Learning identity with radial basis function networks

被引：35

作者：

Howell, AJ ^{[1
]}

Buxton, H ^{[1
]}

机构：

[1] Univ Sussex, Sch Cognit & Comp Sci, Brighton BN1 9QH, E Sussex, England

来源：

NEUROCOMPUTING | 1998年 / 20卷 / 1-3期

关键词：

face recognition; invariance; time-delay networks; receptive field functions; image sequences;

D O I：

10.1016/S0925-2312(98)00016-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Radial basis function (RBF) networks are compared with other neural network techniques on a face recognition task for applications involving identification of individuals using low-resolution video information. The RBF networks are shown to exhibit useful shift, scale and pose (y-axis head rotation) invariance after training when the input representation is made to mimic the receptive held functions found in early stages of the human vision system. In particular, representations based on difference of Gaussian (DoG) filtering and Gabor wavelet analysis are compared. Extensions of the techniques to the case of image sequence analysis are described and a time delay (TD) RBF network is used for recognising simple movement-based gestures. Finally, we discuss how these techniques can be used in real-life applications that require recognition of faces and gestures using low-resolution video images. (C) 1998 Elsevier Science B.V. All rights reserved.

引用

页码：15 / 34

页数：20

共 50 条

[11] Learning of radial basis function networks: Experimental results
Neruda, Roman
2002, World Scientific and Engineering Academy and Society
[12] Radial-basis-function networks: Learning and applications
Schwenker, F
Kestler, HA
Palm, G
KES'2000: FOURTH INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ENGINEERING SYSTEMS & ALLIED TECHNOLOGIES, VOLS 1 AND 2, PROCEEDINGS, 2000, : 33 - 43
[13] An incremental algorithm for learning radial basis function networks
Blanzieri, E
Giordana, A
FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 667 - 673
[14] Learning Errors by Radial Basis Function Neural Networks and Regularization Networks
Neruda, Roman
Vidnerova, Petra
INTERNATIONAL JOURNAL OF GRID AND DISTRIBUTED COMPUTING, 2009, 2 (01): : 49 - 57
[15] Learning errors by radial basis function neural networks and regularization networks
Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod vodárenskou věžíí 2, Prague 8, Czech Republic
Int. J. Grid Distrib. Comput., 2009, 1 (49-58):
[16] Nonlinear function learning using optimal radial basis function networks
Krzyzak, A
NONLINEAR ANALYSIS-THEORY METHODS & APPLICATIONS, 2001, 47 (01) : 293 - 302
[17] Radial basis function networks and complexity regularization in function learning and classification
Kégl, B
Krzyzak, A
Niemann, H
15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS: PATTERN RECOGNITION AND NEURAL NETWORKS, 2000, : 81 - 86
[18] An efficient learning algorithm for function approximation with radial basis function networks
Oyang, YJ
Hwang, SC
ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 1037 - 1042
[19] AN ACTIVE LEARNING APPROACH FOR RADIAL BASIS FUNCTION NEURAL NETWORKS
Abdullah, S. S.
Allwright, J. C.
JURNAL TEKNOLOGI, 2006, 45
[20] Dynamics of on-line learning in radial basis function networks
Freeman, JAS
Saad, D
PHYSICAL REVIEW E, 1997, 56 (01): : 907 - 918

← 1 2 3 4 5 →