Independent component representations for face
recognition.
Marian Stewart Bartlett, H. Martin Lades, and Terrence J. Sejnowski
In press: Proceedings of the SPIE Symposium on Electonic Imaging:
Science and Technology; Conference on Human Vision and Electronic Imaging
III, San Jose, CA, January, 1998.
Abstract
In a task such as face recognition, much of the important information may
be contained in the high-order relationships among the image pixels. A
number of face recognition algorithms employ principal component analysis
(PCA), which 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. ICA was performed on a
set of face images by an unsupervised learning algorithm derived from the
principle of optimal information transfer through sigmoidal neurons (Bell &
Sejnowski, 1995). The algorithm maximizes the mutual information between
the input and the output, which produces statistically independent outputs
under certain conditions. ICA was performed on the face images under two
different architectures. The first architecture provided a statistically
independent basis set for the face images that can be viewed as a set of
independent facial features. The second architecture provided a factorial
code, in which the probability of any combination of features can be
obtained from the product of their individual probabilities. Both ICA
representations were superior to representations based on principal
components analysis for recognizing faces across sessions and changes in
expression.