Preprint available
Marian Stewart Bartlett
marni at salk.edu
Wed Jan 17 16:12:10 EST 1996
The following preprints are available
via anonymous ftp or
http://www.cnl.salk.edu/~marni
------------------------------------------------------------------------
CLASSIFYING FACIAL ACTION
Marian Stewart Bartlett, Paul A. Viola, Terrence J. Sejnowski,
Beatrice A. Golomb, Jan Larsen, Joseph C. Hager, and Paul Ekman
To appear in "Advances in Neural Information Processing Systems 8",
D. Touretzky, M. Mozer, and M. Hasselmo (Eds.), MIT Press, Cambridge, MA,
1996.
ABSTRACT
The Facial Action Coding System, (FACS), devised by Ekman and Friesen,
provides an objective means for measuring the facial muscle contractions
involved in a facial expression. In this paper, we approach automated
facial expression analysis by detecting and classifying facial actions. We
generated a database of over 1100 image sequences of 24 subjects performing
over 150 distinct facial actions or action combinations. We compare three
different approaches to classifying the facial actions in these images:
Holistic spatial analysis based on principal components of graylevel
images; explicit measurement of local image features such as wrinkles; and
template matching with motion flow fields. On a dataset containing six
individual actions and 20 subjects, these methods had 89%, 57%, and 85%
performances respectively for generalization to novel subjects. When
combined, performance improved to 92%.
nips95.ps.Z
7 pages; 352K compressed
--------------------------------------------------------------------------
UNSUPERVISED LEARNING OF INVARIANT REPRESENTATIONS OF FACES
THROUGH TEMPORAL ASSOCIATION
Marian Stewart Bartlett and Terrence J. Sejnowski
To appear in "The Neurobiology of Computation: Proceedings of the Annual
Computational Neuroscience Meeting." J.M. Bower, ed. Kluwer Academic
Publishers, Boston.
ABSTRACT
The appearance of an object or a face changes continuously as the observer
moves through the environment or as a face changes expression or pose.
Recognizing an object or a face despite these image changes is a
challenging problem for computer vision systems, yet we perform the task
quickly and easily. This simulation investigates the ability of an
unsupervised learning mechanism to acquire representations that are
tolerant to such changes in the image. The learning mechanism finds these
representations by capturing temporal relationships between 2-D patterns.
Previous models of temporal association learning have used idealized input
representations. The input to this model consists of graylevel images of
faces. A two-layer network learned face representations that incorporated
changes of pose up to 30 degrees. A second network learned
representations that were independent of facial expression.
cns95.ta.ps.Z
6 pages; 428K compressed
=========================================================================
FTP-host: ftp.cnl.salk.edu
FTP-pathnames: /pub/marni/nips95.ps.Z and /pub/marni/cns95.ta.ps.Z
URL: ftp://ftp.cnl.salk.edu/pub/marni
WWW URL: http://www.cnl.salk.edu/~marni
If you have difficulties, email marni at salk.edu
More information about the Connectionists
mailing list