THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
Natural Basis Functions and Topographic Memory for Face Recognition
UR > CS > Research > Vision > Publications > Natural Basis Functions and Topographic Memory for Face Recognition
pdf 615 KB
ps.gz 1.36 MB
ps 3.64 MB
@Article{Rao:IJCAI95,
  author = 	 {Rajesh P.N. Rao and Dana H. Ballard},
  title = 	 {Natural Basis Functions and Topographic Memory for Face Recognition},
  journal = 	 {Proc International Joint Conf. on Artificial Intelligence},
  year = 	 {1995},
  pages = 	 {10 - 17},
  abstract = { Recent work regarding the statistics of nat­
ural images has revealed that the dominant
eigenvectors of arbitrary natural images closely
approximate various oriented derivative­of­
Gaussian functions; these functions have also
been shown to provide the best fit to the recep­
tive field profiles of cells in the primate striate
cortex. We propose a scheme for expression­
invariant face recognition that employs a fixed
set of these ``natural'' basis functions to gener­
ate multiscale iconic representations of human
faces. Using a fixed set of basis functions obvi­
ates the need for recomputing eigenvectors (a
step that was necessary in some previous ap­
proaches employing principal component anal­
ysis (PCA) for recognition) while at the same
time retaining the redundancy­reducing prop­
erties of PCA. A face is represented by a set of
iconic representations automatically extracted
from an input image. The description thus ob­
tained is stored in a topographically­organized
sparse distributed memory that is based on a
model of human long­term memory first pro­
posed by Kanerva. We describe experimental
results for an implementation of the method
on a pipeline image processor that is capable
of achieving near real­time recognition by ex­
ploiting the processor's frame­rate convolution
capability for indexing purposes.  }
}