3D Semi-Landmark based Statistical Face Reconstruction

Maxime Berar (1) , Michel Desvignes (1) , Gérard Bailly (2) , Yohan Payan (3)

1 LIS - Laboratoire des images et des signaux
2 ICP - Institut de la communication parlée
3 TIMC-IMAG-GMCAO - Gestes Medico-chirurgicaux Assistés par Ordinateur

The aim of craniofacial reconstruction is to produce a likeness of a face given the skull. Few works in computerized assisted facial reconstruction have been done in the past, due to poor machine performances and data availability, and major works are manually reconstructions. In this paper, we present an approach to build 3D statistical models of the skull and the face with soft tissues from 3D CT scans. This statistical model is used by our reconstruction method to produce 3D soft tissues from the skull of one individual. Results on real data are presented that envision the pertinence of the proposed method using a larger training set.

Mots clés: volume visualization; interactive exploration; high performance computing; imaging; segmentation; anatomic localization

Domaines: Biomécanique [physics.med-ph]; Biomécanique [physics.med-ph]; Théorie [stat.TH]; Statistiques [math.ST]

Maxime Berar, Michel Desvignes, Gérard Bailly, Yohan Payan. 3D Semi-Landmark based Statistical Face Reconstruction. Journal of Computing and Information Technology, 2006, 14 (1), pp.31-43. ⟨hal-00080375⟩