NONRIGID POINT CORRESPONDENCE RECOVERY FOR PLANAR CURVES U SING FOURIER DECOMPOSITION

A novel method of point correspondence recovery between planar curves is presented in this paper where motion between the curves is nonrigid. Fourier transformation is use d to decompose planar curves into a set of ellipses, each at a different frequency level. The point correspondences between two planar curves is based on the correspondences between two ellipses in the same frequency level. At each level, a simple method is implemented to get the correspondences between the two ellipses through their shape information. This way, nonrigid point correspondence problem between two planar curves is decomposed to a set of simple subproblems – the correspondence between ellipses. We have conducted comprehensive experiments on synthetic and real data sets and found that the algorithm is quite effectiv and efficient.

[1]  Charles R. Giardina,et al.  Elliptic Fourier features of a closed contour , 1982, Comput. Graph. Image Process..

[2]  Chun-Shin Lin,et al.  New forms of shape invariants from elliptic fourier descriptors , 1987, Pattern Recognit..

[3]  Karl Rohr,et al.  Elastic registration of medical images using radial basis functions with compact support , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  Lawrence H. Staib,et al.  Shape-based 3D surface correspondence using geodesics and local geometry , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

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

[6]  Hemant D. Tagare,et al.  Shape-based nonrigid correspondence with application to heart motion analysis , 1999, IEEE Transactions on Medical Imaging.

[7]  John S. Duncan,et al.  Pointwise tracking of left-ventricular motion in 3D , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[8]  James S. Duncan,et al.  Measurement of non-rigid motion using contour shape descriptors , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Zhengyou Zhang,et al.  Iterative point matching for registration of free-form curves and surfaces , 1994, International Journal of Computer Vision.

[11]  Jitendra Malik,et al.  Matching Shapes , 2001, ICCV.

[12]  Dominik S. Meier,et al.  Parameter space warping: shape-based correspondence between morphologically different objects , 2002, IEEE Transactions on Medical Imaging.

[13]  Nicholas Ayache,et al.  Rigid, affine and locally affine registration of free-form surfaces , 1996, International Journal of Computer Vision.

[14]  C. Kambhamettu,et al.  Curvature-based approach to point correspondence recovery in conformal nonrigid motion , 1994 .

[15]  James S. Duncan,et al.  Bending and stretching models for LV wall motion analysis from curves and surfaces , 1992, Image Vis. Comput..