Robust Rigid Shape Registration Method using a Level Set Formulation
Muayed Al-Huseiny, Sasan Mahmoodi and Mark Nixon
In: International Symposium on Visual Computing, 29 November- 1 December, Las Vegas, USA.
This paper presents a fast algorithm for robust registration
of shapes implicitly represented by signed distance functions(SDFs). The proposed algorithm aims to recover the transformation parameters (scaling, rotation, and translation) by minimizing the dissimilarity between two shapes. To achieve a robust and fast algorithm, linear orthogonal transformations are employed to minimize the dissimilarity measures. The algorithm is applied to various shape registration problems, to address issues such as topological invariance, shape complexity, and convergence speed and stability. The outcomes are compared with other state-of-the-art shape registration algorithms to show the advantages of the new technique.