Towards more accurate 3D face registration under the guidance of prior anatomical knowledge on human faces

Abstract

Three-dimensional face registration is a critical step in 3D face recognition. A fully automatic registration method for aligning frontal 3D face data is presented in this paper with high accuracy and robustness to facial expressions. In our method, the nose region, which is relatively more rigid than other facial regions in Anatomy sense, is automatically located and analyzed for computing the precise location of a symmetry plane. We then proceed on to find a stable reference point and a nose line from the global information of the nose region. In this way, the six degrees of freedom as well as a unified coordinate system can be determined for each face. Extensive experiments have been conducted on the FRGC V1.0 benchmark face dataset to evaluate the accuracy and robustness of our registration method. Firstly, we compare its results with two other registration methods. One of such methods employs manually marked points on visualized face data and the other is based on the use of a symmetry plane analysis obtained from the whole face region. Secondly, we test its application in a 3-D face verification system. Preliminary experiment results show that this approach can efficiently reduce the intra-class distance and performs better than the other two registration methods in face recognition.

Learning the Spherical Harmonic Features for 3-D Face Recognition

“…Conde et al [27] successfully applied Spin Image to facial normalization and face verification. Tang et al [28] found the reference point and nose line for face registration by computing the symmetry plane of the nose region using prior anatomical knowledge. Pears et al [2] gave an elaborate review of related work and applied radial basis function (RBF) to creating a pose-normalized depth map.…”

3D Face Recognition in the Conception of Sparse Representation

“…Therefore, it is necessary to align the 3D faces with pixel-wise correspondence by the mesh resample method [3]. By taking advantage of this resample method, all the faces are uniformly registered [4], [5]. Consequently, the whole process of 3D face normalization can be summarized as the following block diagram Figure 1.…”

Representing 3d Face From Point Cloud to Face-Aligned Spherical Depth Map

“…Colbry et al 8 used shape index to detect the anchor points in 3D face scans and achieved 99% success rate in¯nding the anchor points in frontal images and 86% success rate in scans with large variations in pose and expression. Tang et al 27 found the reference point and nose line for face registration by computing the symmetry plane of nose region under prior anatomical knowledge. Chang et al 6 used a principal component analysis (PCA) analysis to establish a local coordinate system for 3D faces, by which two kinds of curvatures were computed for face segmentation and landmark detection.…”

“…We compare our face alignment with some state-of-the-art work 8,12,27 from four aspects: the requirement of input, restrictive assumption, preprocessing and accuracy. As shown in Table 3, the comparison demonstrates the wider applicability, the better robustness and the higher accuracy of the proposed method.…”