基于T分布混合模型的点集非刚性配准算法

周志勇1; 薛维琴1; 郑健3; 蒯多杰3; 张涛3; 胡粟4

doi:10.3788/OPE.20132109.2405

您当前的位置：

首页 >

文章列表页 >

基于T分布混合模型的点集非刚性配准算法

信息科学 | 更新时间：2020-08-12

- 基于T分布混合模型的点集非刚性配准算法
- Point sets non-rigid registration using T-distribution mixture model
- 光学精密工程 2013年21卷第9期页码：2405-2420
- 作者机构：
  
  1. 中国科学院大学北京,中国,100049
  2. 中国科学院长春光学精密机械与物理研究所，吉林长春 130033
  3. 中国科学院苏州生物医学工程技术研究所，江苏苏州 215163
  4. 苏州大学附属第一医院,江苏苏州,215006
- 作者简介：
- 基金信息：
  
  三维成像和诊断关键技术研究();江苏省基础研究计划资助项目();苏州医工所二期建设重大项目&ldquo();PET/CT-医用回旋加速器系统研制&rdquo()
- DOI：10.3788/OPE.20132109.2405
  中图分类号： TP391
- 收稿日期：2012-04-09，
  
  修回日期：2012-07-06，
  
  网络出版日期：2013-09-30，
  
  纸质出版日期：2013-09-15
- 稿件说明：
移动端阅览
周志勇薛维琴郑健蒯多杰张涛胡粟. 基于T分布混合模型的点集非刚性配准算法[J]. 光学精密工程, 2013,21(9): 2405-2420

ZHOU Zhi-yong XUE Wei-qin ZHENG Jian KUAI Duo-jie ZHANG Tao H U Su. Point sets non-rigid registration using T-distribution mixture model[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2405-2420
周志勇薛维琴郑健蒯多杰张涛胡粟. 基于T分布混合模型的点集非刚性配准算法[J]. 光学精密工程, 2013,21(9): 2405-2420 DOI： 10.3788/OPE.20132109.2405.

ZHOU Zhi-yong XUE Wei-qin ZHENG Jian KUAI Duo-jie ZHANG Tao H U Su. Point sets non-rigid registration using T-distribution mixture model[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2405-2420 DOI： 10.3788/OPE.20132109.2405.

摘要

考虑高斯混合模型（TMM）的点集非刚性配准算法易受异常点和重尾点的影响，提出了基于t分布混合模型的运动一致性非刚性配准算法。通过期望最大化（EM）框架的完整数据定义将高斯混合模型推广为t分布混合模型，使用EM算法最小化参数的条件期望获得非刚性配准参数的闭合解。在EM算法中计算浮动点集各个点的先验权重，减小异常点和重尾点对配准结果的影响；计算浮动点集各个点的自由度，自适应地改变每个点的概率密度分布模型，提高算法的鲁棒性，并避免了异常点水平估计误差对配准结果的影响。在t分布混合模型的条件期望函数中加入点集位移的正则项，使邻近点具有运动一致性（CPD）。仿真数据表明，当噪声水平很高时，TMM-CPD仍可以精确配准点集，且误差仅为对比算法的1/10。真实图像的近似椭圆状分布、管状分布和三维点云状分布的点集配准结果表明，TMM-CPD的配准误差仅为对比算法的42.0%、80.1%和77.5%。实验表明，TMM-CPD配准含有重尾点和异常点的点集，具有精度高、鲁棒性好和受重尾点与异常点干扰小等优点。

Abstract

A robust non-rigid registration approach with a t-distribution Mixture Model(TMM) was proposed because point sets as Gaussian mixture model is vulnerable to the outliers and the data with longer than normal tails. The Gaussian mixture model was extended to the students-t Mixture Model by full data definition in the Expectation Maximazation(EM) frame

then the closed solutions of the parameter set of the t-distribution mixture model were solved by re-parameterization of the t-distribution mixture model in the EM algorithm. The priori-weight of each float point was calculated in EM framework to reduce the effects of outliers and the data with longer than normal tails on the matching results. The degree of freedom of each float point in the t-distribution mixture model was calculated to change the probability density distribution

improve the robustness of the algorithm and avoid the effect of estimating the outlier level of point sets that may bring additional errors. The conditional expectation function in t-distribution mixture model was added a regular item of point set

so that the points have a feature of Coherent Point Drift(CPD). The simulation data show that the error from the TMM-CPD is only one tenth of that from comparison algorithms. When the point sets are approximate ellipse shape

tubular and three dimensions

the registration errors of TMM-CPD are only 42.0%

80.1% and77.5% of those using comparison algorithms

respectively. The experiments show that this non-rigid registration approach using the t-distribution mixture model has features of high-accuracy

good robustness compared to other point set registration algorithms for point sets containing outliers and data with longer than normal tails.

