Graphics Reference
In-Depth Information
4
3D Morphable Models for Face
Surface Analysis and Recognition
Frank B. ter Haar
1
and Remco Veltkamp
2
1
TNO - Intelligent Imaging, The Hague, The Netherlands
2
Department of Information and Computing Sciences, Utrecht University,
The Netherlands
In this chapter, we present an automatic and efficient method to fit a statistical deformation
model of the human face to 3D scan data. In a global-to-local fitting scheme, the shape
parameters of this model are optimized such that the produced instance of the model accurately
fits the 3D scan data of the input face. To increase the expressiveness of the model and to
produce a tighter fit of the model, the method fits a set of predefined face components and
blends these components afterwards. Quantitative evaluation shows an improvement of the
fitting results when multiple components are used instead of one.
For a 3D face recognition system based on model coefficients, it is of utmost importance that
the statistics of many realistic faces are captured in the morphable model. In case a face cannot
be modeled, the automatically acquired model coefficients are unreliable, which hinders the
