Geometric Neural Computing for 2D Contour and 3D Surface Reconstruction
In this work we present an algorithm to approximate the surface of 2D or 3D objects combining concepts from geometric algebra and artificial neural networks. Our approach is based on the self-organized neural network called Growing Neural Gas (GNG), incorporating versors of the geometric algebra in its neural units; such versors are the transformations that will be determined during the training stage and then applied to a point to approximate the surface of the object. We also incorporate the information given by the generalized gradient vector flow to select automatically the input patterns, and also in the learning stage in order to improve the performance of the net. Several examples using medical images are presented, as well as images of automatic visual inspection. We compared the results obtained using snakes against the GSOM incorporating the gradient information and using versors. Such results confirm that our approach is very promising. As a second application, a kind of morphing or registration procedure is shown; namely the algorithm can be used when transforming one model at time t 1 into another at time t 2. We include also examples applying the same procedure, now extended to models based on spheres.
KeywordsInput Pattern Geometric Algebra Neural Unit Conformal Geometric Algebra Automatic Visual Inspection
Unable to display preview. Download preview PDF.
- 1.Angelopoulou, A., Psarrou, A., García Rodríguez, J., Revett, K.: Automatic landmarking of 2D medical shapes using the growing neural gas network. In: Proceedings of the International Conference on Computer Vision, ICCV 2005, October 13–21, Beijing, China, pp. 210–219 Google Scholar
- 2.Bayro-Corrochano, E.: Robot perception and action using conformal geometry. In: Handbook of Geometric Computing. Applications in Pattern Recognition, Computer Vision, Neurocomputing and Robotics, pp. 405–458. Springer, Heidelberg (2005). Chap. 13. Bayro-Corrochano, E. (ed.) Google Scholar
- 3.Buchholz, S., Hitzer, E., Tachibana, K.: Coordinate independent update formulas for versor Clifford neurons. In: Joint 4th International Conference on Soft Computing and Intelligent Systems and 9th International Symposium on Advanced Intelligent Systems (SCIS&ISIS2008), Nagoya, Japan, 17–21 Sep. 2008, pp. 814–819 Google Scholar
- 4.Fritzke, B.: A Growing Neural Gas Network Learns Topologies. Advances in Neural Information Processing Systems, vol. 7. MIT Press, Cambridge (1995) Google Scholar
- 5.Mehrotra, K., Mohan, C., Ranka, S.: Unsupervised learning. In: Elements of Artificial Neural Networks, Chap. 5, pp. 157–213 Google Scholar
- 6.Perwass, C., Hildenbrand, D.: Aspects of geometric algebra in Euclidean, projective and conformal space. Christian-Albrechts-University of Kiel, Technical Report No. 0310 (2003) Google Scholar
- 7.Pham, M.T., Tachibana, K., Hitzer, E.M.S., Buchholz, S., Yoshikawa, T., Furuhashi, T.: Feature extractions with geometric algebra for classification of objects. In: Proceedings of the International Joint Conference on Neural Networks, IJCNN 2008, Part of the IEEE World Congress on Computational Intelligence, WCCI 2008, Hong Kong, China, 1–6 June 2008 Google Scholar
- 8.Ranjan, V., Fournier, A.: Union of spheres (UoS) model for volumetric data. In: Proceedings of the Eleventh Annual Symposium on Computational Geometry, Vancouver, Canada, C2–C3, pp. 402–403 (1995) Google Scholar
- 9.Rosenhahn, B., Sommer, G.: Pose estimation in conformal geometric algebra. Christian-Albrechts-University of Kiel, Technical Report No. 0206, pp. 13–36 (2002) Google Scholar
- 10.Xu, Ch.: Deformable models with applications to human cerebral cortex reconstruction from magnetic resonance images. Ph.D. thesis, Johns Hopkins University, pp. 14–63 (1999) Google Scholar