Abstract
In this paper, we present a method for automated estimation of a human face given a skull remain. Our proposed method is based on three statistical models. A volumetric (tetrahedral) skull model encoding the variations of different skulls, a surface head model encoding the head variations, and a dense statistic of facial soft tissue thickness (FSTT). All data are automatically derived from computed tomography (CT) head scans and optical face scans. In order to obtain a proper dense FSTT statistic, we register a skull model to each skull extracted from a CT scan and determine the FSTT value for each vertex of the skull model towards the associated extracted skin surface. The FSTT values at predefined landmarks from our statistic are well in agreement with data from the literature. To recover a face from a skull remain, we first fit our skull model to the given skull. Next, we generate spheres with radius of the respective FSTT value obtained from our statistic at each vertex of the registered skull. Finally, we fit a head model to the union of all spheres. The proposed automated method enables a probabilistic face-estimation that facilitates forensic recovery even from incomplete skull remains. The FSTT statistic allows the generation of plausible head variants, which can be adjusted intuitively using principal component analysis. We validate our face recovery process using an anonymized head CT scan. The estimation generated from the given skull visually compares well with the skin surface extracted from the CT scan itself.
Highlights
Facial reconstruction is mainly used in two principal branches of science: forensic science and archaeology
In this paper we presented an automated method based on a parametric skull model, a parametric head model, and a statistic of facial soft tissue thickness (FSTT) for reconstructing the face for a given skull
For any vertex of the parametric skull model a FSTT value can be derived from the statistic of FSTT
Summary
Facial reconstruction is mainly used in two principal branches of science: forensic science and archaeology. An approach for craniofacial reconstruction based on dense FSTT statistics, utilizing CT data, was presented by Shui et al [6] Their method depends on 78 manually selected landmarks placed on the skull, which guide the coarse registration of a template skull to each individual skull, followed by a fine registration using ICP and thin plate splines (TPS). For this purpose, in a fitting process, we register an appropriate template model to each given mesh of a specific input type. The meshes extracted from CT data were supplemented by triangle meshes from 3D surface head scans (From www.3dscanstore.com) of real subjects in order to fill up the database for our model generation processes. EðSÞ 1⁄4 EfitðSÞ þ lregEregðSprev; SÞ ð1Þ consisting of a fitting term Efit and a regularization term Ereg
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have