Graphics Reference
In-Depth Information
3
3D Face Surface Analysis and
Recognition Based on Facial
Curves
Hassen Drira,
1
Stefano Berretti,
2
Boulbaba Ben Amor,
1
Mohamed
Daoudi,
1
Anuj Srivastava,
3
Alberto del Bimbo,
2
and Pietro Pala
2
1
Institut Mines-Telecom/Telecom Lille 1, France
2
Dipartimento di Sistemi e Informatica, University of Firenze, Firenze, Italy
3
Department of Statistics, Florida State University, Tallahassee, USA
3.1 Introduction
There is an increasing interest in analyzing the shapes of facial surfaces with many applications
including biometrics, facial surgery, video communications, and 3D animation. This interest
is fuelled by the advent of cheaper and lighter scanners that can provide high-resolution
measurements of the geometry and texture of human facial surfaces. One general goal here is
to develop computational tools for analyzing 3D face data, in particular, comparing the shapes
of facial surfaces. Such a tool can be used to recognize human beings according to their facial
shapes, to measure changes in a facial shape due to a surgery, or to study/capture the variations
in facial shapes during conversations and expressions of emotions. Additionally, a subproblem
may be to find an optimal deformation of one surface into another under some chosen criterion.
These deformations can be useful in defining the summary statistics of a collection of faces.
For example, one can compute an
average
of faces of different people, under different facial
expressions. Efficient tools for understanding and studying variability in facial shapes are of
great importance in our biometric-oriented society.
Major issues in surface analysis:
What are the difficulties in performing standard shape
analysis on the face data? The main issue is that there is no canonical coordinate system to
represent and study the geometry of a nonlinear surface such as a face. To highlight this issue,
