University of BRISTOL
Logo
     

 

 

Home

The Team

>Publications

 

 

 

 

Synthesising Facial Emotions

David Oziem, Lisa Gralewski, Neill Campbell, Colin Dalton, David Gibson and Barry Thomas

Theory and Practice of Computer Graphics (EG UK),
Bournemouth 8-10th June 2004

Downloads: [pdf] [pps] [zip]



 
Example: Crowd scene of multiple emotions. All generated clips from both methods are random and therefore all characters will have a different motion signature.

We present two approaches for the generation of novel video textures which portray a human expressing different emotions. Here training data is provided by video sequences of an actress expressing specific emotions such as angry, happy and sad. The main challenge of modelling these video texture sequences is the high variance in head position and facial expression. Principal Components Analysis (PCA) is used to generate so called ‘motion signatures’ which are shown to be complex and have non-Gaussian distributions.
The first method uses a combined appearance model to transform the video data into a lower dimensional Gaussian space. This can then be modelled using a standard autoregressive process. The second technique presented extracts sub-samples from the original data using short temporal windows, some of which have Gaussian distributions and can be modelled by an autoregressive process (ARP). We find that the combined appearance technique produces more aesthetically pleasing clips but does not maintain the motion characteristics as well as the temporal window approach.

Video Samples

crowd scene (23Mb)
generated angry sequence using the combined appearance model (1Mb)
original angry clip (5Mb)
generated angry sequence using the copying and ARP method (2Mb)
labelled footage (1Mb)
shape space (2Mb)
example of a video texture (15Mb)
generated sad sequence using the combined appearance model (1Mb)
original sad clip (1Mb)
texture space (24Mb)
original data (3Mb)
generated sad sequence using the copying and ARP method (2Mb)

 
Last Modified: Tuesday, August 30, 2005 10:13 AM , By David Oziem
about this page / terms and conditions
University of Bristol, Department of Computer Science, Merchant Venturers Building,
Woodland Road, Bristol BS8 1UB, UK - Tel: +44 (0)117 954 5264 - Fax: +44 (0)117 954 5208
©1995-2006 University of Bristol
Updated: 30 August 2005