TR available on Face Recognition

[Lee Giles]

-----------------------------------------------------------------------


The following paper presents a hybrid neural network solution to
face recognition which outperforms eigenfaces and some other methods
on the database of 400 images considered. 

_______________________________________________________________________

        FACE RECOGNITION: A HYBRID NEURAL NETWORK APPROACH

Steve Lawrence (1,3), C. Lee Giles (1,2), Ah Chung Tsoi (3), Andrew D. Back (3)

  (1) NEC Research Institute, 4 Independence Way, Princeton, NJ 08540, USA
    (2) Institute for Advanced Computer Studies, University of Maryland, 
                    College Park, MD 20742, USA
     (3) Electrical and Computer Engineering, University of Queensland, 
                    St. Lucia, Australia 4072

    U. of Maryland Technical Report CS-TR-3608 and UMIACS-96-16 

                             ABSTRACT

Faces represent complex, multidimensional, meaningful visual stimuli
and developing a computational model for face recognition is
difficult.  We present a hybrid neural network solution which compares
favorably with other methods. The system combines local image
sampling, a self-organizing map neural network, and a convolutional
neural network.  The self-organizing map provides a quantization of
the image samples into a topological space where inputs that are
nearby in the original space are also nearby in the output space,
thereby providing dimensionality reduction and invariance to minor
changes in the image sample, and the convolutional neural network
provides for partial invariance to translation, rotation, scale, and
deformation.  The convolutional network extracts successively larger
features in a hierarchical set of layers.  We present results using
the Karhunen-Loeve transform in place of the self-organizing map, and
a multi-layer perceptron in place of the convolutional network. The
Karhunen-Loeve transform performs almost as well (5.3% error versus
3.8%). The multi-layer perceptron performs very poorly (40% error
versus 3.8%). The method is capable of rapid classification, requires
only fast, approximate normalization and preprocessing, and
consistently exhibits better classification performance than the
eigenfaces approach on the database considered as the number of images
per person in the training database is varied from 1 to 5.  With 5
images per person the proposed method and eigenfaces result in 3.8 and
10.5 error respectively. The recognizer provides a measure of
confidence in its output and classification error approaches zero when
rejecting as few as 10 of the examples. We use a database of 400
images of 40 individuals which contains quite a high degree of
variability in expression, pose, and facial details. We analyze
computational complexity and discuss how new classes could be added to
the trained recognizer.

Keywords: Convolutional Neural Networks, Hybrid Systems, Face Recognition, 
Self-Organizing Map

__________________________________________________________________________

The paper is available from:

http://www.neci.nj.nec.com/homepages/lawrence   - USA
http://www.neci.nj.nec.com/homepages/giles.html - USA
http://www.cs.umd.edu/TRs/TR-no-abs.html        - USA
http://www.elec.uq.edu.au/~lawrence             - Australia
ftp://ftp.nj.nec.com/pub/giles/papers/UMD-CS-TR-3608.face.recognition_hybrid.neural.nets.ps.Z

We welcome your comments.



--                                 
C. Lee Giles / Computer Sciences / NEC Research Institute / 
4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482
www.neci.nj.nec.com/homepages/giles.html
==