Issue No. 10 - Oct. (2012 vol. 18)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2012.26
Qiqi Liao , Zhejiang University, Hangzhou
Xiaogang Jin , Zhejiang University, Hangzhou
Wenting Zeng , Zhejiang University, Hangzhou
We present an engine for enhancing the geometry of a 3D face mesh model while making the enhanced version share close similarity with the original. After obtaining the feature points of a given scanned 3D face model, we first perform a local and global symmetrization on the key facial features. We then apply an overall proportion optimization to the frontal face based on Neoclassical Canons and golden ratios. A nonlinear least-squares solution is adopted to adjust the feature points so that the face profile complies with the aesthetic criteria, which are derived from the profile cosmetology. Through the above processes, we obtain the optimized feature points, which will lead to a more attractive face. According to the original feature points and the optimized ones, we perform Laplacian deformation to adjust the remaining points of the face in order to preserve the geometric details. The analysis of user study in this paper validates the effectiveness of our 3D face geometry enhancement engine.
Face recognition, Three dimensional displays, Geometry, Solid modeling, Facial features, facial geometry., Facial attractiveness, facial symmetrization, facial proportion, facial profile
Q. Liao, X. Jin and W. Zeng, "Enhancing the Symmetry and Proportion of 3D Face Geometry," in IEEE Transactions on Visualization & Computer Graphics, vol. 18, no. , pp. 1704-1716, 2012.