Craniofacial reconstruction based on heat flow geodesic grid regression (HF-GGR) model

Abstract Craniofacial reconstruction is to predict the 3D facial geometry according to the internal relationship between the skull and face, which is widely applied in the field of criminal investigation, archaeology, forensic medicine and so on. In this paper, utilizing the inherent advantage of geodesic to encode craniofacial geometry, we propose a heat flow geodesic grid regression (HF-GGR) model to facilitate craniofacial reconstruction. Our algorithm consists of three steps. In the first step, we extract the nose-tip rooted geodesic distance field and discretize it into a radial grid representation. Then in the second step, we generate geodesic grid of target skull appearance by utilizing the partial least squares regression (PLSR) method. Finally in the third step, we reconstruct the face of target skull according to the geodesic grid and face statistical model. We have conducted experiments on a data set with 213 pairs of craniofacial data. The extensive experimental results show that our algorithm can achieve accurate reconstruction results with faster speed and fewer geodesic grid points than the state-of-the-art method.

[1]  Maxime Berar,et al.  Construction and analysis of a head CT-scan database for craniofacial reconstruction. , 2009, Forensic science international.

[2]  Paul Suetens,et al.  A spatially-dense regression study of facial form and tissue depth: towards an interactive tool for craniofacial reconstruction. , 2014, Forensic science international.

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

[4]  Zhongke Wu,et al.  Face Reconstruction from Skull Based on Partial Least Squares Regression , 2011, 2011 Seventh International Conference on Computational Intelligence and Security.

[5]  Paul Suetens,et al.  Bayesian estimation of optimal craniofacial reconstructions. , 2010, Forensic science international.

[6]  Zhongke Wu,et al.  A regional method for craniofacial reconstruction based on coordinate adjustments and a new fusion strategy. , 2016, Forensic science international.

[7]  Joseph S. B. Mitchell,et al.  The Discrete Geodesic Problem , 1987, SIAM J. Comput..

[8]  Zhongke Wu,et al.  Densely calculated facial soft tissue thickness for craniofacial reconstruction in Chinese adults. , 2016, Forensic science international.

[9]  Thomas Vetter,et al.  Probabilistic Joint Face-Skull Modelling for Facial Reconstruction , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  D. Mount.  On Finding Shortest Paths on Convex Polyhedra. , 1985 .

[11]  Mario Botsch,et al.  A method for automatic forensic facial reconstruction based on dense statistics of soft tissue thickness , 2018, PloS one.

[12]  Shi-Qing Xin,et al.  Applying the improved Chen and Han's algorithm to different versions of shortest path problems on a polyhedral surface , 2010, Comput. Aided Des..

[13]  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.

[14]  Ligang Liu,et al.  Fast Wavefront Propagation (FWP) for Computing Exact Geodesic Distances on Meshes , 2015, IEEE Transactions on Visualization and Computer Graphics.

[15]  Na Lei,et al.  Automatic and Robust Skull Registration Based on Discrete Uniformization , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[17]  S. Wold,et al.  The multivariate calibration problem in chemistry solved by the PLS method , 1983 .

[18]  Keenan Crane,et al.  Geodesics in heat: A new approach to computing distance based on heat flow , 2012, TOGS.

[19]  Micha Sharir,et al.  On Shortest Paths in Polyhedral Spaces , 1986, SIAM J. Comput..

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

[21]  Yijie Han,et al.  Shortest paths on a polyhedron , 1990, SCG '90.

[22]  Yanfeng Sun,et al.  A hierarchical dense deformable model for 3D face reconstruction from skull , 2012, Multimedia Tools and Applications.

[23]  Ozgur Bulut,et al.  Facial soft tissue thickness database for craniofacial reconstruction in the Turkish adult population. , 2014, Forensic science international.

[24]  Xin Li,et al.  Automatic craniofacial registration based on radial curves , 2019, Comput. Graph..

[25]  Antonio De Donno,et al.  Facial approximation: Soft tissue thickness values for Caucasian males using cone beam computer tomography. , 2019, Legal medicine.

[26]  Shuangmin Chen,et al.  Computing Smooth Quasi-geodesic Distance Field (QGDF) with Quadratic Programming , 2020, Comput. Aided Des..

[27]  Meng Yang,et al.  A local modeling approach of craniofacial shape correlation based on PLSR , 2017, 2017 2nd International Conference on Image, Vision and Computing (ICIVC).

[28]  Junli Zhao,et al.  Craniofacial Reconstruction Based on Geodesic Regression Model , 2021, Journal of Computer-Aided Design & Computer Graphics.

[29]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[30]  Fuqing Duan,et al.  Craniofacial Reconstruction Using Gaussian Process Latent Variable Models , 2015, CAIP.

[31]  Bailin Deng,et al.  Parallel and Scalable Heat Methods for Geodesic Distance Computation , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Ying He,et al.  Saddle vertex graph (SVG) , 2013, ACM Trans. Graph..

[33]  Mingquan Zhou,et al.  A computerized craniofacial reconstruction method for an unidentified skull based on statistical shape models , 2020, Multimedia Tools and Applications.

[34]  Liang Chang,et al.  Craniofacial reconstruction based on least square support vector regression , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[35]  Yun Tian,et al.  3D face reconstruction from skull by regression modeling in shape parameter spaces , 2015, Neurocomputing.

[36]  Yongli Hu,et al.  Craniofacial reconstruction based on multi-linear subspace analysis , 2012, Multimedia Tools and Applications.

[37]  Jie Sun,et al.  A Survey on 3D Face Recognition based on Geodesics , 2019, J. Inf. Hiding Multim. Signal Process..

[38]  J A Sethian,et al.  A fast marching level set method for monotonically advancing fronts. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[39]  Michel Desvignes,et al.  3D Semi-Landmarks Based Statistical Face Reconstruction , 2006, J. Comput. Inf. Technol..