CFP last date
22 April 2024
Reseach Article

PSO based Selection of Spectral Features for Remotely Sensed Image Classification

Published on December 2013 by Agrawal R. K., N. G. Bawane
National Conference on Innovative Paradigms in Engineering & Technology 2013
Foundation of Computer Science USA
NCIPET2013 - Number 8
December 2013
Authors: Agrawal R. K., N. G. Bawane
ef200c70-3c16-4ba4-a4f5-bc87e9e38d0a

Agrawal R. K., N. G. Bawane . PSO based Selection of Spectral Features for Remotely Sensed Image Classification. National Conference on Innovative Paradigms in Engineering & Technology 2013. NCIPET2013, 8 (December 2013), 22-26.

@article{
author = { Agrawal R. K., N. G. Bawane },
title = { PSO based Selection of Spectral Features for Remotely Sensed Image Classification },
journal = { National Conference on Innovative Paradigms in Engineering & Technology 2013 },
issue_date = { December 2013 },
volume = { NCIPET2013 },
number = { 8 },
month = { December },
year = { 2013 },
issn = 0975-8887,
pages = { 22-26 },
numpages = 5,
url = { /proceedings/ncipet2013/number8/14749-1448/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 National Conference on Innovative Paradigms in Engineering & Technology 2013
%A Agrawal R. K.
%A N. G. Bawane
%T PSO based Selection of Spectral Features for Remotely Sensed Image Classification
%J National Conference on Innovative Paradigms in Engineering & Technology 2013
%@ 0975-8887
%V NCIPET2013
%N 8
%P 22-26
%D 2013
%I International Journal of Computer Applications
Abstract

Spectral feature used in remotely sensed image classification are recorded in narrow, adjacent frequency bands in the visible to infrared spectrum. Due to narrow spacing, these features are highly correlated and provide some redundant information which may reduce classification accuracy. Hence discriminative feature selection technique is required for better classification. In this paper, we present particle swarm optimization based technique to select best spectral features for remotely sensed image classification. The pixels intensity in selected best spectral band is used to construct the feature vector for that pixel. Each pixel in multispectral imagery is classified into various land cover types like water, vegetation, road and urban area etc. We employed ANN for supervised classification of the image pixel. The accuracy obtained with proposed algorithm is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of the proposed system is evaluated quantitatively using Xie-Beni and ? indexes. The result shows the superiority of the proposed method to the conventional one.

References
  1. P. M. Mather. 1999. Computer Processing of Remotely Sensed Images. John Wiley, UK.
  2. D. A. Landgrebe. 2003. Signal Theory Methods in Multispectral Remote Sensing, Wiley, New York.
  3. P. M. Atkinson, Tattnall. 997. Neural network in remote sensing. Int. J. Remote Sensing 18 (4) 699-709.
  4. J. A. Benediktsson, Swain P. H. , Erosy O. K. . 1990. Neural network approaches versus statistical methods in classification of multisource remote sensing data. IEEE Transactions on Geosciences and Remote Sensing 28 540-552.
  5. G. M. Foody, M. K. Arora. 1997. An evaluation of some factors affecting the accuracy of classification by an artificial neural network. Int. J. Remote Sensing 18 (4) 799–810.
  6. H. M. Chee, O. K. Ersoy. 2005. A statistical self-organizing learning system for remote sensing classification. IEEE Transactions on Geosciences and Remote Sensing 432 (8) 1890–1900.
  7. M. Acharyya, R. K. De, M. K. Kundu. 2003. Segmentation of remotely sensed images using wavelet features and their evaluation in soft computing framework. IEEE Transactions on Geosciences and Remote Sensing 41 (12) 2900-2905.
  8. B. Mannan Joy, A. K. Ray. 1998. Fuzzy ARTMAP supervised classification of multispectral remotely sensed images. Int. J. Remote Sensing 19 (4) 767-774.
  9. Saroj K. Meher, B. Uma Shankar, and Ashish Ghosh. 2007. Wavelet Feature Based Classifier for emotely sensed Images. IEEE Transactions on Geosciences and Remote Sensing 45 (06) 1881-1886.
  10. L. O. Jimenez, D. A. Landgrebe. 1998. Supervised classification in high dimensional space: Geometrical, statistical, and asymptotical properties of multivariate data. IEEE Trans. Syst. , Man, Cybern. A, 28, 39–54.
  11. A. Jain, D. Zongker. 1997. Feature selection: Evaluation, application, and small sample performance. IEEE Trans. Pattern Anal. Mach. Intell. , vol. 19, no. 2, pp. 153–158.
  12. J. Kennedy, R. C. Eberhart. 2001. Swarm Intelligence. Morgan Kaufmann, San Mateo.
  13. R. C. Gonzalez, R. E. Woods, S. L. Eddins. 2002. Digital Image Processing using MATLAB, Pearson, Singapore.
  14. S. Haykin. 1997. Neural Networks: A Comprehensive Foundation, Prentice Hall, England.
  15. S. K. Pal, A. Ghosh, and B. U. Shankar. 2000. Segmentation of remotely sensed images with fuzzy thresholding and quantitative evaluation. Int. J. Remote Sens. , vol. 21, no. 11, pp. 2269–2300.
  16. X. L. Xie, G. Beni. 1991. A validity measure for fuzzy clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 13 (8), 841–847.
Index Terms

Computer Science
Information Sciences

Keywords

Ann Classification Feature Selection Pso Multispectral Image.