3D surface matching and registration through shape images.

In this paper, we present a novel and efficient surface matching framework through shape image representation. This representation allows us to simplify a 3D surface matching problem to a 2D shape image matching problem. Furthermore, we present a shape image diffusion-based method to find the most robust features to construct the matching and registration of surfaces. This is particularly important for inter-subject surfaces from medical scans of different subjects since these surfaces exhibit the inherited physiological variances among subjects. We conducted extensive experiments on real 3D human neocortical surfaces, which demonstrate the excellent performance of our approach in terms of accuracy and robustness.