A global-to-local model for the representation of human faces

Knothe, Reinhard. A global-to-local model for the representation of human faces. 2009, Doctoral Thesis, University of Basel, Faculty of Science.


Official URL: http://edoc.unibas.ch/diss/DissB_8817

Downloads: Statistics Overview


In the context of face modeling and face recognition, statistical models are
widely used for the representation and modeling of surfaces. Most of these
models are obtained by computing Principal Components Analysis (PCA) on a set
of representative examples. These models represent novel faces poorly due to
their holistic nature (i.e.\ each component has global support), and they
suffer from overfitting when used for generalization from partial information.
In this work, we present a novel analysis method that breaks the objects up
into modes based on spatial frequency. The high-frequency modes are segmented
into regions with respect to specific features of the object. After computing
PCA on these segments individually, a hierarchy of global and local components
gradually decreasing in size of their support is combined into a linear
statistical model, hence the name, Global-to-Local model (G2L). We apply our
methodology to build a novel G2L model of 3D shapes of human heads. Both the
representation and the generalization capabilities of the models are evaluated
and compared in a standardized test, and it is demonstrated that the G2L model
performs better compared to traditional holistic PCA models. Furthermore, both
models are used to reconstruct the 3D shape of faces from a single photograph.
A novel adaptive fitting method is presented that estimates the model parameters
using a multi-resolution approach. The model is first fitted to contours
extracted from the image. In a second stage, the contours are kept fixed and
the remaining flexibility of the model is fitted to the input image. This makes
the method fast (30 sec on a standard PC), efficient, and accurate.
Advisors:Vetter, Thomas
Committee Members:Burkhardt, Hans
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Ehemalige Einheiten Mathematik & Informatik > Computergraphik Bilderkennung (Vetter)
UniBasel Contributors:Knothe, Reinhard and Vetter, Thomas
Item Type:Thesis
Thesis Subtype:Doctoral Thesis
Thesis no:8817
Thesis status:Complete
Number of Pages:127
Identification Number:
edoc DOI:
Last Modified:22 Jan 2018 15:51
Deposited On:02 Dec 2009 14:21

Repository Staff Only: item control page