基于全局与局部相似性测度的非刚性点集配准

doi:10.11772/j.issn.1001-9081.2019040681

计算机应用 ›› 2019, Vol. 39 ›› Issue (10): 3028-3033.DOI: 10.11772/j.issn.1001-9081.2019040681

• 虚拟现实与多媒体计算 • 上一篇下一篇

基于全局与局部相似性测度的非刚性点集配准

彭磊^1,2, 杨秀云³, 张裕飞², 李光耀¹

1. 同济大学电子与信息工程学院, 上海 201804;
2. 山东第一医科大学(山东省医学科学院) 医学信息工程学院, 山东泰安 271016;
3. 山东第一医科大学(山东省医学科学院) 现代教育技术中心, 山东泰安 271016

收稿日期:2019-04-22 修回日期:2019-06-23 发布日期:2019-08-21 出版日期:2019-10-10
通讯作者: 彭磊
作者简介:彭磊(1977-),男,山东泰安人,副教授,硕士,CCF会员,主要研究方向:医学图像处理、机器学习;杨秀云(1982-),女,山东聊城人,助理工程师,硕士,主要研究方向:医学图像处理;张裕飞(1965-),男,山东微山人,教授,硕士,主要研究方向:医学信息学;李光耀(1965-),男,安徽安庆人,教授,博士,主要研究方向:计算机视觉、图像处理。
基金资助:
山东省自然科学基金资助项目（ZR2015FL005）；泰安市科技发展计划项目（2017GX0045）。

Non-rigid point set registration based on global and local similarity measurement

PENG Lei^1,2, YANG Xiuyun³, ZHANG Yufei², LI Guangyao¹

1. College of Electronics and Information Engineering, Tongji University, Shanghai 201804, China;
2. College of Medical Information Engineering, Shandong First Medical University & Shandong Academy of Medical Sciences, Tai'an Shandong 271016, China;
3. Modern Education Technology Center, Shandong First Medical University & Shandong Academy of Medical Sciences, Tai'an Shandong 271016, China

Received:2019-04-22 Revised:2019-06-23 Online:2019-08-21 Published:2019-10-10
Supported by:
This work is partially supported by the Shandong Provincial Natural Science Foundation (ZR2015FL005), the Tai'an Science and Technology Development Program (2017GX0045).

摘要/Abstract

摘要： 非刚性点集配准算法中，能否找到正确的对应关系对配准结果起着至关重要的作用，而通常两个点集中的对应点除了距离比较接近之外还具有相似的邻域结构，因此提出基于全局与局部相似性测度的非刚性点集配准算法。首先，使用一致性点漂移（CPD）算法作为配准框架，采用高斯混合模型对点集进行建模。然后，对全局局部混合距离进行改进，形成全局与局部相似性测度准则。最后，采用期望最大化（EM）算法迭代地求解对应关系和变换公式：在迭代初期局部相似性所占比重较大，从而能够尽快地找到正确的对应关系；随着迭代的进展全局相似性比重逐渐增大，从而确保得到较小的配准误差。实验结果表明，与薄板样条鲁棒点匹配（TPS-RPM）算法、高斯混合模型点集配准（GMMREG）算法、基于L₂E估计的鲁棒点匹配算法（RPM-L2E）、基于全局局部混合距离与薄板样条的点集配准算法（GLMDTPS）和CPD算法相比，所提算法的均方根误差（RMSE）分别下降了39.93%、42.45%、32.51%、22.36%和11.76%，说明该算法具有较好的配准效果。

关键词: 点集配准, 图像配准, 非刚性配准, 高斯混合模型, 相似性测度

Abstract: In the non-rigid point set registration algorithm, whether the correct correspondence can be found plays an important role. Generally the corresponding points in two point sets have similar neighborhood structures besides the close distance. Therefore, a non-rigid point set registration algorithm based on global and local similarity measurement was proposed. Firstly, the Coherent Point Drift (CPD) algorithm was used as the registration framework, and the Gaussian mixture model was used to model the point sets. Secondly, the global and local mixture distance was improved to form the global and local similarity measurement criterion. Finally, the correspondence and the transformation formula were solved by the Expectation Maximization (EM) algorithm. In the initial stage of the iteration, the proportion of local similarity was larger so that the correct correspondence was able to be found rapidly; with the progress of the iteration, the proportion of global similarity was increased to ensure the smaller registration error. Experimental results show that compared with the Thin Plate Spline Robust Point Matching (TPS-RPM) algorithm, the Gaussian Mixture Models point set REGistration (GMMREG) algorithm, the Robust Point Matching algorithm based on L₂E estimation (RPM-L2E), the Global and Local Mixture Distance and Thin Plate Spline based point set registration algorithm (GLMDTPS) and the CPD algorithm, the proposed algorithm has the Root Mean Squared Error (RMSE) decreased by 39.93%, 42.45%, 32.51%, 22.36% and 11.76% respectively, indicating the proposed algorithm has better registration performance.

Key words: point set registration, image registration, non-rigid registration, Gaussian mixture model, similarity measurement

中图分类号:

TP391.41

彭磊, 杨秀云, 张裕飞, 李光耀. 基于全局与局部相似性测度的非刚性点集配准[J]. 计算机应用, 2019, 39(10): 3028-3033.

PENG Lei, YANG Xiuyun, ZHANG Yufei, LI Guangyao. Non-rigid point set registration based on global and local similarity measurement[J]. Journal of Computer Applications, 2019, 39(10): 3028-3033.

