Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment
Summary :
This paper presents an efficient Hybrid Learning Algorithm (HLA) for Radial Basis Function Neural Network (RBFNN). The HLA combines the gradient method and the linear least squared method for adjusting the RBF parameters and connection weights. The number of hidden neurons and their characteristics are determined using an unsupervised clustering procedure, and are used as input parameters to the learning algorithm. We demonstrate that the HLA, while providing faster convergence in training phase, is also less sensitive to training and testing patterns. The proposed HLA in conjunction with RBFNN is used as a classifier in a face recognition system to show the usefulness of the learning algorithm. The inputs to the RBFNN are the feature vectors obtained by combining shape information and Pseudo Zernike Moment (PZM). Simulation results on the Olivetti Research Laboratory (ORL) database and comparison with other algorithms indicate that the HLA yields excellent recognition rate with less hidden neurons in human face recognition.
- Publication
- IEICE TRANSACTIONS on Information Vol.E86-D No.2 pp.316-325
- Publication Date
- 2003/02/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Biocybernetics, Neurocomputing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Javad HADDADNIA, Karim FAEZ, Majid AHMADI, Payman MOALLEM, "Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment" in IEICE TRANSACTIONS on Information,
vol. E86-D, no. 2, pp. 316-325, February 2003, doi: .
Abstract: This paper presents an efficient Hybrid Learning Algorithm (HLA) for Radial Basis Function Neural Network (RBFNN). The HLA combines the gradient method and the linear least squared method for adjusting the RBF parameters and connection weights. The number of hidden neurons and their characteristics are determined using an unsupervised clustering procedure, and are used as input parameters to the learning algorithm. We demonstrate that the HLA, while providing faster convergence in training phase, is also less sensitive to training and testing patterns. The proposed HLA in conjunction with RBFNN is used as a classifier in a face recognition system to show the usefulness of the learning algorithm. The inputs to the RBFNN are the feature vectors obtained by combining shape information and Pseudo Zernike Moment (PZM). Simulation results on the Olivetti Research Laboratory (ORL) database and comparison with other algorithms indicate that the HLA yields excellent recognition rate with less hidden neurons in human face recognition.
URL: https://global.ieice.org/en_transactions/information/10.1587/e86-d_2_316/_p
Copy
@ARTICLE{e86-d_2_316,
author={Javad HADDADNIA, Karim FAEZ, Majid AHMADI, Payman MOALLEM, },
journal={IEICE TRANSACTIONS on Information},
title={Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment},
year={2003},
volume={E86-D},
number={2},
pages={316-325},
abstract={This paper presents an efficient Hybrid Learning Algorithm (HLA) for Radial Basis Function Neural Network (RBFNN). The HLA combines the gradient method and the linear least squared method for adjusting the RBF parameters and connection weights. The number of hidden neurons and their characteristics are determined using an unsupervised clustering procedure, and are used as input parameters to the learning algorithm. We demonstrate that the HLA, while providing faster convergence in training phase, is also less sensitive to training and testing patterns. The proposed HLA in conjunction with RBFNN is used as a classifier in a face recognition system to show the usefulness of the learning algorithm. The inputs to the RBFNN are the feature vectors obtained by combining shape information and Pseudo Zernike Moment (PZM). Simulation results on the Olivetti Research Laboratory (ORL) database and comparison with other algorithms indicate that the HLA yields excellent recognition rate with less hidden neurons in human face recognition.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment
T2 - IEICE TRANSACTIONS on Information
SP - 316
EP - 325
AU - Javad HADDADNIA
AU - Karim FAEZ
AU - Majid AHMADI
AU - Payman MOALLEM
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2003
AB - This paper presents an efficient Hybrid Learning Algorithm (HLA) for Radial Basis Function Neural Network (RBFNN). The HLA combines the gradient method and the linear least squared method for adjusting the RBF parameters and connection weights. The number of hidden neurons and their characteristics are determined using an unsupervised clustering procedure, and are used as input parameters to the learning algorithm. We demonstrate that the HLA, while providing faster convergence in training phase, is also less sensitive to training and testing patterns. The proposed HLA in conjunction with RBFNN is used as a classifier in a face recognition system to show the usefulness of the learning algorithm. The inputs to the RBFNN are the feature vectors obtained by combining shape information and Pseudo Zernike Moment (PZM). Simulation results on the Olivetti Research Laboratory (ORL) database and comparison with other algorithms indicate that the HLA yields excellent recognition rate with less hidden neurons in human face recognition.
ER -
English
