A Spatial Hypergraph Based Semi-Supervised Band Selection Method for Hyperspectral Imagery Semantic Interpretation

Hyperspectral imagery (HSI) typically provides a
wealth of information captured in a wide range of the
electromagnetic spectrum for each pixel in the image. Hence, a
pixel in HSI is a high-dimensional vector of intensities with a
large spectral range and a high spectral resolution. Therefore, the
semantic interpretation is a challenging task of HSI analysis. We
focused in this paper on object classification as HSI semantic
interpretation. However, HSI classification still faces some issues,
among which are the following: The spatial variability of spectral
signatures, the high number of spectral bands, and the high cost
of true sample labeling. Therefore, the high number of spectral
bands and the low number of training samples pose the problem of
the curse of dimensionality. In order to resolve this problem, we
propose to introduce the process of dimensionality reduction trying
to improve the classification of HSI. The presented approach is a
semi-supervised band selection method based on spatial hypergraph
embedding model to represent higher order relationships with
different weights of the spatial neighbors corresponding to the
centroid of pixel. This semi-supervised band selection has been
developed to select useful bands for object classification. The
presented approach is evaluated on AVIRIS and ROSIS HSIs
and compared to other dimensionality reduction methods. The
experimental results demonstrate the efficacy of our approach
compared to many existing dimensionality reduction methods for
HSI classification.

Authors:

• Akrem Sellami
• Imed Riadh Farah

Keywords:

• Hyperspectral image
• spatial hypergraph
• dimensionality reduction
• semantic interpretation
• band selection
• feature extraction.

References:

