Recently, shape matching in three dimensions (3-D) has been gaining importance in a wide variety of fields such as computer graphics, computer vision, medicine, and biology,
with applications such as object recognition, medical diagnosis, and quantitative morphological analysis of biological operations. Automatic shape matching techniques developed in the field of computer graphics handle object surfaces, but ignore intensities
of inner voxels. In biology and medical imaging, voxel intensities obtained by computed tomography (CT), magnetic resonance imagery (MRI), and confocal microscopes are important to determine point correspondences. Nevertheless, most biomedical volume matching techniques require human interactions, and automatic methods assume matched objects to have very similar shapes so as to avoid combinatorial explosions of point. This
article is aimed at decreasing the gap between the two fields. The proposed method automatically finds dense point correspondences between two grayscale v