Skull Identification via Correlation Measure Between Skull and Face Shape

Skull identification is an important subject for research in forensic medicine. Current research can be divided into two categories: 1) craniofacial superimposition and 2) craniofacial reconstruction. Both categories rely essentially on the accurate extraction and representation of the intrinsic relationship between the skull and face in terms of the morphology, which still remain unsolved. They have high uncertainty and a low identification capability. This paper proposes a novel skull identification method that matches an unknown skull with enrolled 3D faces, in which the mapping between the skull and face is obtained using canonical correlation analysis. Unlike existing techniques, this method needs no accurate relationship between the skull and face, and measures only the correlation between them. In order to measure the correlation more reliably and improve the identification capability of the correlation analysis model, a region fusion strategy is adopted. Experimental results validate the proposed method, and show that the region-based method can significantly boost the matching accuracy. The correct identification rate reaches 94% when using a CT data set. This paper can provide a theory support for research on craniofacial superimposition and craniofacial reconstruction.

[1]  Oscar Cordón,et al.  Craniofacial Superimposition in Forensic Identification using Genetic Algorithms , 2007, Third International Symposium on Information Assurance and Security.

[2]  Oscar Cordón,et al.  Forensic identification by computer-aided craniofacial superimposition: A survey , 2011, CSUR.

[3]  Paul Suetens,et al.  Computerized craniofacial reconstruction using CT-derived implicit surface representations. , 2006, Forensic science international.

[4]  Ruey-Song Huang,et al.  3-D facial model estimation from single front-view facial image , 2002, IEEE Trans. Circuits Syst. Video Technol..

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

[6]  Zhongke Wu,et al.  A novel skull registration based on global and local deformations for craniofacial reconstruction. , 2011, Forensic science international.

[7]  Seung-Yeob Baek,et al.  3D face model reconstruction from single 2D frontal image , 2009, VRCAI '09.

[8]  Oscar Cordón,et al.  Tackling the coplanarity problem in 3D camera calibration by means of fuzzy landmarks: a performance study in forensic craniofacial superimposition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[9]  W. Heidrich,et al.  High resolution passive facial performance capture , 2010, ACM Trans. Graph..

[10]  John Shawe-Taylor,et al.  Canonical Correlation Analysis: An Overview with Application to Learning Methods , 2004, Neural Computation.

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

[12]  W A Aulsebrook,et al.  Superimposition and reconstruction in forensic facial identification: a survey. , 1995, Forensic science international.

[13]  Yun Tian,et al.  The Weighted Landmark-Based Algorithm for Skull Identification , 2011, CAIP.

[14]  Yanfeng Sun,et al.  Craniofacial reconstruction based on a hierarchical dense deformable model , 2012, EURASIP J. Adv. Signal Process..

[15]  G M Gordon,et al.  An investigation into the accuracy and reliability of skull-photo superimposition in a South African sample. , 2012, Forensic science international.

[16]  Thabo Beeler,et al.  High-quality single-shot capture of facial geometry , 2010, ACM Trans. Graph..

[17]  W. Zheng,et al.  Facial expression recognition using kernel canonical correlation analysis (KCCA) , 2006, IEEE Transactions on Neural Networks.

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

[19]  J. Clement,et al.  Craniofacial identification by computer-mediated superimposition. , 2006, The Journal of forensic odonto-stomatology.

[20]  Maxime Berar,et al.  Craniofacial reconstruction as a prediction problem using a Latent Root Regression model , 2011, Forensic science international.

[21]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Oscar Cordón,et al.  An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification , 2009, Inf. Sci..

[23]  Bovas Abraham,et al.  Dimensionality reduction approach to multivariate prediction , 2005, Comput. Stat. Data Anal..

[24]  Etty Indriati.  Historical Perspectives on Forensic Anthropology in Indonesia , 2016 .

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

[26]  Peter H. Tu,et al.  Automatic Face Recognition from Skeletal Remains , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Dennis C. Dirkmaat,et al.  A Companion to Forensic Anthropology: Dirkmaat/A Companion to Forensic Anthropology , 2012 .

[28]  Dennis C. Dirkmaat,et al.  A companion to forensic anthropology , 2015 .

[29]  D. Vandermeulen,et al.  Computerized craniofacial reconstruction: Conceptual framework and review. , 2010, Forensic science international.

[30]  Yan Zhu,et al.  Structural Digital Signature and Semi-Fragile Fingerprinting for Image Authentication in Wavelet Domain , 2007 .

[31]  Pascal Fua,et al.  Accurate face models from uncalibrated and ill-lit video sequences , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[32]  Oscar Cordón,et al.  Modeling the Skull–Face Overlay Uncertainty Using Fuzzy Sets , 2011, IEEE Transactions on Fuzzy Systems.

[33]  Thabo Beeler,et al.  High-quality single-shot capture of facial geometry , 2010, SIGGRAPH 2010.

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

[35]  Stan Z. Li,et al.  2D–3D face matching using CCA , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[36]  T. Fenton,et al.  Skull‐Photo Superimposition and Border Deaths: Identification Through Exclusion and the Failure to Exclude * , 2008, Journal of forensic sciences.