Face Reconstruction from Skull Based on Partial Least Squares Regression

Craniofacial reconstruction can be applied in many fields such as forensic, archaeology etc. This paper proposes to learn the relationship between the face and the skull by Partial Least Squares Regression (PLSR), and reconstruct a person's face skin from his skull using the relationship. In order to better represent shape variations of skulls and skins, we divide the skull and skin into five correspondent local feature regions respectively, and five mappings from the skull regions to the corresponding skin regions are obtained by PLSR. For an unknown skull, we can get five skin regions by the five mappings learned, and the face can be recovered by stitching the five skin regions. Experimental results validate the proposed method.

[1]  G Quatrehomme,et al.  A fully three-dimensional method for facial reconstruction based on deformable models. , 1997, Journal of forensic sciences.

[2]  Yongli Hu,et al.  An Automatic Dense Point Registration Method for 3D Face Animation , 2009, 2009 2nd International Congress on Image and Signal Processing.

[3]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Hongbin Zha,et al.  The Craniofacial Reconstruction from the Local Structural Diversity of Skulls , 2008, Comput. Graph. Forum.

[5]  Mark W. Jones,et al.  Facial Reconstruction Using Volumetric Data , 2001, VMV.

[6]  Francesco Santini,et al.  Face Reconstruction from Skull Shapes and Physical Attributes , 2009, DAGM-Symposium.

[7]  M. Berar,et al.  3D statistical facial reconstruction , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[8]  P Vanezi,et al.  Facial reconstruction using 3-D computer graphics. , 2000, Forensic science international.

[9]  Paul Suetens,et al.  Statistically deformable face models for cranio-facial reconstruction , 2005 .

[10]  Paul Suetens,et al.  Craniofacial reconstruction using a combined statistical model of face shape and soft tissue depths: methodology and validation. , 2006, Forensic science international.

[11]  E. Martin,et al.  Non-linear projection to latent structures revisited: the quadratic PLS algorithm , 1999 .

[12]  Mingquan Zhou,et al.  Face Appearance Reconstruction Based on a Regional Statistical Craniofacial Model (RCSM) , 2010, 2010 20th International Conference on Pattern Recognition.

[13]  Caroline Wilkinson,et al.  Forensic Facial Reconstruction , 2004 .

[14]  S. Wold,et al.  Nonlinear PLS modeling , 1989 .