Spatial Mutual Information Based Hyperspectral Band Selection for Classification
The amount of information involved in hyperspectral imaging is large. Hyperspectral band selection is a popular method for reducing dimensionality. Several information based measures such as mutual information have been proposed to reduce information redundancy among spectral bands. Unfortunately, m...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2015/630918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558537126969344 |
|---|---|
| author | Anthony Amankwah |
| author_facet | Anthony Amankwah |
| author_sort | Anthony Amankwah |
| collection | DOAJ |
| description | The amount of information involved in hyperspectral imaging is large. Hyperspectral band selection is a popular method for reducing dimensionality. Several information based measures such as mutual information have been proposed to reduce information redundancy among spectral bands. Unfortunately, mutual information does not take into account the spatial dependency between adjacent pixels in images thus reducing its robustness as a similarity measure. In this paper, we propose a new band selection method based on spatial mutual information. As validation criteria, a supervised classification method using support vector machine (SVM) is used. Experimental results of the classification of hyperspectral datasets show that the proposed method can achieve more accurate results. |
| format | Article |
| id | doaj-art-76595339fd4b4765894e9800497168db |
| institution | Kabale University |
| issn | 2356-6140 1537-744X |
| language | English |
| publishDate | 2015-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-76595339fd4b4765894e9800497168db2025-02-03T01:32:10ZengWileyThe Scientific World Journal2356-61401537-744X2015-01-01201510.1155/2015/630918630918Spatial Mutual Information Based Hyperspectral Band Selection for ClassificationAnthony Amankwah0Computer Science Department, University of Ghana, Legon, GhanaThe amount of information involved in hyperspectral imaging is large. Hyperspectral band selection is a popular method for reducing dimensionality. Several information based measures such as mutual information have been proposed to reduce information redundancy among spectral bands. Unfortunately, mutual information does not take into account the spatial dependency between adjacent pixels in images thus reducing its robustness as a similarity measure. In this paper, we propose a new band selection method based on spatial mutual information. As validation criteria, a supervised classification method using support vector machine (SVM) is used. Experimental results of the classification of hyperspectral datasets show that the proposed method can achieve more accurate results.http://dx.doi.org/10.1155/2015/630918 |
| spellingShingle | Anthony Amankwah Spatial Mutual Information Based Hyperspectral Band Selection for Classification The Scientific World Journal |
| title | Spatial Mutual Information Based Hyperspectral Band Selection for Classification |
| title_full | Spatial Mutual Information Based Hyperspectral Band Selection for Classification |
| title_fullStr | Spatial Mutual Information Based Hyperspectral Band Selection for Classification |
| title_full_unstemmed | Spatial Mutual Information Based Hyperspectral Band Selection for Classification |
| title_short | Spatial Mutual Information Based Hyperspectral Band Selection for Classification |
| title_sort | spatial mutual information based hyperspectral band selection for classification |
| url | http://dx.doi.org/10.1155/2015/630918 |
| work_keys_str_mv | AT anthonyamankwah spatialmutualinformationbasedhyperspectralbandselectionforclassification |