A local technique based on vectorized surfaces for craniofacial reconstruction

Abstract : In this paper, we focus on the automation of facial reconstruction. Since they consider the whole head as the object of interest, usual reconstruction techniques are global and involve a large number of parameters to be estimated. We present a local technique which aims at reaching a good trade-off between bias and variance following the paradigm of non-parametric statistics. The estimation is localized on patches delimited by surface geodesics between anatomical points of the skull. The technique relies on a continuous representation of the individual surfaces embedded in the vectorial space of extended normal vector fields. This allows to compute deformations and averages of surfaces. It consists in estimating the soft-tissue surface over patches. Using a homogeneous database described in [31], we obtain results on the chin and nasal regions with an average error below 1 mm, outperforming the global reconstruction techniques.
Type de document :
Article dans une revue
Forensic Science International, Elsevier, 2010, 200 (1-3), pp.50-59. 〈10.1016/j.forsciint.2010.03.029〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00522667
Contributeur : Frédéric Richard <>
Soumis le : vendredi 1 octobre 2010 - 13:35:00
Dernière modification le : mardi 10 octobre 2017 - 11:22:03

Identifiants

Collections

Citation

Françoise Tilotta, Joan Alexis Glaunès, Frédéric Richard, Yves Rozenholc. A local technique based on vectorized surfaces for craniofacial reconstruction. Forensic Science International, Elsevier, 2010, 200 (1-3), pp.50-59. 〈10.1016/j.forsciint.2010.03.029〉. 〈hal-00522667〉

Partager

Métriques

Consultations de la notice

94