Weighted radial basis function kernels-based support vector machines for multispectral image classification

Shih Yu Chen; Yen Chieh Ouyang; Chein I. Chang

doi:10.1109/IGARSS.2012.6351707

Weighted radial basis function kernels-based support vector machines for multispectral image classification

Shih Yu Chen
, Yen Chieh Ouyang
, Chein I. Chang

Department of Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

Radial basis function (RBF) has been widely used in kernel-based approaches. This paper extended RBF kernels to weighted RBF (WRBF) kernels by introducing a weighting matrix A into RBF kernels. A key to success in implementing WRBF kernels is to design different appropriate weighting matrices to implement WRBF kernels. Three weighting matrices are of particular interest, covariance matrix, correlation matrix and within-class scatter matrix. Experimental results via various applications show that classifiers using WRBF kernels provide better performance than that using un-weigheted RBF kernels.

Original language	English
Pages	4339-4342
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6351707
Publication status	Published - 2012
Event	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 2012 Jul 22 → 2012 Jul 27

Other

Other	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/Territory	Germany
City	Munich
Period	12-07-22 → 12-07-27

All Science Journal Classification (ASJC) codes

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS.2012.6351707

Cite this

@conference{2996a0b020c9420aa50e1a74e8c7d20a,

title = "Weighted radial basis function kernels-based support vector machines for multispectral image classification",

abstract = "Radial basis function (RBF) has been widely used in kernel-based approaches. This paper extended RBF kernels to weighted RBF (WRBF) kernels by introducing a weighting matrix A into RBF kernels. A key to success in implementing WRBF kernels is to design different appropriate weighting matrices to implement WRBF kernels. Three weighting matrices are of particular interest, covariance matrix, correlation matrix and within-class scatter matrix. Experimental results via various applications show that classifiers using WRBF kernels provide better performance than that using un-weigheted RBF kernels.",

author = "Chen, \{Shih Yu\} and Ouyang, \{Yen Chieh\} and Chang, \{Chein I.\}",

year = "2012",

doi = "10.1109/IGARSS.2012.6351707",

language = "English",

pages = "4339--4342",

note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

TY - CONF

T1 - Weighted radial basis function kernels-based support vector machines for multispectral image classification

AU - Chen, Shih Yu

AU - Ouyang, Yen Chieh

AU - Chang, Chein I.

PY - 2012

Y1 - 2012

N2 - Radial basis function (RBF) has been widely used in kernel-based approaches. This paper extended RBF kernels to weighted RBF (WRBF) kernels by introducing a weighting matrix A into RBF kernels. A key to success in implementing WRBF kernels is to design different appropriate weighting matrices to implement WRBF kernels. Three weighting matrices are of particular interest, covariance matrix, correlation matrix and within-class scatter matrix. Experimental results via various applications show that classifiers using WRBF kernels provide better performance than that using un-weigheted RBF kernels.

AB - Radial basis function (RBF) has been widely used in kernel-based approaches. This paper extended RBF kernels to weighted RBF (WRBF) kernels by introducing a weighting matrix A into RBF kernels. A key to success in implementing WRBF kernels is to design different appropriate weighting matrices to implement WRBF kernels. Three weighting matrices are of particular interest, covariance matrix, correlation matrix and within-class scatter matrix. Experimental results via various applications show that classifiers using WRBF kernels provide better performance than that using un-weigheted RBF kernels.

UR - https://www.scopus.com/pages/publications/84873118335

UR - https://www.scopus.com/pages/publications/84873118335#tab=citedBy

U2 - 10.1109/IGARSS.2012.6351707

DO - 10.1109/IGARSS.2012.6351707

M3 - Paper

AN - SCOPUS:84873118335

SP - 4339

EP - 4342

T2 - 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012

Y2 - 22 July 2012 through 27 July 2012

ER -

Weighted radial basis function kernels-based support vector machines for multispectral image classification

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this