Login Register Cart 0
Generic placeholder image

Recent Patents on Engineering

Editor-in-Chief

ISSN (Print): 1872-2121
ISSN (Online): 2212-4047

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Hyperspectral Image Data Classification with Refined Spectral Spatial Features Based on Stacked Autoencoder Approach

Author(s): Jacintha Menezes * and Nagesh Poojary

Volume 15, Issue 2, 2021

Published on: 11 September, 2019

Page: [140 - 149] Pages: 10

DOI: 10.2174/1872212113666190911141616

Price: $65

Abstract

Background: Hyperspectral (HS) image data comprises of tremendous amount of spatial and spectral information which offers feature identification and classification with high accuracy. As part of the Deep Learning (DL) framework Stacked Autoencoders (SAEs) has been successfully applied for deep spectral features extraction in high dimensional data. HS deep image feature extraction becomes complex and time consuming due to the hundreds of spectral bands available in the hypercubes.

Methods: The proposed method aims condense the spectral-spatial information through suitable feature extraction and feature selection methods to reduce data dimension to an appropriate scale. Further, the reduced feature set is processed by SAE for final feature representation and classification.

Results: The proposed method has resulted in reduced computation time by ~ 300s and an improvement in classification accuracy by ~15% as compared to uncondensed spectral-spatial features fed directly to SAE network.

Conclusion: Future research could explore the combination of most state-of-the art techniques.

Keywords: Deep learning, stacked auto encoders, hyperspectral imaging, data reduction, data dimension, framework.

