CVPR 2011 workshop on gesture
recognition
Deciphering the Face
Aleix Martinez
Ohio State
University, USA
Much progress
has been made to understand human cognition. Yet, little is know about
face perception. Facial expressions of emotions is a clear example of
this limitation. It has been established how the underlying muscles
move in response to felt emotions, but little is known on how these
constructs are interpreted by the visual system and how to build robust
computer vision systems that emulate human perception. In this talk, we
will review the recent literature on this subject and proposes a model
for the perception of facial expressions of emotion. We will show that
different emotions have diverse uses in human behavior/cognition,
suggesting that different mechanisms are in play when recognizing
distinct emotions. This is in contradiction to the continuous models in
cognitive science and the multidimensional approaches typically defined
in computer vision. We propose an alternative categorical approach to
the perception of facial expressions and show that configural and shape
features are most important for the recognition of emotional constructs
such as sadness, anger, surprise and joy. We will emphasize the
implications of these results on the construction of computer vision
systems for the automatic analysis and recognition of facial
expressions and its importance in human-computer interaction systems.
We will also discuss the implications of these findings in
computational models of other face perception tasks, e.g., identity,
gender and grammar.