Three-dimensional surface registration: A neural network strategy

Abstract Three-dimensional surface registration is a necessary step and widely used in shape analysis, surface representation, and medical image-aided surgery. Traditional methods to fulfill such task are extremely computation complex and sometimes will obtain bad results if configured with unstructured mass data. In this paper, we propose a novel neural network strategy for efficient surface registration. Before surface registration, we use mesh PCA to normalize 3D model coordinate directions. The results and comparisons show that such neural network method is a promising approach for 3D surface registration.

[1]  Nicholas Ayache,et al.  Extension of the ICP Algorithm to Nonrigid Intensity-Based Registration of 3D Volumes , 1997, Comput. Vis. Image Underst..

[2]  Dietmar Saupe,et al.  Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics , 2001, 2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564).

[3]  P. George.  Improvements on Delaunay-based three-dimensional automatic mesh generator , 1997 .

[4]  Antonio Adán,et al.  A flexible similarity measure for 3D shapes recognition , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  P. Schröder.  Subdivision as a fundamental building block of digital geometry processing algorithms , 2002 .

[6]  Siti Mariyam Hj. Shamsuddin,et al.  3D object reconstruction and representation using neural networks , 2004, GRAPHITE '04.

[7]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[8]  Aly A. Farag,et al.  Surfacing Signatures: An Orientation Independent Free-Form Surface Representation Scheme for the Purpose of Objects Registration and Matching , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Miroslaw Bober,et al.  Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization , 2011, Computational Imaging and Vision.

[10]  Michael G. Strintzis,et al.  Rigid 3-D motion estimation using neural networks and initially estimated 2-D motion data , 2000, IEEE Trans. Circuits Syst. Video Technol..

[11]  Nasser M. Nasrabadi,et al.  Hopfield network for stereo vision correspondence , 1992, IEEE Trans. Neural Networks.

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

[13]  Denis Zorin,et al.  A simple algorithm for surface denoising , 2001, Proceedings Visualization, 2001. VIS '01..

[14]  Yuan Zhou,et al.  Quadric-based simplification in any dimension , 2005, TOGS.

[15]  Ting Chen,et al.  Artificial neural networks for 3-D motion analysis-Part II: Nonrigid motion , 1995, IEEE Trans. Neural Networks.

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