Spectral angle based kernels for the classification of hyperspectral images using support vector machines
Support vector machines (SVM) have been extensively used for classification purposes in a broad range of applications. These learning machines base their classification on the Euclidean distance of the data vectors or their dot products. These measures do not account for the spectral signature infor...
| Main Authors: | , |
|---|---|
| Format: | Book Section |
| Published: |
Institute of Electrical and Electronics Engineers
2008
|
| Subjects: |
| _version_ | 1796855134321377280 |
|---|---|
| author | Sap, M. N. N. Kohram, Mojtaba |
| author_facet | Sap, M. N. N. Kohram, Mojtaba |
| author_sort | Sap, M. N. N. |
| collection | ePrints |
| description | Support vector machines (SVM) have been extensively used for classification purposes in a broad range of applications. These learning machines base their classification on the Euclidean distance of the data vectors or their dot products. These measures do not account for the spectral signature information that can be achieved from remote sensing images. Given the high value of this information, integrating it into the SVM algorithm is a reasonable suggestion. This paper utilizes the spectral angle (SA) function as a measure for classification of a hyperspectral image. The SA function is joined together with the radial basis function (RBF) to form a spectral angle based RBF function. Experimentation results are promising and confirm that this approach can compete with existing classification methods. |
| first_indexed | 2024-03-05T18:24:10Z |
| format | Book Section |
| id | utm.eprints-12764 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:24:10Z |
| publishDate | 2008 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | utm.eprints-127642011-06-28T09:10:25Z http://eprints.utm.my/12764/ Spectral angle based kernels for the classification of hyperspectral images using support vector machines Sap, M. N. N. Kohram, Mojtaba QA75 Electronic computers. Computer science Support vector machines (SVM) have been extensively used for classification purposes in a broad range of applications. These learning machines base their classification on the Euclidean distance of the data vectors or their dot products. These measures do not account for the spectral signature information that can be achieved from remote sensing images. Given the high value of this information, integrating it into the SVM algorithm is a reasonable suggestion. This paper utilizes the spectral angle (SA) function as a measure for classification of a hyperspectral image. The SA function is joined together with the radial basis function (RBF) to form a spectral angle based RBF function. Experimentation results are promising and confirm that this approach can compete with existing classification methods. Institute of Electrical and Electronics Engineers 2008 Book Section PeerReviewed Sap, M. N. N. and Kohram, Mojtaba (2008) Spectral angle based kernels for the classification of hyperspectral images using support vector machines. In: Proceedings - 2nd Asia International Conference on Modelling and Simulation, AMS 2008. Institute of Electrical and Electronics Engineers, New York, 559 -563. ISBN 978-076953136-6 http://dx.doi.org/10.1109/AMS.2008.152 doi:10.1109/AMS.2008.152 |
| spellingShingle | QA75 Electronic computers. Computer science Sap, M. N. N. Kohram, Mojtaba Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title | Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title_full | Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title_fullStr | Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title_full_unstemmed | Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title_short | Spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| title_sort | spectral angle based kernels for the classification of hyperspectral images using support vector machines |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT sapmnn spectralanglebasedkernelsfortheclassificationofhyperspectralimagesusingsupportvectormachines AT kohrammojtaba spectralanglebasedkernelsfortheclassificationofhyperspectralimagesusingsupportvectormachines |