参考文献

[1] MA J, ZHAO J, JIANG J, et al. Locality preserving matching[J]. International Journal of Computer Vision, 2019, 127(5):512-531.
[2] FERRANTE E, PARAGIOS N. Slice-to-volume medical image registration:a survey[J]. Medical Image Analysis, 2017, 39:101-123.
[3] GUAN S, WANG T, MENG C, et al. A review of point feature based medical image registration[J]. Chinese Journal of Mechanical Engineering, 2018, 31:No.76.
[4] TANG H, PAN A, YANG Y, et al. Retinal image registration based on robust non-rigid point matching method[J]. Journal of Medical Imaging and Health Informatics, 2018, 8(2):240-249.
[5] WU Y, MA W, ZHANG J, et al. Point-matching algorithm based on local neighborhood information for remote sensing image registration[J]. Journal of Applied Remote Sensing, 2018, 12(1):No.016002.
[6] BELONGIE S, MALIK J, PUZICHA J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(4):509-522.
[7] BESL P J, McKAY N D. Method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2):239-256.
[8] CHUI H, RANGARAJAN A. A new point matching algorithm for non-rigid registration[J]. Computer Vision and Image Understanding, 2003, 89(2/3):114-141.
[9] MYRONENKO A, SONG X. Point set registration:coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12):2262-2275.
[10] WANG G, CHEN Y. Fuzzy correspondences guided Gaussian mixture model for point set registration[J]. Knowledge-Based Systems, 2017, 136:200-209.
[11] JIAN B, VEMURI B C. Robust point set registration using Gaussian mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8):1633-1645.
[12] WANG G, ZHOU Q, CHEN Y. Robust non-rigid point set registration using spatially constrained Gaussian fields[J]. IEEE Transactions on Image Processing, 2017, 26(4):1759-1769.
[13] WANG G, CHEN Y, ZHENG X. Gaussian field consensus:a robust nonparametric matching method for outlier rejection[J]. Pattern Recognition, 2018, 74:305-316.
[14] MA J, QIU W, ZHAO J, et al. Robust L₂E estimation of transformation for non-rigid registration[J]. IEEE Transactions on Signal Processing, 2015, 63(5):1115-1129.
[15] MA J, ZHAO J, TIAN J, et al. Robust estimation of nonrigid transformation for point set registration[C]//Proceedings of the IEEE 2013 Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2013:2147-2154.
[16] YANG Y, ONG S H, FOONG K W C. A robust global and local mixture distance based non-rigid point set registration[J]. Pattern Recognition, 2015, 48(1):156-173.
[17] 王丽芳, 王雁丽, 蔺素珍, 等. 基于改进的Zernike矩的局部描述符与图割离散优化的非刚性多模态脑部图像配准[J]. 计算机应用, 2019, 39(2):582-588. (WANG L F, WANG Y L, LIN S Z, et al. Non-rigid multi-modal brain image registration based on improved Zernike moments based local descriptor and graph cuts discrete optimization[J]. Journal of Computer Applications, 2019, 39(2):582-588.)

基于全局与局部相似性测度的非刚性点集配准

Non-rigid point set registration based on global and local similarity measurement

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	孙启昌, 麦永锋, 陈晓军. 基于增强现实的手术导航系统快速标定算法[J]. 计算机应用, 2021, 41(3): 833-838.
[2]	张家岗, 李达平, 杨晓东, 邹茂扬, 吴锡, 胡金蓉. 基于深度卷积特征光流的形变医学图像配准算法[J]. 计算机应用, 2020, 40(6): 1799-1805.
[3]	丁辉, 李丽宏, 原钢. 融合GMS与VCS+GC-RANSAC的图像配准算法[J]. 计算机应用, 2020, 40(4): 1138-1143.
[4]	吴孟桦, 胡晓兵, 李航, 江代渝. 基于图像配准的零件轮廓修正方法[J]. 计算机应用, 2020, 40(4): 1144-1150.
[5]	陈聿, 田博今, 彭云竹, 廖勇. 联合手肘法和期望最大化的高斯混合聚类电力系统客户分群算法[J]. 计算机应用, 2020, 40(11): 3217-3223.
[6]	王丽芳, 王雁丽, 蔺素珍, 秦品乐, 高媛. 基于改进的Zernike矩的局部描述符与图割离散优化的非刚性多模态脑部图像配准[J]. 计算机应用, 2019, 39(2): 582-588.
[7]	梁志刚, 顾军华. 改进头脑风暴优化算法与Powell算法结合的医学图像配准[J]. 计算机应用, 2018, 38(9): 2683-2688.
[8]	林朗, 王让定, 严迪群, 李璨. 基于修正倒谱特征的回放语音检测算法[J]. 计算机应用, 2018, 38(6): 1648-1652.
[9]	叶峰, 洪峥, 赖乙宗, 赵雨亭, 谢先治. 基于匹配质量提纯的改进D-Nets算法[J]. 计算机应用, 2018, 38(4): 1121-1126.
[10]	王丽芳, 成茜, 秦品乐, 高媛. 基于多通道稀疏编码的非刚性多模态医学图像配准[J]. 计算机应用, 2018, 38(4): 1127-1133.
[11]	喻新荣, 李志华, 闫成雨, 李双俐. 云数据中心高效的虚拟机整合方法[J]. 计算机应用, 2018, 38(2): 550-556.
[12]	陶志勇, 刘晓芳, 王和章. 融合密度峰值的高斯混合模型聚类算法[J]. 计算机应用, 2018, 38(12): 3433-3437.
[13]	李舫, 张挺. 基于深度信念网络的异常点集间的匹配算法[J]. 计算机应用, 2018, 38(12): 3570-3573.
[14]	陈文兵, 管正雄, 陈允杰. 基于条件生成式对抗网络的数据增强方法[J]. 计算机应用, 2018, 38(11): 3305-3311.
[15]	陈艳, 严腾, 宋俊芳, 宋焕生. 基于高斯混合模型和AdaBoost的夜间车辆检测[J]. 计算机应用, 2018, 38(1): 260-263.