Volume 9, Issue 2
Spatial Entropy Based Mutual Information in Hyperspectral Band Selection for Supervised Classification

B. Wang, X. Wang & Z. Chen

Int. J. Numer. Anal. Mod., 9 (2012), pp. 181-192

Published online: 2012-09

Preview Purchase PDF 1 3384
Export citation
  • Abstract
Hyperspectral band image selection is a fundamental problem for hyperspectral remote sensing data processing. Accepting its importance, several information-based band selection methods have been proposed, which apply Shannon entropy to measure image information. However, the Shannon entropy is not accurate in measuring image information since it neglects the spatial distribution of pixels and is computed only from a histogram. This paper investigates the potential of spatial entropy in measuring image information and proposes a new mutual information (MI) band selection method based on the spatial entropy. Then selected band images are validated for supervised classification via Support Vector Machine (SVM). Using a hyperspectral AVIRIS 92AV3C dataset, experiment results show that with 20 images selection from 220 bands, the supervised classification accuracy can reach 90.6 %. Comparison with a previous Shannon entropy-based band selection method shows that the proposed method selects band images which can achieve more accurate classification results.
  • Keywords

Spatial entropy mutual information band selection support vector machine classification hyperspectral remote sensing data

  • AMS Subject Headings

62H35 68U10

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{IJNAM-9-181, author = {}, title = {Spatial Entropy Based Mutual Information in Hyperspectral Band Selection for Supervised Classification}, journal = {International Journal of Numerical Analysis and Modeling}, year = {2012}, volume = {9}, number = {2}, pages = {181--192}, abstract = {Hyperspectral band image selection is a fundamental problem for hyperspectral remote sensing data processing. Accepting its importance, several information-based band selection methods have been proposed, which apply Shannon entropy to measure image information. However, the Shannon entropy is not accurate in measuring image information since it neglects the spatial distribution of pixels and is computed only from a histogram. This paper investigates the potential of spatial entropy in measuring image information and proposes a new mutual information (MI) band selection method based on the spatial entropy. Then selected band images are validated for supervised classification via Support Vector Machine (SVM). Using a hyperspectral AVIRIS 92AV3C dataset, experiment results show that with 20 images selection from 220 bands, the supervised classification accuracy can reach 90.6 %. Comparison with a previous Shannon entropy-based band selection method shows that the proposed method selects band images which can achieve more accurate classification results.}, issn = {2617-8710}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/ijnam/619.html} }
TY - JOUR T1 - Spatial Entropy Based Mutual Information in Hyperspectral Band Selection for Supervised Classification JO - International Journal of Numerical Analysis and Modeling VL - 2 SP - 181 EP - 192 PY - 2012 DA - 2012/09 SN - 9 DO - http://doi.org/ UR - https://global-sci.org/intro/article_detail/ijnam/619.html KW - Spatial entropy KW - mutual information KW - band selection KW - support vector machine KW - classification KW - hyperspectral remote sensing data AB - Hyperspectral band image selection is a fundamental problem for hyperspectral remote sensing data processing. Accepting its importance, several information-based band selection methods have been proposed, which apply Shannon entropy to measure image information. However, the Shannon entropy is not accurate in measuring image information since it neglects the spatial distribution of pixels and is computed only from a histogram. This paper investigates the potential of spatial entropy in measuring image information and proposes a new mutual information (MI) band selection method based on the spatial entropy. Then selected band images are validated for supervised classification via Support Vector Machine (SVM). Using a hyperspectral AVIRIS 92AV3C dataset, experiment results show that with 20 images selection from 220 bands, the supervised classification accuracy can reach 90.6 %. Comparison with a previous Shannon entropy-based band selection method shows that the proposed method selects band images which can achieve more accurate classification results.
B. Wang, X. Wang & Z. Chen. (1970). Spatial Entropy Based Mutual Information in Hyperspectral Band Selection for Supervised Classification. International Journal of Numerical Analysis and Modeling. 9 (2). 181-192. doi:
Copy to clipboard
The citation has been copied to your clipboard