Human faces provide enormous information and a friendly interface
in intelligent human computer interaction.
This has motivated a very active research area on, among others, face
recognition, face tracking, pose estimation, expression
recognition and gesture recognition.
However, most existing methods on these topics assume human faces in
an image or a image sequence have been identified and localized.
To build a fully automated system that analyzes information of
human faces, it is essential to develop robust and efficient
algorithms to detect human faces.
Given a single or a sequence of images,
the goal of face detection is to identify and locate human faces
regardless of their positions, scales, orientations and lighting
conditions.
Such problem is challenging because human faces
are highly non-rigid objects
with a high degree of variability in size, shape, color and texture.
In this project, I develop a method that uses a mixture of subspaces
to detect faces with facial expression and facial features, faces in
different poses, and faces under different lighting conditions.
The main idea behind this project is to use Kohonen's Self Organizing Map
and Fisher Linear Discriminant function to better model the
distribution of the complex face and nonface patterns.
Preliminary results show that such approach is able to detect
faces regardless of their poses, facial expressions or lighting
conditions.