Graphics Reference
In-Depth Information
automatic recognition. We present a new bootstrapping algorithm to automatically enhance a
3D morphable face model with new face data. The algorithm is based on a morphable model-
fitting method that uses a set of predefined face components. This fitting method produces
accurate model fits to 3D face data with noise and holes. In the fitting process, the dense
point-to-point correspondences between the scan data and the face model can become less
reliable at the border of components. This is solved by introducing a blending technique
that improves on the distorted correspondences close to the borders. Afterwards, a new face
instance is acquired similar to the 3D scan data and in full correspondence with the face model.
These newly generated face instances, which go beyond the statistics of the initial morphable
face model, can then be added to the morphable face model to build a more descriptive
one. To avoid our bootstrapping algorithm from needlessly adding redundant face data, we
incorporate a redundancy estimation algorithm. Quantitative and qualitative evaluation shows
that this algorithm successfully enhances an initial morphable face model with new face data,
in a fully automatic manner.
The accurately generated face instances are manifold meshes without noise and holes and
can be effectively used for 3D face recognition. The results show that model coefficient-based
face matching outperforms contour curve and landmark-based face matching, and is more
time efficient than contour curve matching.
4.1 Introduction
There are numerous methods to perform 3D face analysis and recognition. Some of these
techniques are based on 3D geodesic surface information, such as the methods of Bronstein
et al. (2005) and Berretti et al. (2007). The geodesic distance between two points on a surface is
the length of the shortest path between two points. To compute accurate 3D geodesic distances
for face recognition purposes, a 3D face without noise and without holes is desired. Because
this is typically not the case with laser range scans, the noise has to be removed and the
holes in the 3D surface interpolated. However, the success of basic noise removal techniques,
such as Laplacian smoothing, is very much dependent on the resolution and density of the
scan data. Straightforward techniques to interpolate holes using curvature information or flat
triangles often fail in case of complex holes, as pointed out by Davis et al. (2002). The use
of a deformation model to approximate new scan data and interpolate missing data is a gentle
way to regulate flaws in scan data.
A well known statistical deformation model specifically designed for surface meshes of
3D faces, is the 3D morphable face model of Blanz and Vetter (1999). This statistical
model was built from 3D face scans with dense correspondences to which principal com-
ponent analysis (PCA) was applied. In their early work, Blanz and Vetter fit this 3D mor-
phable face model to 2D color images and cylindrical depth images from the Cyberware TM
(Del Monte AvenueMonterey, CA) scanner. In each iteration of their fitting procedure, the
model parameters are adjusted to obtain a new 3D face instance, which is projected to 2D
cylindrical image space allowing the comparison of its color values (or depth values) to
the input image. The parameters are optimized using a stochastic Newton algorithm. More
recently, Blanz et al. (2007) proposed a method to fit their 3D morphable face model to more
common textured depth images. In the fitting process, a cost function is minimized using both
color and depth values after the projection of the 3D model to 2D image space. To initialize
Search WWH ::




Custom Search