Integration of spectral information into support vector machine for land cover classification
Support vector machines (SVM) have been widely used for classification purposes. These learning machines are based on classification of data through a kernel function. Classically these kernel functions are either based the Euclidean distance of two data vectors or their dot products. This is a gene...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press
2007
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/8184/1/MohdNoorMd2007_IntegrationOfSpectralInformation.PDF |
| _version_ | 1796854347021156352 |
|---|---|
| author | Md. Sap, Mohd. Noor Kohram, Mojtaba |
| author_facet | Md. Sap, Mohd. Noor Kohram, Mojtaba |
| author_sort | Md. Sap, Mohd. Noor |
| collection | ePrints |
| description | Support vector machines (SVM) have been widely used for classification purposes. These learning machines are based on classification of data through a kernel function. Classically these kernel functions are either based the Euclidean distance of two data vectors or their dot products. This is a general formulation which is suitable for most data sets. However, when dealing with remote sensing images, the addition of spectral information can add to the divisibility of the data and hence produce higher classification accuracy. In this paper, instead of the Euclidean distance we use the spectral angle function as a differentiation measure of two data vectors. The results show that using this method, high quality separation is achieved leading us to believe that integration of spectral information into the SVM method is indeed an effective approach. |
| first_indexed | 2024-03-05T18:12:53Z |
| format | Article |
| id | utm.eprints-8184 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T18:12:53Z |
| publishDate | 2007 |
| publisher | Penerbit UTM Press |
| record_format | dspace |
| spelling | utm.eprints-81842017-11-01T04:17:25Z http://eprints.utm.my/8184/ Integration of spectral information into support vector machine for land cover classification Md. Sap, Mohd. Noor Kohram, Mojtaba ZA4050 Electronic information resources Support vector machines (SVM) have been widely used for classification purposes. These learning machines are based on classification of data through a kernel function. Classically these kernel functions are either based the Euclidean distance of two data vectors or their dot products. This is a general formulation which is suitable for most data sets. However, when dealing with remote sensing images, the addition of spectral information can add to the divisibility of the data and hence produce higher classification accuracy. In this paper, instead of the Euclidean distance we use the spectral angle function as a differentiation measure of two data vectors. The results show that using this method, high quality separation is achieved leading us to believe that integration of spectral information into the SVM method is indeed an effective approach. Penerbit UTM Press 2007-12 Article PeerReviewed application/pdf en http://eprints.utm.my/8184/1/MohdNoorMd2007_IntegrationOfSpectralInformation.PDF Md. Sap, Mohd. Noor and Kohram, Mojtaba (2007) Integration of spectral information into support vector machine for land cover classification. Jurnal Teknologi Maklumat, 19 (2). pp. 47-56. ISSN 0128-3790 |
| spellingShingle | ZA4050 Electronic information resources Md. Sap, Mohd. Noor Kohram, Mojtaba Integration of spectral information into support vector machine for land cover classification |
| title | Integration of spectral information into support vector machine for land cover classification
|
| title_full | Integration of spectral information into support vector machine for land cover classification
|
| title_fullStr | Integration of spectral information into support vector machine for land cover classification
|
| title_full_unstemmed | Integration of spectral information into support vector machine for land cover classification
|
| title_short | Integration of spectral information into support vector machine for land cover classification
|
| title_sort | integration of spectral information into support vector machine for land cover classification |
| topic | ZA4050 Electronic information resources |
| url | http://eprints.utm.my/8184/1/MohdNoorMd2007_IntegrationOfSpectralInformation.PDF |
| work_keys_str_mv | AT mdsapmohdnoor integrationofspectralinformationintosupportvectormachineforlandcoverclassification AT kohrammojtaba integrationofspectralinformationintosupportvectormachineforlandcoverclassification |