I. Introduction
Point set registration (PSR) is an important and fundamental problem in the fields of robotics [1], [2], medical image analysis [3]–[5], computer vision [1], [6]–[10], and image-guided surgery (IGS) [11], [11]–[23]. Broadly speaking, PSR can be divided into rigid PSR and nonrigid PSR [9]. In terms of the rigid PSR, the parameters are a few (such as a rotation matrix, a translation vector, and possibly a scaling) and the problem is rather simple compared to the nonrigid registration one [24], [25]. Recently, the normal vectors are adopted in the rigid registration problem and have been validated to significantly improve the registration’s accuracy and robustness [20], [24], [26]–[28]. On the other hand, nonrigid PSR is still a challenging problem because the transformation between the two point sets (PSs) is nonrigid and unknown. The simplest approximations of the true nonrigid transformation, including piecewise affine and polynomial models, are often inaccurate for correct nonrigid transformation.