Learning to compute the plane of symmetry for human faces
Jia Xin Wu, Raymond W. Tse, Carrie L. Heike, Linda G. Shapiro · 2011
Facial symmetry analysis is complex in both computer vision and medicine. This paper presents a method to compute the plane of symmetry for 3D meshes of the human head and face through learning. The two steps of processing include: 1) landmark-related region detection and 2) symmetry plane computation in the learning stage, which uses the landmarks and the standard symmetry planes identified by medical experts for training. Experimental results show that our method performs better than the existing mirror method [1], and is robust to rotation and noise.