CFP last date
22 April 2024
Reseach Article

Hybrid Subspace Detection based on Spectral and Spatial Information for Effective Hyperspectral Image Classification

by Sadia Zaman Mishu, Boshir Ahmed
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 178 - Number 41
Year of Publication: 2019
Authors: Sadia Zaman Mishu, Boshir Ahmed
10.5120/ijca2019919307

Sadia Zaman Mishu, Boshir Ahmed . Hybrid Subspace Detection based on Spectral and Spatial Information for Effective Hyperspectral Image Classification. International Journal of Computer Applications. 178, 41 ( Aug 2019), 37-43. DOI=10.5120/ijca2019919307

@article{ 10.5120/ijca2019919307,
author = { Sadia Zaman Mishu, Boshir Ahmed },
title = { Hybrid Subspace Detection based on Spectral and Spatial Information for Effective Hyperspectral Image Classification },
journal = { International Journal of Computer Applications },
issue_date = { Aug 2019 },
volume = { 178 },
number = { 41 },
month = { Aug },
year = { 2019 },
issn = { 0975-8887 },
pages = { 37-43 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume178/number41/30812-2019919307/ },
doi = { 10.5120/ijca2019919307 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:52:49.554784+05:30
%A Sadia Zaman Mishu
%A Boshir Ahmed
%T Hybrid Subspace Detection based on Spectral and Spatial Information for Effective Hyperspectral Image Classification
%J International Journal of Computer Applications
%@ 0975-8887
%V 178
%N 41
%P 37-43
%D 2019
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Subspace detection of remote sensing hyperspectral image data cube has become an important area of research because of the challenges of dealing with high dimensional feature space for efficient identification of ground objects. Standard feature extraction method such as Principal Component Analysis (PCA) has several shortcomings as it depends solely on global variance of the data set generated ignoring the low variant components. In this paper these limitations are addressed and alternatively Folded-PCA (FPCA) is used for feature extraction. FPCA has some advantages over PCA as it utilizes both local and global structures of the image and requires comparatively less computational cost and memory. These properties make it suitable for feature extraction therefore our proposed method combines it with Quadratic Mutual Information (QMI) for the task of feature reduction. In this research, QMI is utilized as a means of feature selection over the new features generated from FPCA to obtain an informative subspace. The proposed method is named as (FPCA-QMI). It is tested on two hyperspectral datasets one is real mixed agricultural land and another one is an university area. Finally Kernel Support Vector Machine (KSVM) technique is applied to measure the classification accuracy of these two datasets. From the experimental analysis it is observed that the proposed method can detect effective subspace and obtains the highest accuracy of 98.0328% and 99.0431% on two real hyperspectral images which is better than the baseline approaches.

References
  1. Hossain, M. A., X. Jia, and M. Pickering, 2014. “Subspace detection using a mutual information measure for hyperspectral image classification,” IEEE Geoscience and Remote Sensing Letters, vol. 11, no. 2, pp. 424–428.
  2. Mishu, S. Z., M. A. Hossain, and B. Ahmed. 2018. “Hybrid Sub-space Detection Technique for Effective Hyperspectral Image Classification.” Paper presented at the IEEE 4th International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, Bangladesh
  3. Zabalza, J., J. Ren, M. Yang, Y. Zhang, J. Wang, S. Marshall, and J. Han. 2014. “Novel Folded-PCA for Improved Feature Extraction and Data Reduction with Hyperspectral Imaging and SAR in Remote Sensing.” ELSEVIER ISPRS
  4. Hughes, G. 1968. “On the mean accuracy of statistical pattern recognizers”, IEEE Transactions on Information Theory, IT-14(1): 55-63. doi:10.1109/TIT.1968.1054102.
  5. Jia, X., B. Kuo, and M. M. Crawford, 2013. "Feature mining for hyperspectral image classification," Proceedings of the IEEE Journals and Magazines, vol. 101, pp. 676-697,
  6. Richards, J. A. and X. Jia, 2006. “Remote Sensing Digital Image Analysis,” 4th Edition: Springer-Verlag Berlin Heidelberg, Germany
  7. Deepa, P.,and K. Thilagavathi, 2015. “Feature Extraction of Hyperspectral Image Using Principal Component Analysis and Folded-principal Component Analysis”, Paper presented at 2nd International Conference on Electronics and Communication Systems (ICECS): 656-660.
  8. Uddin, M. P., M. A. Mamun, and M. A. Hossain, 2017. “Feature Extraction for Hyperspectral Image Classification”, Paper presented at the IEEE 5th Region 10 Humanitarian Technology Conference (R10-HTC), Bangladesh.
  9. Uddin, M. P., M. A. Mamun, and M. A. Hossain, 2017. “Segmented FPCA for hHyperspectral Image Classification”, Paper presented at the IEEE 3rd International Conference on Electrical Information and Communication Technology (EICT), Bangladesh.
  10. Torkkola, K, 2003. “Feature extraction by non-parametric mutual information maximization,” Journal of Machine Learning Research, vol. 3, pp. 1415–1438.
  11. Viola, P. and W. M. Wells III, 1997. “Alignment by maximization of mutual information,” International Journal of Computer Vision, vol. 24, no. 2, pp. 137 – 154.
  12. Vinh, N. X. and J. Bailey, 2010. “Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance,” Journal of Machine Learning Research, vol. 11, pp. 2837–2854.
  13. Hossain, M. A., M. Pickering, X. Jia, 2011. ”Unsupervised feature extraction based on mutual information measure for hyperspectral image classification”, IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 978-1-4577-1005-6.
  14. Deolindo, C. S., A. C. B. Kunicki, F. L. Brasil, and R. C. Moioli, 2014. “Limitations of Principal Component Analysis as a Method to Detect Neuronal Assemblies” Paper presented at IEEE 16th International Conference on e-health Networking, Applications and Services (Healthcom).
  15. Rodarmel, C. and J. Shan, 2002.“Principal component analysis for hyperspectral image classification”. In: Surveying and Land Information Systems, 62.2, pp. 115–122.
  16. Shannon, C. E. and W. Weaver, 1949.“The mathematical theory of communication,” Urbana, IL: University of Illinois Press.
  17. Sluga, D. and U. Lotri, 2017. ”Quadratic mutual information feature selection,“Journal of Entropy,19,157.
  18. Sluga, D. and U. Lotric, 2013. “Generalized Information-theoretic Measures for Feature Selection,” In Proceedings of the International Conference on Adaptive and Natural Computing Algorithms, Lausanne, Switzerland, Springer: Berlin/Heidelberg, Germany, pp. 189–197. 4-6.
  19. Hossain, M.A., H. E. Jannat, B. Ahmed, and M. A. Mamun,”Feature mining for effective subpace detection and classification of hyperspectral images,” International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox’s Bazar, Bangladesh, 16-18 Februar, 2017.
  20. Kavitha, K., S. Arivazhagan and B. Suriya, 2014, “Classification of Pavia University Hyperspectral Image using Gabor and SVM Classifier”, International Journal of New Trends in Electronics and Communication, vol.2 issue. 3.
Index Terms

Computer Science
Information Sciences

Keywords

Subspace Folded Principal Component Analysis Quadratic Mutual Information Kernel Support Vector Machine