A 3D face registration algorithm based on conformal mapping

Abstract

Summary Recently, 3D facial datasets are more easily available, and at the same time, the research of 3D face becomes more and more important. One of the most important research fields is 3D face registration, which plays an important role in face recognition, face shape analysis, and face animation. However, one of the most challenging issues in 3D face registration is to obtain a unique mapping for faces with different expression and landmark constraints. In this paper, we propose a novel conformal mapping algorithm to deal with the 3D face registration. Besides, the calculation is about harmonic energy, which makes our method applicable to low‐quality meshes. We begin with a harmonic mapping, then minimize the harmonic energy by a specific boundary condition on surfaces, and to obtain the conformal mapping, finally, we use a landmark‐constrained surface registration algorithm to register faces. Numerical experiments on various surfaces demonstrate the efficiency and robustness of our method.

Symmetric Reconstruction of Functional Liver Segments and Cross-Individual Correspondence of Hepatectomy

“…Mesh parameterization has been used in a range of applications in image analyses and computerized graphics, e.g., texture mapping, occlusion completion, mesh compression, and shape metamorphosis [42]. In medical imaging, it is useful in analyzing and comparing biological materials, such as the brain, carotid artery and hippocampus [43], and the modeling of muscles, such as those of the levator ani [44] and face [45,46]. It has been commonly accepted that conformal mapping minimizes the angular distortion of surface elements, and thus their geometrical formation [47,48].…”

Special issue on 2017 International Conference of Intelligence Computation and Evolutionary Computation (ICEC2017)

“…They begin with a harmonic mapping, and then minimize the harmonic energy by a specific boundary condition on surfaces and to obtain the conformal mapping; finally, they use a landmark‐constrained surface registration algorithm to register faces. Numerical experiments on various surfaces demonstrate the efficiency and robustness of the method …”