Abstract
The neural network method, a relatively new method in reverse engineering (RE), has the potential to reconstruct 3D models accurately and fast. A neural network (NN) is a set of interconnected neurons, in which each neuron is capable of making autonomous arithmetic and geometric calculations. Moreover, each neuron is affected by its surrounding neurons through the structure of the network.
This work proposes a new approach that utilizes growing neural gas neural network (GNG NN) techniques to reconstruct a triangular manifold mesh. This method has the advantage of reconstructing the surface of an n-genus freeform object without a priori knowledge regarding the original object, its topology or its shape. The resulting mesh can be improved by extending the MGNG into an adaptive algorithm. The proposed method was also extended for micro-structure modeling. The feasibility of the proposed method is demonstrated on several examples of freeform objects with complex topologies.
Similar content being viewed by others
References
Azernikov, S., Fischer, A.: A new approach to reverse engineering based on volume warping. J. Comput. Inf. Sci. Eng. (JCISE) 6(4), 355–363 (2006) (Special Issue on Computation metrology and RE, ASME Transactions)
Bajaj, C., Bernardini, F., Xu, G.: Automatic reconstruction of surfaces and scalar fields from 3D scans. In: Computer Graphics (SIGGRAPH ’95), pp. 109–118. ACM, New York, NY (1995)
Barhak, J., Fischer, A.: Adaptive reconstruction of freeform objects with 3D SOM neural network grids. Comput. Graph. 26(5), 745–751 (2002)
Bar-Yoseph, P.Z., Mereu, S., Chippada, S., Kalro, V.J.: Automatic monitoring of element shape quality in 2D and 3D computational mesh dynamics. Comput. Mech. 27, 378–395 (2001)
Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Computer Graphics (SIGGRAPH ’96), pp. 303–312. ACM, New York, NY (1996)
Diekmann, R., Dralle, U., Neugebauer, F., Romke, T.: PadFEM: A portable parallel {FEM}-tool. In: High-Performance Computing and Networking. Lect. Notes Comput. Sci., vol. 1067, pp. 580–585. Springer, Berlin, Heidelberg (1996)
Eck, M., Hoppe, H.: Automatic reconstruction of B-spline surfaces of arbitrary topological type. In: Computer Graphics (SIGGRAPH ’96), pp. 325–334. ACM, New York, NY (1996)
Fischer, A., Barhak, J.: Parameterization and reconstruction from 3D scattered points based on neural network and PDE techniques. IEEE Trans. Visual Comput. Graphics 7(1), 1–16 (2001)
Fischer, A., Barhak, J.: Parameterization of laser-scanned data for reconstruction of freeform surfaces based on PDE method. Visual Comput. J. 6, 353–369 (2001)
Fritzke, B.: Growing cell structures – a self-organizing network for unsupervised and supervised learning. Neural Netw. 7(9), 1441–1460 (1994)
Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge, MA (1995)
Gopi, M., Krishnan, S.: Fast and efficient projection based approach for surface reconstruction. In: 15th Brazilian Symposium on Computer Graphics and Image Processing. SIBGRAPI, pp. 179–186 (2002)
Holdstein, Y.: Reconstruction of Freeform Surface Objects Using Neural Networks Methods. M.S thesis, Faculty of mechanical engineering, Technion, Haifa (2006)
Ho-Le, K.: Finite element mesh generation methods: A review and classification. Comput. Aided Design 20(1), 27–38 (1988)
Hoppe, H., DeRose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. In: Computer Graphics (SIGGRAPH ’92), pp. 71–78. ACM, New York, NY (1992)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall PTR, Upper Saddle River, NJ (1998)
Kohonen, T.: Self-Organizing Maps. Springer, New York, Secaucus (1997)
Krause, F.-L., Fischer, A., Gross, N., Barhak, J.: Surface reconstruction of freeform objects from 3D camera data based on multiresolution volumetric method. CIRP Ann. 52(1), 125–129 (2003)
Steiner, D., Fischer, A.: Finding and defining the generators of genus-n objects for constructing topological and cut graphs. Visual Comput. 20(4), 266–278 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Holdstein, Y., Fischer, A. Three-dimensional surface reconstruction using meshing growing neural gas (MGNG). Visual Comput 24, 295–302 (2008). https://doi.org/10.1007/s00371-007-0202-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-007-0202-z