Manufacturing classification of CAD models using curvature and SVMs

This paper used surface curvatures and support vector machines for the identification of manufacturing processes in a database of mesh based CAD artifacts. The target is to classify prismatic machined and cast-then-machined parts into their respective classification to assist the manufacturing cost estimation. Current research on shape matching techniques has used shape functions to match the gross shapes of mesh models. However, they do not adequately discriminate artifacts manufactured by different processes. Our approach shows how different kinds of surfaces can distinguish different manufacturing processes. Statistics on surface curvatures are used to construct shape descriptors; then supervised machine learning classifier support vector machines are applied to separate the two classifications.

[1]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[2]  Qiang Ji,et al.  Machine interpretation of CAD data for manufacturing applications , 1997, CSUR.

[3]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[4]  Jami J. Shah,et al.  A Discourse on Geometric Feature Recognition From CAD Models , 2001, J. Comput. Inf. Sci. Eng..

[5]  William C. Regli,et al.  Using shape distributions to compare solid models , 2002, SMA '02.

[6]  Michael Elad,et al.  Content Based Retrieval of VRML Objects - An Iterative and Interactive Approach , 2001, Eurographics Multimedia Workshop.

[7]  Ali Shokoufandeh,et al.  Scale-Space Representation and Classification of 3D Models , 2003, J. Comput. Inf. Sci. Eng..

[8]  JungHyun Han,et al.  Manufacturing feature recognition from solid models: a status report , 2000, IEEE Trans. Robotics Autom..

[9]  Szymon Rusinkiewicz,et al.  Estimating curvatures and their derivatives on triangle meshes , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[10]  Gabriel Taubin,et al.  Estimating the tensor of curvature of a surface from a polyhedral approximation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[11]  Remco C. Veltkamp,et al.  A Survey of Content Based 3D Shape Retrieval Methods , 2004, SMI.

[12]  Thomas C. Henderson,et al.  Feature-based reverse engineering of mechanical parts , 1999, IEEE Trans. Robotics Autom..

[13]  Ali Shokoufandeh,et al.  Automated learning of model classifications , 2003, SM '03.

[14]  Joonki Paik,et al.  Normal Vector Voting: Crease Detection and Curvature Estimation on Large, Noisy Meshes , 2002, Graph. Model..

[15]  Reinhard Klein,et al.  Shape retrieval using 3D Zernike descriptors , 2004, Comput. Aided Des..

[16]  Remco C. Veltkamp,et al.  Polyhedral Model Retrieval Using Weighted Point Sets , 2003, Int. J. Image Graph..

[17]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[18]  Szymon Rusinkiewicz,et al.  Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[19]  Victoria Interrante,et al.  A novel cubic-order algorithm for approximating principal direction vectors , 2004, TOGS.

[20]  Bernard Chazelle,et al.  Shape distributions , 2002, TOGS.

[21]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[22]  Mark Meyer,et al.  Discrete Differential-Geometry Operators for Triangulated 2-Manifolds , 2002, VisMath.