Automatic correspondence using the enhanced hexagonal center-based inner search algorithm for point-based dental image registration.

In this paper a modified version of the center-based inner search algorithm, the enhanced hexagonal center-based inner search algorithm, for automatic point correspondence is proposed towards dental registration. The modified algorithm is incorporated within a general registration scheme which is based on extracting a set of candidate points on the reference image, finding their corresponding points in the other image (float image) using the proposed algorithm and applying an affine geometrical transformation towards automatic registration. The performance of the proposed algorithm is evaluated against a well-known method for automatic correspondence, in terms of the registration accuracy. Qualitative and quantitative results on registering 24 dental pairs showed that the proposed algorithm outperforms the other method for automatic correspondence.