|
Face
Recognition by Independent Component Analysis |
In a task such as face
recognition, much of the important information may be contained in the
high-order relationships among the image pixels. Some success has been attained
using data-driven face representations based on principal component analysis,
such as "Eigenfaces" (Turk & Pentland, 1991) and "Holons"
(Cottrell & Metcalfe, 1991). Principal component analysis (PCA) is based on
the second-order statistics of the image set, and does not address high-order
statistical dependencies such as the relationships among three or more pixels.
Independent component analysis (ICA) is a generalization of PCA
which separates the high-order moments of the input in addition to the
second-order moments. We developed image representations based on the
independent components of the face images and compared them to a PCA
representation for face recognition.
ICA
was performed on the face images under two different architectures. The first
architecture provided a set of statistically independent basis images for the
faces that can be viewed as a set of independent facial features. These ICA
basis images were spatially local, unlike the PCA basis vectors. The
representation consisted of the coefficients for the linear combination of
basis images that comprised each face image. The second architecture produced
independent coding variables (coefficients). This provided a factorial face
code, in which the probability of any combination of features can be obtained
from the product of their individual probabilities. The distributions of these coefficents were sparse and highly kurtotic.
Classification was performed using nearest neighbor, with similarity measured
as the cosine of the angle between representation vectors. Both ICA
representations were superior to the PCA representation for recognizing faces
across sessions, changes in expression, and changes in pose.
Long F, Wu T, Movellan J, Bartlett M, Littlewort, G (2012).
Learning spatiotemporal features by using independent component analysis
with application to facial expression recognition. Neurocomputing
93: 126-132 (2012). Download pdf
Bartlett, M.S., Movellan,
J.R., & Sejnowski, T.J. (2002). Face recognition by independent component
analysis. IEEE Transactions on Neural Networks 13(6) p. 1450-64.
Download pdf
Bartlett,
M. S., (2001). Face Image Analysis by Unsupervised Learning. Foreword
by Terrence J. Sejnowski. Kluwer
International Series on Engineering and Computer Science, V. 612.
Boston: Kluwer Academic Publishers. Summary
Bartlett,
M. Stewart (1998). Face image
analysis by unsupervised learning and redundancy reduction. Doctoral dissertation, University of California, San Diego.
1.9 megs compressed.
Abstract
Bartlett, M. Stewart, Lades,
H. Martin, and Sejnowski, T.J. (1998). Independent
component representations for face recognition. Proceedings of the SPIE, Vol 3299: Conference on Human Vision and Electronic Imaging
III, p. 528-539.
Abstract
Download
.ps
Bartlett, M. Stewart, and Sejnowski, T. J. (1997). Viewpoint
invariant face recognition using independent component analysis and attractor
networks. In M. Mozer, M. Jordan, T. Petsche (Eds.), Advances in Neural Information
Processing Systems 9, MIT Press, Cambridge, MA.
817-823.
Abstract
Download .ps
Facial expression analysis
using ICA: Comparison to other methods
Bartlett, M.S., Donato, G.L., Movellan, J.R.,
Hager, J.C., Ekman, P., and Sejnowski, T.J. (2000). Image representations for facial expression coding. In S. Solla, T.Leen,
& K. Mueller, Eds. Advances in Neural Information Processing
Systems 12, Cambridge, MA: MIT Press, p. 886-892.
Abstract
Download .ps
Donato, G.L., Bartlett, M.S., Hager, J.C., Ekman, P., and
Sejnowski, T.J. (1999). Classifying Facial Actions. IEEE
Transactions on Pattern Analysis and Machine Intelligence 21(10) p. 974-989.
Abstract Download
.ps.gz
Matlab Code
Matlab code for face representations using ICA. Full code now available for architectures I and II. Updated 6/2005.