http://iet.metastore.ingenta.com
1887

Band selection for hyperspectral imagery using affinity propagation

Band selection for hyperspectral imagery using affinity propagation

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Hyperspectral imagery generally contains enormous amounts of data because of hundreds of spectral bands. Band selection is often adopted to reduce computational cost and accelerate knowledge discovery and other tasks such as subsequent classification. An exemplar-based clustering algorithm termed affinity propagation for band selection is proposed. Affinity propagation is derived from factor graph, and operates by initially considering all data points as potential cluster centres (exemplars) and then exchanging messages between data points until a good set of exemplars and clusters emerges. Affinity propagation has been applied to computer vision and bioinformatics, and shown to be much faster than other clustering methods for large data. By combining the information about the discriminative capability of each individual band and the correlation/similarity between bands, the exemplars generated by affine propagation have higher importance and less correlation/similarity. The performance of band selection is evaluated through a pixel image classification task. Experimental results demonstrate that, compared with some popular band selection methods, the bands selected by affinity propagation best characterise the hyperspectral imagery from the pixel classification standpoint.

References

    1. 1)
      • Hyperspectral imaging: techniques for spectral detection and classification
    2. 2)
      • Best-bases feature extraction algorithms for classification of hyperspectral data
    3. 3)
      • Unsupervised linear feature-extraction methods and their effects in the classification of high-dimensional data
    4. 4)
      • A new search algorithm for feature selection in hyperspectral remote sensing images
    5. 5)
      • An introduction to variable and feature selection
    6. 6)
      • Constrained band selection for hyperspectral imagery
    7. 7)
      • Dash, M., Liu, H., Yao, J.: `Dimensionality reduction of unsupervised data', Proc. Int. Conf. Tools with Artificial Intelligence, November 1997, p. 532–539
    8. 8)
      • A joint band prioritization and band-deccorelation approach to band selection for hyperspectral image classification
    9. 9)
      • Sotoca, J.M., Pla, F.: `Hyperspectral data selection from mutual information between image bands', Proc. SSPR&SPR 2006, August 2006, p. 853–861
    10. 10)
      • Elements of information theory
    11. 11)
      • Unsupervised feature selection using feature similarity
    12. 12)
      • Data clustering: a review
    13. 13)
      • Clustering-based hyperspectral band selection using information measures
    14. 14)
      • Clustering by passing messages between data points
    15. 15)
      • Dueck, D.: `Affinity propagation: clustering data by passing messages', 2009, PhD, University of Toronto
    16. 16)
      • Exact and approximation algorithms for clustering
    17. 17)
      • Factor graphs and the sum-product algorithm
    18. 18)
      • Dependence, correlation and Gaussianity in independent component analysis
    19. 19)
      • Kohavi, R.: `A study of cross-validation and bootstrap for accuracy estimation and model selection', Int. Joint Conf. on Artificial Intelligence, IJCAI, 1995, 2, p. 1137–1143
    20. 20)
      • On clustering fMRI time series
    21. 21)
      • Nearest neighbor pattern classification
    22. 22)
      • Classification of hyperspectral remote sensing images with support vector machines
    23. 23)
      • Gaussian processes for machine learning
    24. 24)
      • In defense of one-vs-all classification
    25. 25)
      • ftp://ftp.ecn.purdue.edu/biehl/MultiSpec/92AV3C (original files) and ftp://ftp.ecn.purdue.edu/pub/biehl/PC-MultiSpec/ThyFiles.zip (ground truth)
    26. 26)
      • A bayesian mrf framework for labeling terrain using hyperspectral imaging
    27. 27)
      • http://tlclab.unipv.it/dftc/home.do, accessed 2008
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2009.0034
Loading

Related content

content/journals/10.1049/iet-cvi.2009.0034
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address