Automatic Multiple-view Person Identification System under unconstrained environment using one sample per person
Speaker: Ting Shan, ITEE
When: 2005-08-09 13:00:00
Venue: 78-420
Host: Prof Brian Lovell
Abstract:Automatic Face Recognition System is an active research area and has
attracted considerable attention from psychophysicists,
neuroscientists and engineers. It has several commercial and law
enforcement applications, ranging from video conferencing, crowd
surveillance, and intelligent human-computer interaction.
However, most existing person identification system performs in the
following way: The face is first detected and then tracked over
time. Only when a frame satisfies certain criteria (size, pose,
expression or illumination) is acquired, recognition is performed.
In this project, we will present our method to build a real-time
Automatic Person Identification System which can work under all
conditions, including illumination, pose and expression variation,
using a gallery of still images which only contains one frontal view
image per person.
Biography:(biography unavailable)
Type: Ph.D confirmation
Contact:Prof Brian Lovell, seminar host (lovell@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)