Three-dimensional object registration using the wavelet transform

Rapid, three-dimensional, shape-based registration is a key aspect of current challenges in applications from automated surface inspection to cancer detection and surgery. Fast, automatic registration of three-dimensional objects is an area of active research. Two main approaches exist: registration using geometric features and registration using voxel comparison. In general, registration using geometric features is faster but less accurate, while registration using voxel comparison is very accurate but requires an initial positioning as the methods tend to settle into local minima. In addition, most geometric feature methods are not designed for use on voxelized data. We present a fast, automatic, rigid registration method using wavelet features which is designed for voxelized data and which provides an excellent initial positioning for further non-rigid registration using a voxel comparison method. The efficacy of the algorithm is demonstrated through examples from solid modeling and biomedical applications.

[1]  H. Röder,et al.  Separable and nonseparable multiwavelets in multiple dimensions , 2002 .

[2]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[3]  Nicholas M. Patrikalakis,et al.  Three-dimensional object registration using wavelet features , 2009, Engineering with Computers.

[4]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[5]  Jacqueline Le Moigne,et al.  Multiresolution registration of remote sensing imagery by optimization of mutual information using a stochastic gradient , 2003, IEEE Trans. Image Process..

[6]  Cedric Nishan Canagarajah,et al.  Rotationally invariant texture features using the dual-tree complex wavelet transform , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[7]  Tamal K. Dey,et al.  Shape Segmentation and Matching with Flow Discretization , 2003, WADS.

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

[9]  Mohammed Bennamoun,et al.  Rigid Medical Image Registration And Its Association With Mutual Information , 2003, Int. J. Pattern Recognit. Artif. Intell..

[10]  Truong Q. Nguyen,et al.  Wavelets and filter banks , 1996 .

[11]  Luc Van Gool,et al.  Matching of 3-D curves using semi-differential invariants , 1995, Proceedings of IEEE International Conference on Computer Vision.

[12]  Thomas Ertl,et al.  Integrated registration and visualization of medical image data , 1998, Proceedings. Computer Graphics International (Cat. No.98EX149).

[13]  Horst Bischof,et al.  SIFT and Shape Context for Feature-Based Nonlinear Registration of Thoracic CT Images , 2006, CVAMIA.

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

[15]  Nicholas M. Patrikalakis,et al.  An algorithm for optimal free-form object matching , 2003, Comput. Aided Des..

[16]  Nicholas M. Patrikalakis,et al.  Shape Intrinsic Properties for Free-Form Object Matching , 2003, Journal of Computing and Information Science in Engineering.

[17]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[18]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[19]  Paul Suetens,et al.  Medical image registration using mutual information , 2003, Proc. IEEE.

[20]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[21]  William T. Freeman,et al.  Presented at: 2nd Annual IEEE International Conference on Image , 1995 .

[22]  Rui Xu,et al.  Wavelet-based Multiresolution Medical Image Registration Strategy Combining Mutual Information with Spatial Information , 2006 .

[23]  N. Kingsbury.  Complex Wavelets for Shift Invariant Analysis and Filtering of Signals , 2001 .

[24]  Thierry Blu,et al.  Isotropic polyharmonic B-splines: scaling functions and wavelets , 2005, IEEE Transactions on Image Processing.

[25]  Joonki Paik,et al.  Point fingerprint: A new 3-D object representation scheme , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[26]  M. Sharir,et al.  Partial surface and volume matching in three dimensions , 1997 .

[27]  D. W. Scott.  Averaged Shifted Histograms: Effective Nonparametric Density Estimators in Several Dimensions , 1985 .

[28]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[29]  Nasser Khalili,et al.  Multi-scale free-form 3D object recognition using 3D models , 2001, Image Vis. Comput..

[30]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[31]  Greg Turk,et al.  Simplification and Repair of Polygonal Models Using Volumetric Techniques , 2003, IEEE Trans. Vis. Comput. Graph..

[32]  Nick G. Kingsbury,et al.  Design of Q-shift complex wavelets for image processing using frequency domain energy minimization , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[33]  Yunmei Chen,et al.  A New & Robust Information Theoretic Measure and Its Application to Image Alignment , 2003, IPMI.