Illumination and Expression Invariant Face Recognition with One Sample Image
Speaker: Shaokang Chen, ITEE
When: 2004-11-16 11:00:00
Venue: 78-420
Host: A/Prof. Brian C. Lovell
Abstract:Robust face recognition is a challenging goal because of the gross
similarity of all faces accompanied by large differences between
face images of the same person due to variations in lighting
conditions, view point, pose and facial expression. Most face
recognition approaches either assume constant lighting condition or
standard facial expressions, thus cannot deal with both kinds of
variations simultaneously. This problem becomes more serious in
applications when only one sample images per class is available. In
this presentation, we will introduce a linear pattern classification
algorithm, Adaptive Principal Component Analysis (APCA), to
compensate for both illumination and experssion
variations. Principal Component Analysis is used to construct a
subspace for image representation. We then warp the subspace
according to the within-class covariance and between-class
covariance of samples to improve the class separability. Further,
subspace is rotated before warping in order to enhance the
representativeness of features.
Biography:Shaokang Chen received his BE degree in Automatic Control
Engineering from the South China University of Technology in 1999.
From 2000 to 2004 he has been working on his PhD within the
Intelligent Real-Time Imaging and Sensing Research Group at the
University of Queensland, Australia. His major work has been on
robust real-time face recognition.
Type: Ph.D confirmation
Contact:A/Prof. Brian C. Lovell, seminar host (lovell@itee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)