by A. Jonathan Howell, A. Jonathan Howell, Hilary Buxton, Hilary Buxton
ftp://ftp.cogs.susx.ac.uk/pub/reports/csrp/csrp416.ps.Z
Add To MetaCart
Abstract:
This paper presents experiments using an adaptive learning component based on Radial Basis Function (RBF) networks to tackle the unconstrained face recognition problem using low resolution video information. Firstly, we performed preprocessing of face images to mimic the effects of receptive field functions found at various stages of the human vision system. These were then used as input representations to RBF networks that learnt to classify and generalise over different views for a standard face recognition task. Two main types of preprocessing (Difference of Gaussian filtering and Gabor wavelet analysis) are compared. Secondly we provide an alternative, `face unit ' RBF network model that is suitable for large-scale implementations by decomposition of the network, which avoids the unmanagability of neural networks above a certain size. It uses small, individual networks for each class and allows the addition of new data to the database without complete re-training of the system. Finally, we show the 2-D shift, scale and y-axis rotation invariance properties of the standard RBF network. Quantitative and qualitative differences in these schemes are described and conclusions drawn about the best approach for real applications to address the face recognition problem using low resolution images.
Citations
|
3052
|
Neural Networks for Pattern Recognition
– Bishop
- 1995
|
|
1745
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
1390
|
Introduction to the Theory of Neural Computation
– Hertz, Krogh, et al.
- 1991
|
|
548
|
Theory of edge detection
– Maar, Hildreth
|
|
524
|
Networks for approximation and learning
– Poggio, Girosi
- 1990
|
|
478
|
View-based and modular eigenspaces for face recognition
– Pentland, Moghaddam, et al.
- 1994
|
|
396
|
Fast learning in networks of locally-tuned processing units
– Darken
- 1989
|
|
265
|
Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression
– Daugman
- 1988
|
|
210
|
Regularization algorithms for learning that are equivalent to multilayer networks
– Poggio, Girosi
- 1990
|
|
171
|
Orthogonal Least-Squares Learning Algorithms for Radial Basis Function Network
– Chen, Cowan, et al.
- 1991
|
|
113
|
Learning with localized receptive fields
– Moody, Darken
- 1988
|
|
55
|
On the training of radial basis function classifiers Neural Networks 5
– Musavi, Ahmed, et al.
- 1992
|
|
53
|
Understanding face recognition
– Bruce, Young
- 1986
|
|
47
|
Some solutions to the missing feature problem in vision
– Ahmad, Tresp
- 1993
|
|
36
|
Learning to Recognize Faces from Examples
– Edelman, Reisfeld, et al.
- 1992
|
|
36
|
Natural basis functions and topographic memory for face recognition
– Rao, Ballard
- 1995
|
|
23
|
Recognising Faces. Lawrence Erlbaum Associates
– BRUCE
- 1988
|
|
22
|
Some Extensions of Radial Basis Functions and their Applications in
– Girosi
- 1992
|
|
21
|
Biologically Motivated Approach to Face Recognition
– Petkov, Kruizinga, et al.
- 1993
|
|
14
|
Invariance in radial basis function neural networks in human face classification
– Howell, Buxton
- 1995
|
|
12
|
Receptive field functions for face recognition
– Howell, Buxton
- 1995
|
|
8
|
A scaleable approach to face identification
– Howell, Buxton
- 1995
|
|
2
|
Missing dimensions of facial distinctiveness
– Bruce, Burton, et al.
- 1995
|
