CAD models clustering with machine learning

• Autorzy: Machalica Dawid , Matyjewski Marek

Identyfikatory

DOI

10.24425/ame.2019.128441

• Języki publikacji: EN

Abstrakty

EN

Similarity assessment between 3D models is an important problem in many fields including medicine, biology and industry. As there is no direct method to compare 3D geometries, different model representations (shape signatures) are developed to enable shape description, indexing and clustering. Even though some of those descriptors proved to achieve high classification precision, their application is often limited. In this work, a different approach to similarity assessment of 3D CAD models was presented. Instead of focusing on one specific shape signature, 45 easy-to-extract shape signatures were considered simultaneously. The vector of those features constituted an input for 3 machine learning algorithms: the random forest classifier, the support vector classifier and the fully connected neural network. The usefulness of the proposed approach was evaluated with a dataset consisting of over 1600 CAD models belonging to 9 separate classes. Different values of hyperparameters, as well as neural network configurations, were considered. Retrieval accuracy exceeding 99% was achieved on the test dataset.

Słowa kluczowe

EN

3D shape matching; 3D shape retrieval; 3D model recognition; 3D shape; content-based retrieval; machine learning

PL

dopasowanie kształtu 3D; pobieranie kształtu 3D; rozpoznawanie modeli 3D; kształt 3D; pobieranie oparte na treści; uczenie maszynowe

• Wydawca: Komitet Budowy Maszyn PAN
• Czasopismo: Archive of Mechanical Engineering
• Rocznik: 2019
• Tom: Vol. LXVI, nr 2
• Strony: 133--152
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Machalica Dawid

• Warsaw Institute of Aviation, Warsaw, Poland

autor

Matyjewski Marek

• Warsaw University of Technology, Institute of Aeronautics and Applied Mechanics, Warsaw, Poland

