The objective of this project is to recognize
human faces and other natural objects from images.
The same system can also be used for example-based
image retrieval from large image databases.
The method we used is based on our
Self-Organizing Hierarchical Optimal Subspace Learning and
Inference Framework (SHOSLIF). It uses the theories of optimal linear
projection for automatic optimal
feature selection and a hierarchical structure to achieve a logarithmic
retrieval complexity.
A Space-Tessellation Tree is automatically generated using the Most
Expressive Features} (MEFs) and the Most Discriminating Features
(MDFs) at each internal node of the tree.
These features are computed from the Karhunen-Loeve projection
and Fisher's multi-dimensional linear discriminant theory,
respectively.
We allow for perturbations in the size and position of objects
in the images through learning.
We demonstrate the technique on a large image database of widely varying
real-world objects taken in natural settings, and show the applicability of
the approach for variability in position, size, and 3D orientation.
At this stage of the work, we require ``well-framed'' images as input for
training and
query-by-example test probes. By well-framed images we mean that only a small
variation in the size, position, and orientation of the objects in the
images is allowed.
The system works under a supervised, unsupervised, or
hybrid learning mode. In the supervised mode, a hierarchy of class labels
is provided with each
training image. No class labels are given under the unsupervised learning
mode, and some training images are labeled in the hybrid mode.
J. Weng and D. L. Swets, `` Face Recognition,''
in A. K. Jain, R. Bolle (eds), Biometrics: Personal
Identification in Networked Society,
Kluwer Academic Press, Hingham, Massachusetts, 1999.
Click here
to down load the paper (PostScript).
Dan L. Swets and John J. Weng, ``Hierarchical Discriminant Analysis for Image Retrieval,'' IEEE Trans. Pattern
Analysis and Machine Intelligence,
vol. 21, no. 5, pp. 386 - 401, May 1999.
Click here
to down load the paper (PDF).
Dan Swets and John J. Weng, ``Using Discriminant Eigenfeatures for Image Retrieval,'' IEEE Trans. on Pattern Analysis
and Machine Intelligence, vol. 18, no. 8, pp. 831-836, Aug. 1996.
Click here
to down load the paper (PDF).
Dan Swets and John J. Weng,
``Discriminant Analysis and Eigenspace Partition Tree
for Face and Object Recognition from Views,'' in
Proc. 2nd International Conference on
Automatic Face- and Gesture-Recognition, October 14-16
Killington, Vermont, pp. 192-197, 1996.
Click here
to down load the paper (PostScript).
Dan Swets and John J. Weng, ``HOSLIF-O: SHOSLIF for Object Recognition and Image Retrieval (Phase II),''
Technical Report CPS-95-39, Department of Computer Science, MSU,
December 1995.
Click
here
to down load the paper (PostScript).
D. L. Swets and J. Weng,
``Efficient content-based image retrieval using automatic
feature selection,''
in Proc. IEEE Int'l Symposium on
Computer Vision, Coral Gables, FL, pp. 85-90, Nov. 20-22, 1995.
Dan Swets and John J. Weng, ``Efficient image retrieval using a network with
complex neurons,''
in Proc. IEEE Int'l
Conf. on Neural Networks,
Perth, Australia, Nov. 27 - Dec 1, 1995.
Dan Swets and John J. Weng, ``SHOSLIF-O: SHOSLIF for Object Recognition (Phase I),''
Technical Report CPS-94-64, Department of Computer Science, MSU,
December 1994.
To Weng's Home Page: http://web.cse.msu.edu/~weng/