关键词

Keywords

references

纪华, 吴元昊, 孙宏海,等. 结合全局信息的SIFT特征匹配算法[J]. 光学精密工程, 2009,17(2): 439-444.JI H, WU Y H, SUN H H, et al.. SIFT feature matching algorithm with global information[J]. Opt. Precision Eng., 2009, 17(2):439-444. (in Chinese)[2]谢雨来,李醒飞,吕津玮. 基于SURF算法的水下图像实时配准方法[J]. 计算机辅助设计与图形学学报, 2010, 22(12): 2215-2220.XIE Y L, LI X F, LV J W. Underwater images real-time registration method based on SURF [J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(12): 2215-2220. (in Chinese)[3]PAULY M, MITRA N J, GIESEN J. et al.. Example-based 3D Scan Completion [C]. Proceedings of the third Euro graphics Symposium on Geometry Processing, Aire-la-Ville, Switzerland: SGP, 2005: 23-32.[4]PAUL J B, NEIL D M. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.[5]BIN L, HANCOCK E R. Structural graph matching using the EM algorithm and singular value decomposition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(10): 1120-1136.[6]CHUI H, RANGARAJAN A. A feature registration framework using mixture models [C]. IEEE Workshop on Mathematical Methods in Biomedical Image Analysis, South Carolina, US, 2000:190-197.[7]REVOW M, MILLIAMS C K I, HINTON G E. Using generative models for handwritten digit recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(6): 592-606.[8]HAILI C, ANAND R. A new point matching algorithm for non-rigid registration[J]. Computer Vision and Image Understanding, 2003, 89(2-3): 114-141.[9]BING J, BABA C V. A robust algorithm for point set registration using mixture of gaussians [C]. Proceedings of the Tenth IEEE International Conference on Computer Vision, Beijing, China, 2005: 1246-1251.[10]DEMPSTER A. Maximum likelihood from incomplete data via the EM algorithm [J]. Journal of the Royal Statistical Society, 1977, 39(1): 1-38.[11]MYRONENKO A, SONG X B. Point set registration: coherent point drift [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12):2262-2275.[12]聂宏宾,侯晴宇,赵明,等. 基于似然函数EM迭代的红外与可见光图像配准[J]. 光学精密工程, 2011, 19(3): 657-663.NIE H B, HOU Q M, ZHAO M, et al.. IR/ visible image registration based on EM iteration of log -likelihood function[J]. Opt. Precision Eng., 2011, 19(3): 657-663. (in Chinese)[13]MYRONENKO A, SONG X B, MIGUEL A. Non-rigid point set registration: coherent point drift [C]. Twenty-First Annual Conference on Neural Information Processing Systems, Hyatt Regency Vancouver, Canada, NIPS 2007:1009-1016.[14]WANG P, WANG P, QU Z G, et al.. A refined Coherent Point Drift (CPD) algorithm for point set registration[J]. Science China, 2011, 54(12): 2659-2666.[15]GEOFFREY M, DAVID P. Robust cluster analysis via mixtures of multivariate t-distributions [J]. Advances in Pattern Recognition, 1998, 1451:658-666.[16]DAVID P, GEOFFREY M. Robust mixture modeling using the t-distribution[J]. Statistics and Computing, 2000, 10(4): 339-348.[17]DEMETRIOS G, CHRISTOPHOROS N, ARISTIDIS L. The mixtures of students t-distributions as a robust framework for rigid registration [J]. Image and Vision Computing, 2009, 27(9): 1285-1294.[18]WANG H X, ZHANG Q B, LUO B, et al.. Robust mixture modeling using multivariate T-distribution with missing information [J]. Pattern Recognition Letters, 2004, 25(6): 701-710.[19]ZHE C, SIMON H. On different facets of regularization theory [J]. Neural Computation, 2002, 14(12): 2791-2846.[20]GIROSI F, JONES M, POGGIO T. Regularization theory and neural networks architectures [J]. Neural Computation, 1995, 7(2): 219-269.

浏览量

145

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于图像特征和光流场的非刚性图像配准

改进Demons算法的非刚性医学图像配准