Point Pattern Matching based on point pair local nonuniform ODT and Spectral Matching

This article proposes a novel and robust point Pattern Matching Algorithm (PPM) which combines the invariant feature and Spectral Matching (SM). A new point-set based invariant feature, point pair local nonuniform ODT (Orientation and Distance Based Topology), is presented firstly. The matching measurement of point pair local nonuniform ODT descriptor's statistic test is used to define new compatibility coefficients. Then on basis of the gained compatibility measurement, we can construct a matching graph and its affinity matrix. Finally, the correct matching results are achieved using the main eigenvector of affinity matrix of assignment graph and the mapping constraint conditions. Convictive experimental results on both synthetic point-sets and real world data indicate that the proposed algorithm is robust to outliers and noise. In addition, it performs better in the presence of similarity or even perspective transformation among point sets in the meantime comparing with the other state-of-art algorithms.

[1]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[3]  Edwin R. Hancock,et al.  Spectral correspondence for point pattern matching , 2003, Pattern Recognit..

[4]  Edwin R. Hancock,et al.  Correspondence Matching with Modal Clusters , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

[6]  Michael Brady,et al.  Feature-based correspondence: an eigenvector approach , 1992, Image Vis. Comput..

[7]  C. Schmid,et al.  Learning shape prior models for object matching , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Yun Zhang,et al.  A Novel Interest-Point-Matching Algorithm for High-Resolution Satellite Images , 2009, IEEE Transactions on Geoscience and Remote Sensing.

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

[10]  H. C. Longuet-Higgins,et al.  An algorithm for associating the features of two images , 1991, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[11]  Hongsheng Li,et al.  Object matching with a locally affine-invariant constraint , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Edwin R. Hancock,et al.  Probabilistic relaxation labelling using the Fokker-Planck equation , 2008, Pattern Recognit..

[13]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[14]  Shilin Zhou,et al.  Inexact point pattern matching algorithm based on Relative Shape Context and probabilistic relaxation labelling , 2011, 2011 3rd International Conference on Computer Research and Development.

[15]  Rong Jin,et al.  Content-based image retrieval: An application to tattoo images , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[16]  Patrick J. Flynn,et al.  Three-Dimensional Facial Imaging Using a Static Light Screen (SLS) and a Dynamic Subject , 2010, IEEE Transactions on Instrumentation and Measurement.

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