3D facial symmetry evaluation from high – density scanned data

"Purpose: This paper proposes a new method for the identification of the symmetry plane of the human face, starting from a 3D high – density scanned data. This plane is used to evaluate the local and mean asymmetries of the face. Method: The proposed method evaluates the symmetry plane taking into consideration the initial estimation of the symmetry plane performed by an iterative mirroring and registration-based method. Once the mirroring of the original data is carried out with respect to the symmetry plane which has been previously estimated, the source point cloud and the mirrored data are registered by the ICP algorithm that minimises a new weighted function. The final symmetry plane obtained approximates in the least-squares sense the midpoints of the lines connecting homologous points randomly chosen. Result: This method is validated by analysing some specifically-designed test cases. The obtained results show that the method is insensitive to local asymmetries, whether they be near or far from the symmetry plane, and is also repeatable and slightly conditioned by the acquisition process. Discussion & Conclusion:. This method offers promising applications not just in the medical field but also in the face recognition field. Future work should address how to improve the performance of the method in terms of timing costs and how to use the symmetry plane for face feature segmentation and for facial authentication and recognition."