Hierarchical 3D mechanical parts matching based-on adjustable geometry and topology similarity measurements

Abstract

A hierarchical scheme of feature-based model similarity measurement was proposed, named CSG_D2, in which both geometry similarity and topology similarity were applied. The features of 3D mechanical part were constructed by a series of primitive features with tree structure, as a form of constructive solid geometry (CSG) tree. The D2 shape distributions of these features were extracted for geometry similarity measurement, and the pose vector and non-disappeared proportion of each leaf node were gained for topology similarity measurement. Based on these, the dissimilarity between the query and the candidate was accessed by level-by-level CSG tree comparisons. With the adjustable weights, our scheme satisfies different comparison emphasis on the geometry or topology similarity. The assessment results from CSG_D2 demonstrate more discriminative than those from D2 in the analysis of precision-recall and similarity matrix. Finally, an experimental search engine is applied for mechanical parts reuse by using CSG_D2, which is convenient for the mechanical design process.

Keywords

D2 shape distribution / CSG tree / geometry dissimilarity / topology dissimilarity / adjustable weight

References

[1] TangelderJ W H, VeltkampR C. A survey of content based 3D shape retrieval methods [C]. Proceedings of 2004 Shape Modeling International, 2004, Genova, Italy, IEEE Press: 145-156

[2] MademlisA, AxenopoulosA, DarasP, TzovarasD, StrintzisM G. 3D content-based search based on 3D KRAWTCHOUK moments [C]. Proceedings of the 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 2006, North Carolina, USA, IEEE Press: 743-749

[3] ZhangG, MaZ-m, NiuL-q, ZhangC-ming. Modified Fourier descriptor for shape feature extraction [J]. Journal of Central South University, 2012, 19(2): 488-495

[4] FunkhouserT, MinP, KazhdanM, ChenJ, HaldermanA, DobkinD, JacobsD. A search engine for 3D models [J]. ACM Transactions on Graphics, 2003, 22(1): 83-105

[5] ZahariaT, PreteuxF. Shape-based retrieval of 3D mesh models [C]. Proceedings of 2002 IEEE International Conference on Multimedia and Expo, 2002, Lausanne, Switzerland, IEEE Press: 437-440

[6] ZhuK P, WongY S, LuW F, FuhJ Y H. A diffusion wavelet approach for 3-D model matching [J]. Computer-Aided Design, 2009, 41(1): 28-36

[7] HilagaM, ShinagawaY, KohmuraT, KuniiT L. Topology matching for fully automatic similarity estimation of 3D shapes [C]. Proceedings of SIGGRAPH 2001 Conference, 2001, Los Angeles, California, USA, ACM Press: 203-212

[8] SundarH, SilverD, GagvaniN, DickinsonS. Skeleton based shape matching and retrieval [C]. Proceedings of 2003 Shape Modeling International, 2003, Seoul, Korea, IEEE Press: 130-139

[9] JainV, ZhangH. Shape-based retrieval of articulated 3D models using spectral embedding [C]. Proceedings of 2006 Geometric Modeling and Processing, 2006, Berlin, Germany, Springer Press: 299-312

[10] LucasY, RedarceT, JutardA. Spatial contours for vision and CAD model matching [J]. Image and Vision Computing, 1996, 14(2): 147-157

[11] El-MehalawiM, MillerR A. A database system of mechanical components based on geometric and topological similarity (Part I): Representation [J]. Computer-Aided Design, 2003, 35(1): 83-94

[12] El-MehalawiM, MillerR A. A database system of mechanical components based on geometric and topological similarity (Part II): Indexing, retrieval, matching, and similarity assessment [J]. Computer-Aided Design, 2003, 35(1): 95-105

[13] ÇiçekA. STEP based geometric and topological similarity assessment of mechanical parts [J]. Mathematical and Computational Applications, 2007, 12(3): 141-150

[14] OsadaR, FunkhouserT, ChazelleB, DobkinD. Shape distributions [J]. ACM Transactions on Graphics, 2002, 21(4): 807-832

[15] ReaH J, SungR, CorneyJ R, ClarkD E R, TaylorN K. Interpreting three-dimensional shape distributions [J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2005, 219(6): 553-566

[16] IpC Y, LapadatD, SiegerL, RegliW C. Using shape distributions to compare solid models [C]. Proceedings of the 7th ACM Symposium on Solid Modeling and Applications, 2002, Saarbrucken, Germany, ACM Press: 273-280

[17] MoumounL, ChahhouM, El FarM, HaqiqA, GadiT. 3D object retrieval using a global-partial analogy and the bayesian approach [C]. Proceedings of the 7th International Conference on Signal-Image Technology and Internet-Based Systems, 2011, Dijon, France, IEEE Press: 314-321

[18] CicirelloV A, RegliW C. An approach to a feature-based comparison of solid models of machined parts [J]. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 2002, 16(5): 385-399

[19] LiM, FuhJ Y H, ZhangY F, QiuZ M. General and partial shape matching approaches on feature-based CAD models to support efficient part retrieval [C]. Proceedings of 2008 International Design Engineering Technical Conferences and Computers and Information in Engineering, 2008, Brooklyn, New York, USA, ASME Press: 121-130

[20] ChuC H, HsuY C. Similarity assessment of 3D mechanical components for design reuse [J]. Robotics and Computer-Integrated Manufacturing, 2006, 22(4): 332-341

[21] ChengH C, LoC H, ChuC H, KimY S. Shape similarity measurement for 3D mechanical part using D2 shape distribution and negative feature decomposition [J]. Computers in Industry, 2011, 62(3): 269-280

[22] Baeza-YatesR, Ribeiro-NetoBModern information retrieval [M], 1999, New York, ACM Press: 73-82