point sets,replacing the 0-1 value pattern of the corresponding matrix in the traditional algorithm.In this way,the potential corresponding points can avoid being eliminated prematurely,and the convergence to the global optimum can be achieved with maximum probability.At the same time,the distance control coefficient is gradually reduced in the iterative registration process to make the registration process from being coarse to fine.The simulation results show that,compared with shape context,center prealignment and traditional methods,the registration errors of this method can be reduced to 77.5%,32.6%and 23.2%respectively.

关 键 词：非刚体图像配准 迭代最近点 联合估计 模糊分配 全局最优 点对应关系 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]