Robust CPD Algorithm for Non-Rigid Point Set Registration Based on Structure Information

Recently, the Coherent Point Drift (CPD) algorithm has become a very popular and efficient method for point set registration. However, this method does not take into consideration the neighborhood structure information of points to find the correspondence and requires a manual assignment of the outlier ratio. Therefore, CPD is not robust for large degrees of degradation. In this paper, an improved method is proposed to overcome the two limitations of CPD. A structure descriptor, such as shape context, is used to perform the auxiliary calculation of the correspondence, and the proportion of each GMM component is adjusted by the similarity. The outlier ratio is formulated in the EM framework so that it can be automatically calculated and optimized iteratively. The experimental results on both synthetic data and real data demonstrate that the proposed method described here is more robust to deformation, noise, occlusion, and outliers than CPD and other state-of-the-art algorithms.

[1]  Wei Wang,et al.  Relaxation labeling for non-rigid point matching under neighbor preserving , 2013 .

[2]  Christophe Chefd'Hotel,et al.  Registration of multiple temporally related point sets using a novel variant of the coherent point drift algorithm: application to coronary tree matching , 2013, Medical Imaging.

[3]  Xing-wei Yan晏行伟,et al.  Relaxation labeling for non-rigid point matching under neighbor preserving , 2013 .

[4]  David J. Hawkes,et al.  Deformable Vessel-Based Registration Using Landmark-Guided Coherent Point Drift , 2010, MIAR.

[5]  Kai Zhang,et al.  A Robust Point-Matching Algorithm for Remote Sensing Image Registration , 2014, IEEE Geoscience and Remote Sensing Letters.

[6]  Sim Heng Ong,et al.  A robust global and local mixture distance based non-rigid point set registration , 2015, Pattern Recognit..

[7]  Yuan Gao,et al.  A robust and outlier-adaptive method for non-rigid point registration , 2013, Pattern Analysis and Applications.

[8]  Gang Wang,et al.  A robust non-rigid point set registration method based on asymmetric gaussian representation , 2015, Comput. Vis. Image Underst..

[9]  Christine Tanner,et al.  Medical Imaging and Augmented Reality , 2006 .

[10]  Jiayi Ma,et al.  A Mixture Model for Robust Point Matching under Multi-Layer Motion , 2014, PloS one.

[11]  Jian Zheng,et al.  Robust Non-Rigid Point Set Registration Using Student's-t Mixture Model , 2014, PloS one.

[12]  Aristidis Likas,et al.  Registering sets of points using Bayesian regression , 2012, Neurocomputing.

[13]  Lin Xiang,et al.  Robust Point Set Matching under Variational Bayesian Framework , 2014, 2014 22nd International Conference on Pattern Recognition.

[14]  Gang Wang,et al.  Robust Point Matching Using Mixture of Asymmetric Gaussians for Nonrigid Transformation , 2014, ACCV.

[15]  Xiao Han.  Feature-constrained Nonlinear Registration of Lung CT Images , 2010 .

[16]  Baba C. Vemuri,et al.  Robust Point Set Registration Using Gaussian Mixture Models , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Andriy Myronenko,et al.  Point Set Registration: Coherent Point Drift , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Hongjian You,et al.  BFSIFT: A Novel Method to Find Feature Matches for SAR Image Registration , 2012, IEEE Geoscience and Remote Sensing Letters.

[19]  Paul J. Besl,et al.  Method for registration of 3-D shapes , 1992, Other Conferences.

[20]  Ling Shao,et al.  Robust point pattern matching based on spectral context , 2014, Pattern Recognit..

[21]  Anand Rangarajan,et al.  A new point matching algorithm for non-rigid registration , 2003, Comput. Vis. Image Underst..

[22]  Jong-Ha Lee,et al.  Topology Preserving Relaxation Labeling for Nonrigid Point Matching , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Daniel Cremers,et al.  Computer Vision -- ACCV 2014 , 2014, Lecture Notes in Computer Science.

[24]  Zhuowen Tu,et al.  Robust Estimation of Nonrigid Transformation for Point Set Registration , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Li Ma,et al.  Non-rigid point set registration via coherent spatial mapping , 2015, Signal Process..

[26]  Qiang Sang,et al.  Robust non-rigid point registration based on feature-dependant finite mixture model , 2013, Pattern Recognit. Lett..

[27]  Feng Jin,et al.  Image Registration Algorithm Using Mexican Hat Function-Based Operator and Grouped Feature Matching Strategy , 2014, PloS one.

[28]  Nikos Paragios,et al.  Deformable Medical Image Registration: A Survey , 2013, IEEE Transactions on Medical Imaging.

[29]  Gang Sun,et al.  Robust rigid coherent point drift algorithm based on outlier suppression and its application in image matching , 2015 .

[30]  David S. Doermann,et al.  Robust point matching for nonrigid shapes by preserving local neighborhood structures , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  DoermannDavid,et al.  Robust Point Matching for Nonrigid Shapes by Preserving Local Neighborhood Structures , 2006 .

[32]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Walter G. Kropatsch,et al.  Graph-based point drift: Graph centrality on the registration of point-sets , 2015, Pattern Recognit..

[34]  Wenbing Tao,et al.  Asymmetrical Gauss Mixture Models for Point Sets Matching , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Ping Wang,et al.  A refined coherent point drift (CPD) algorithm for point set registration , 2011, Science China Information Sciences.

[36]  Gang Wang,et al.  Robust point matching method for multimodal retinal image registration , 2015, Biomed. Signal Process. Control..

[37]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[38]  JianBing,et al.  Robust Point Set Registration Using Gaussian Mixture Models , 2011 .

[39]  Miguel Á. Carreira-Perpiñán,et al.  Non-rigid point set registration: Coherent Point Drift , 2006, NIPS.

[40]  Guoliang Fan,et al.  Non-rigid Point Set Registration with Global-Local Topology Preservation , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.