[1] A. Radoi, R. Tanase, and M. Datcu, “Semantic interpretation of
multi-level change detection in multi-temporal satellite images,” in
Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE
International. IEEE, 2015, pp. 4157–4160.
[2] M. Ivasic-Kos, M. Pavlic, and P. Poscic, “The analysis and overview of
semantic image interpretation,” in Information Technology Interfaces,
2009. ITI’09. Proceedings of the ITI 2009 31st International
Conference on. IEEE, 2009, pp. 181–186.
[3] G. T. Papadopoulos, C. Saathoff, M. Grzegorzek, V. Mezaris,
I. Kompatsiaris, S. Staab, and M. G. Strintzis, “Comparative
evaluation of spatial context techniques for semantic image analysis,”
in Image Analysis for Multimedia Interactive Services, 2009.
WIAMIS’09. 10th Workshop on. IEEE, 2009, pp. 161–164.
[4] C. Hudelot, N. Maillot, and M. Thonnat, “Symbol grounding
for semantic image interpretation: from image data to semantics,”
in Computer Vision Workshops, 2005. ICCVW’05. Tenth IEEE
International Conference on. IEEE, 2005, pp. 1875–1875.
[5] M. Ivaˇsi´c-Kos, M. Pavli´c, and M. Mateti´c, “Data preparation for
semantic image interpretation,” in Information Technology Interfaces
(ITI), 2010 32nd International Conference on. IEEE, 2010, pp.
181–186.
[6] S. Chen and D. Zhang, “Semisupervised dimensionality reduction
with pairwise constraints for hyperspectral image classification,”
Geoscience and Remote Sensing Letters, IEEE, vol. 8, no. 2, pp.
369–373, 2011.
[7] H. Huang and M. Yang, “Dimensionality reduction of hyperspectral
images with sparse discriminant embedding,” Geoscience and Remote
Sensing, IEEE Transactions on, vol. 53, no. 9, pp. 5160–5169, 2015.
[8] H. Huang, J. Li, and J. Liu, “Enhanced semi-supervised local
fisher discriminant analysis for face recognition,” Future Generation
Computer Systems, vol. 28, no. 1, pp. 244–253, 2012.
[9] W. Li, S. Prasad, J. E. Fowler, and L. M. Bruce, “Locality-preserving
dimensionality reduction and classification for hyperspectral image
analysis,” Geoscience and Remote Sensing, IEEE Transactions on,
vol. 50, no. 4, pp. 1185–1198, 2012.
[10] J. Khoder, R. Younes, and F. B. Ouezdou, “Stability of dimensionality
reduction methods applied on artificial hyperspectral images,” in
Computer Vision and Graphics. Springer, 2012, pp. 465–474. [11] B.-C. Kuo, C.-H. Li, and J.-M. Yang, “Kernel nonparametric weighted
feature extraction for hyperspectral image classification,” Geoscience
and Remote Sensing, IEEE Transactions on, vol. 47, no. 4, pp.
1139–1155, 2009.
[12] J. Feng, L. Jiao, F. Liu, T. Sun, and X. Zhang, “Unsupervised feature
selection based on maximum information and minimum redundancy
for hyperspectral images,” Pattern Recognition, vol. 51, pp. 295–309,
2016.
[13] J. M. Sotoca and F. Pla, “Supervised feature selection by clustering
using conditional mutual information-based distances,” Pattern
Recognition, vol. 43, no. 6, pp. 2068–2081, 2010.
[14] B. Guo, R. I. Damper, S. R. Gunn, and J. D. Nelson, “A
fast separability-based feature-selection method for high-dimensional
remotely sensed image classification,” Pattern Recognition, vol. 41,
no. 5, pp. 1653–1662, 2008.
[15] L. Zhang, C. Chen, J. Bu, and X. He, “A unified feature and instance
selection framework using optimum experimental design,” Image
Processing, IEEE Transactions on, vol. 21, no. 5, pp. 2379–2388,
2012.
[16] C.-I. Chang and S. Wang, “Constrained band selection for
hyperspectral imagery,” Geoscience and Remote Sensing, IEEE
Transactions on, vol. 44, no. 6, pp. 1575–1585, 2006.
[17] S. B. Kim and P. Rattakorn, “Unsupervised feature selection using
weighted principal components,” Expert systems with applications,
vol. 38, no. 5, pp. 5704–5710, 2011.
[18] W. Jian, “Unsupervised intrusion feature selection based on genetic
algorithm and fcm,” in Information Engineering and Applications.
Springer, 2012, pp. 1005–1012.
[19] M. Breaban and H. Luchian, “A unifying criterion for unsupervised
clustering and feature selection,” Pattern Recognition, vol. 44, no. 4,
pp. 854–865, 2011.
[20] M. Sugiyama, “Dimensionality reduction of multimodal labeled data
by local fisher discriminant analysis,” The Journal of Machine
Learning Research, vol. 8, pp. 1027–1061, 2007.
[21] P. Deepa and K. Thilagavathi, “Feature extraction of hyperspectral
image using principal component analysis and folded-principal
component analysis,” in Electronics and Communication Systems
(ICECS), 2015 2nd International Conference on. IEEE, 2015, pp.
656–660.
[22] L. Ding, P. Tang, and H. Li, “Isomap-based subspace analysis for
the classification of hyperspectral data,” in Geoscience and Remote
Sensing Symposium (IGARSS), 2013 IEEE International. IEEE, 2013,
pp. 429–432.
[23] S. Yan, D. Xu, B. Zhang, H.-J. Zhang, Q. Yang, and S. Lin,
“Graph embedding and extensions: a general framework for
dimensionality reduction,” Pattern Analysis and Machine Intelligence,
IEEE Transactions on, vol. 29, no. 1, pp. 40–51, 2007.
[24] C. Berge and E. Minieka, Graphs and hypergraphs. North-Holland
publishing company Amsterdam, 1973, vol. 7.
[25] Y. Huang, Q. Liu, S. Zhang, and D. N. Metaxas, “Image retrieval via
probabilistic hypergraph ranking,” in Computer Vision and Pattern
Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010, pp.
3376–3383.
[26] R. Ji, Y. Gao, R. Hong, Q. Liu, D. Tao, and X. Li, “Spectral-spatial
constraint hyperspectral image classification,” Geoscience and Remote
Sensing, IEEE Transactions on, vol. 52, no. 3, pp. 1811–1824, 2014.
[27] H. Yuan and Y. Y. Tang, “Learning with hypergraph for hyperspectral
image feature extraction,” Geoscience and Remote Sensing Letters,
IEEE, vol. 12, no. 8, pp. 1695–1699, 2015.
[28] A. Soltani-Farani, H. R. Rabiee, and S. A. Hosseini, “Spatial-aware
dictionary learning for hyperspectral image classification,” Geoscience
and Remote Sensing, IEEE Transactions on, vol. 53, no. 1, pp.
527–541, 2015.
[29] F. Nie, S. Xiang, Y. Liu, and C. Zhang, “A general graph-based
semi-supervised learning with novel class discovery,” Neural
Computing and Applications, vol. 19, no. 4, pp. 549–555, 2010.
[30] P. Mitra, C. Murthy, and S. K. Pal, “Unsupervised feature selection
using feature similarity,” IEEE transactions on pattern analysis and
machine intelligence, vol. 24, no. 3, pp. 301–312, 2002.