Improving radial basis function networks for human face recognition using a soft computing approach

Authors:
Wanida Pensuwon;Rod Adams;Neil Davey;Wiroj Taweepworadej
Affiliations:
Department of Computer Engineering, Khon Kaen University, Khon Kaen, Thailand;Department of Computer Science, University of Hertfordshire, Hatfield, Herts, United Kingdom;Department of Computer Science, University of Hertfordshire, Hatfield, Herts, United Kingdom;Department of Computer Engineering, Khon Kaen University, Khon Kaen, Thailand
Venue:
SEAL'06 Proceedings of the 6th international conference on Simulated Evolution And Learning
Year:
2006

Citing 9
Cited 0

Approximation and radial-basis-function networks

Neural Computation
On radial basis function nets and kernel regression: statistical consistency, convergence rates, and receptive field size

Neural Networks
Pattern recognition using neural networks: theory and algorithms for engineers and scientists

Pattern recognition using neural networks: theory and algorithms for engineers and scientists
Improving the generalization properties of radial basis function neural networks

Neural Computation
Comparing support vector machines with Gaussian kernels to radialbasis function classifiers

IEEE Transactions on Signal Processing
Fuzzy logic = computing with words

IEEE Transactions on Fuzzy Systems
Face recognition: a convolutional neural-network approach

IEEE Transactions on Neural Networks
Face recognition/detection by probabilistic decision-based neural network

IEEE Transactions on Neural Networks
RBF neural network center selection based on Fisher ratio class separability measure

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new efficient method is proposed based on the radial basis function neural networks (RBFNs) architecture for human face recognition system using a soft computing approach. The performance of the present method has been evaluated using the BioID Face Database and compared with traditional radial basis function neural networks. The new approach produces successful results and shows significant recognition error reduction and learning efficiency relative to existing technique.