Anatomy-Based Registration of Isometrically Transformed Surfaces Using Geodesic Area Functionals
A novel method for registration of isometrically transformed surfaces is introduced. The isometric transformation is locally decomposed into a sequence of low order transformations after manual analysis and partition of the template surface into its elementary parts. The proposed method employs geodesic moments, first, to find matching corresponding key points, and second, to generate matching regions for each of the object’s parts. The local transformation is estimated using second order moments of the corresponding regions. The method operation is demonstrated on the TOSCA dog object.
KeywordsIsometric transformation object registration
Unable to display preview. Download preview PDF.
- 1.Sethian, J.A.: Level set methods and fast marching methods, Cambridge (1999)Google Scholar
- 2.Mitchell, J.S.B., Mount, D.M., Papadimitriou, C.H.: The discrete geodesic problem. Found. Comput. SIAM Journal of Computing (1987)Google Scholar
- 3.Surazhsky, V., Surazhsky, T., Kirsanov, D., Gortler, S., Hoppe, H.: Fast Exact and Approximate Geodesics on Meshes. ACM Transactions on Graphics (2005)Google Scholar
- 5.Elad, A., Kimmel, R.: On bending invariant signatures for surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence (2003)Google Scholar
- 6.Memoli, F., Sapiro, G.: A Theoretical and Computational Framework for Isometry Invariant Recognition of Point Cloud Data. Found. Comput. Math., 313–347 (2005)Google Scholar
- 9.Tosca project, http://tosca.cs.technion.ac.il/
- 10.Shirman, L.A.: Construction of smooth curves and surfaces from polyhedral models. PhD dissertation, Berkeley University (1990)Google Scholar