Bibliografia

• [1] T. Funkhouser, P. Min, M. Kazhdan, J. Chen, A. Halderman, D. Dobkin, and D. Jacobs. A search engine for 3D models. ACM Transactions on Graphics (TOG), 22(1):83–105, 2003. doi: 10.1145/588272.588279.
• [2] Y. Yang, H. Lin, and Y. Zhang. Content-based 3-D model retrieval: A survey. IEEE Transactions on Systems. Man and Cybernetics Part C: Applications and Reviews, 37(6), 1081–1098, 2007. doi: 10.1109/TSMCC.2007.905756.
• [3] N. Iyer, S. Jayanti, K. Lou, Y. Kalyanaraman, and K. Ramani. Three-dimensional shape searching: State-of-the-art review and future trends. Computer-Aided Design, 37(5):509–530, 2005. doi: 10.1016/j.cad.2004.07.002.
• [4] Z. Zhang, Z. Jiang, and X. Wang. Biased support vector machine active learning for 3D model retrieval. In: 2010 International Conference on Mechanic Automation and Control Engineering, pages 89–92, Wuhan, China, 26–28 June, 2010. doi: 10.1109/MACE.2010.5535431.
• [5] H. Cheng, C. Chu, E. Wang, and Y. Kim. 3D part similarity comparison based on levels of detail in negative feature decomposition using artificial neural network. Computer-Aided Design & Applications, 4(5):619–628, 2007. doi: 10.1080/16864360.2007.10738496.
• [6] B. Bustos, D.A. Keim, D. Saupe, T. Schreck, and D.V. Vranić. Feature-based similarity search in 3D object databases. ACM Computing Surveys, 37(4):345–387, 2005. doi: 10.1145/1118890.1118893.
• [7] J.R. Koza, F.H. Bennett, D. Andre, and M.A. Keane. Automated design of both the topology and sizing of analog electrical circuits using genetic programming. In: J.S. Gero, F. Sudweeks, editors, Artificial Intelligence in Design’96, pages 151–170, Springer, Dordrecht, 1996. doi: 10.1007/978-94-009-0279-4.
• [8] V.B. Sunil and S.S. Pande. Automatic recognition of machining features using artificial neural networks. The International Journal of Advanced Manufacturing Technology, 41(9–10):932–947, 2009. doi: 10.1007/s00170-008-1536-z.
• [9] A.C. Müller and S. Guido. Introduction to Machine Learning with Python: A Guide For Data Scientists. O’Reilly Media Inc., 2016.
• [10] Z. Qin, J. Jia, and J. Qin. Content based 3D model retrieval: A survey. In: 2008 International Workshop on Content-Based Multimedia Indexing, pages 249–256, London, UK, 18–20 June, 2008. doi: 10.1109/CBMI.2008.4564954.
• [11] H.J. Rea, J.R. Corney, D.E.R. Clark, J. Pritchard, M.L. Breaks, and R.A. MacLeod. Part-sourcing in a global market. Concurrent Engineering, 10(4):325–333, 2002. doi: 10.1177/a032004.
• [12] J. Corney, H. Rea, D. Clark, J. Pritchard, M. Breaks and R. MacLeod. Coarse filters for shape matching. IEEE Computer Graphics and Applications, 22(3):65–74, 2002. doi: 10.1109/MCG.2002.999789.
• [13] P. Cicconi, R. Raffaeli, and M. Germani. An approach to support model based definition by PMI annotations. Computer-Aided Design and Applications, 14(4):526–534, 2016. doi: 10.1080/16864360.2016.1257194.
• [14] G. Cybenko, A. Bhasin, and K.D. Cohen. Pattern recognition of 3D CAD objects: towards an electronic yellow pages of mechanical parts. International Journal of Smart Engineering Systems Design, 1(1):1–13, 1997.
• [15] Z. Li, X. Zhou, and W. Liu. A geometric reasoning approach to hierarchical representation for B-rep model retrieval. Computer-Aided Design, 62:190–202, 2015. doi: 10.1016/j.cad.2014.05.008.
• [16] M. Kazhdan, T. Funkhouser, and S. Rusinkiewicz. Rotation invariant spherical harmonic representation of 3D shape descriptors. In: Proceedings of Eurographics Symposium on Geometry Processing, pages 156–164, 2003.
• [17] M. El-Mehalawi and R.A. Miller. A database system of mechanical components based on geometric and topological similarity. Part I: representation. Computer-Aided Design, 35(1):83–94, 2003. doi: 10.1016/S0010-4485(01)00177-4.
• [18] M. El-Mehalawi and R.A. Miller. A database system of mechanical components based on geometric and topological similarity. Part II: indexing, retrieval, matching, and similarity assessment. Computer-Aided Design, 35(1):95–105, 2003. doi: 10.1016/S0010-4485(01)00178-6.
• [19] C.F. You and Y.L. Tsai. 3D solid model retrieval for engineering reuse based on local feature correspondence. The International Journal of Advanced Manufacturing Technology, 46(5–8):649–661,2010. doi: 10.1007/s00170-009-2113-9.
• [20] H. Kaparthi and N.C. Suresh. A neural network system for shape-based classification and coding of rotational parts. International Journal of Production Research, 29(9):1771–1784, 1991. doi: 10.1080/00207549108948048.
• [21] J. Shih, C. Lee, and J.T. Wang. A new 3D model retrieval approach based on the elevation descriptor. Pattern Recognition, 40(1):283–295, 2007. doi: 10.1016/j.patcog.2006.04.034.
• [22] Y. Gao, M. Wang, Z.J. Zha, Q. Tian, Q. Dai, and N. Zhang. Less is more: efficient 3-D object retrieval with query view selection. IEEE Transactions on Multimedia, 13(5):1007–1018, 2011. doi: 10.1109/TMM.2011.2160619.
• [23] Z. Zhu, C. Rao, S. Bai, and L.J. Latecki. Training convolutional neural network from multidomain contour images for 3D shape retrieval. Pattern Recognition Letters, 119:41–48, 2019. doi: 10.1016/j.patrec.2017.08.028.
• [24] Scikit-learn,documentation.
• [25] S. Knerr, L. Personnaz, and G. Dreyfus. Single-layer learning revisited: a stepwise procedure for building and training a neural network. In: F.F. Soulie and Jeanny Herault, editors, Neurocomputing: Algorithms, Architectures and Applications, pages 41–50, Springer-Verlag, 1990.
• [26] Y. Bengio. Learning Deep Architectures for AI. Foundations and Trends® in Machine Learning, 2(1):1–127, 2009. doi: 10.1561/2200000006.
• [27] J. Patterson and A. Gibson. Deep Learning. A Practitioner’s Approach. O’Reilly Media Inc., 2017.
• [28] M.A. Nielsen. Neural Networks and Deep Learning. Determination Press, 2015.
• [29] D.P. Kingma and J.Ba. Adam: a method for stochastic optimization. In: Proceedings of 3rd International Conference for Learning Representations, San Diego,7–9 May, 2015.