Graphical Abstract

[1]
I. Jolliffe, “Principal component analysis”, International encyclopedia of statistical science., Springer, 2011, pp. 1094-1096.
[http://dx.doi.org/10.1007/978-3-642-04898-2_455]
[2]
H. Othman, and S-E. Qian, "Noise reduction of hyperspectral imagery using hybrid spatial-spectral derivative-domain wavelet shrinkage", IEEE Transactions on Geoscience and Remote Sensing, IEEE, vol. 44, pp. 397-408, 2006.
[http://dx.doi.org/10.1109/TGRS.2005.860982]
[3]
J. Wang, and C-I. Chang, Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis.IEEE trans. Geosci. remote sens.IEEE, vol. 44, pp. 1586-1600., 2006..
[4]
A.J. Izenman, Linear discriminant analysis. Modern multivariate statistical techniques., Springer, 2013, pp. 237-280.
[http://dx.doi.org/10.1007/978-0-387-78189-1_8]
[5]
W. Liao, A. Pizurica, P. Scheunders, W. Philips, and Y. Pi, Semisupervised local discriminant analysis for feature extraction in hyperspectral images.IEEE Trans. Geosci. Remote Sens.IEEE, vol. 51, pp. 184-198, 2013..
[http://dx.doi.org/10.1109/TGRS.2012.2200106]
[6]
L.M. Bruce, C.H. Koger, and J. Li, Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction.IEEE Trans. Geosci. Remote Sens.IEEE, vol. 40, pp. 2331- 2338., 2002..
[7]
S. Kaewpijit, J. Le Moigne, and T. El-Ghazawi, Automatic reduction of hyperspectral imagery using wavelet spectral analysis.IEEE trans. Geosci. Remote SensIEEE, vol. 41, pp. 863-871., 2003..
[8]
C.H. Park, and M. Lee, On applying linear discriminant analysis for multi-labeled problems Patt. recog. let., vol. 29, pp. 878-887,, 2008.
[9]
G. Chandrashekar, and F. Sahin, "A survey on feature selection methods", Comput. Electr. Eng., vol. 40, pp. 16-28, 2014.
[http://dx.doi.org/10.1016/j.compeleceng.2013.11.024]
[10]
H. Peng, F. Long, and C. Ding, “Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy”, IEEE Trans. Patt. Anal. mach. intel., vol. 27. IEEE, pp. 1226-1238.2005,
[11]
M. Dash, and H. Liu, Feature selection for classification Intelligent data analysis, vol. 1, IOS Press, 1997, pp. 131-156..
[12]
Q. Dai, J-H. Cheng, D-W. Sun, and X-A. Zeng, “Advances in feature selection methods for hyperspectral image processing in food industry applications: a review”, Crit. Rev. food sci. nutrit., vol. 5. Taylor & Francis, 2015, pp. 1368-1382.
[13]
J. Bao, M. Chi, and J.A. Benediktsson, “Spectral derivative features for classification of hyperspectral remote sensing images: Experimental evaluation”, IEEE J. Select. Topics Appl. Earth Observ. Remote Sens.IEEE, vol. 6, pp. 594-601, 2013..
[http://dx.doi.org/10.1109/JSTARS.2013.2237758]
[14]
I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio, Deep learning., MIT press: Cambridge, 2016.
[15]
L. Zhang, L. Zhang, and B. Du, Deep learning for remote sensing data: A technical tutorial on the state of the art.IEEE Geosci. Remote Sens. Mag.IEEE vol. 4, pp. 22-40, 2016..
[http://dx.doi.org/10.1109/MGRS.2016.2540798]
[16]
M. Fauvel, Y. Tarabalka, J.A. Benediktsson, J. Chanussot, and J.C. Tilton, "Advances in spectral-spatial classification of hyperspectral images", Proceedings of the IEEE, IEEE, vol. 101, pp. 652-675, 2013.
[http://dx.doi.org/10.1109/JPROC.2012.2197589]
[17]
M. Fauvel, J.A. Benediktsson, J. Chanussot, and J.R. Sveinsson, Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles.IEEE Trans. Geosci. Remote Sens.IEEE, vol. 46, pp. 3804-3814, 2008..
[http://dx.doi.org/10.1109/TGRS.2008.922034]
[18]
J. Zabalza, J. Ren, J. Zheng, H. Zhao, C. Qing, Z. Yang, P. Du, and S. Marshall, "Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging", Neurocomput., vol. 185, pp. 1-10, 2016.
[http://dx.doi.org/10.1016/j.neucom.2015.11.044]
[19]
Y. Chen, Z. Lin, X. Zhao, G. Wang, and Y. Gu, “Deep learning-based classification of hyperspectral data”, IEEE J. Select. topics appl. earth observ. remote sens., vol. 7. IEEE, 2014, pp. 2094-2107.
[20]
N. Renard, S. Bourennane, and J. Blanc-Talon, Denoising and dimensionality reduction using multilinear tools for hyperspectral images.IEEE Geosci. Remote Sens. Let.IEEE, vol. 5, pp. 138-142, 2008..
[http://dx.doi.org/10.1109/LGRS.2008.915736]
[21]
M.F. Møller, "A scaled conjugate gradient algorithm for fast supervised learning", Neural Netw., vol. 6, pp. 525-533, .1993,
[22]
Y. Li, Y. Zhang, Z. Yuan, H. Guo, H. Pan, and J. Guo, "Marine Oil Spill Detection Based on the Comprehensive Use of Polarimetric SAR Data, Sustainability", Multidisciplin. Dig. Pub. Inst., vol. 10, p. 4408, 2018.
[23]
S. Zhou, Z. Xue, and P. Du, “Semisupervised Stacked Autoencoder With Cotraining for Hyperspectral Image Classification”, IEEE Trans. Geosci. Remote Sens., IEEE, 2019.
[24]
L. Zhang, and B. Cheng, "A stacked autoencoders-based adaptive subspace model for hyperspectral anomaly detection", Infrared Phys. Technol., vol. 96, pp. 52-60, 2019.
[http://dx.doi.org/10.1016/j.infrared.2018.11.015]
[25]
H. Holden, and E. LeDrew, "Spectral discrimination of healthy and non-healthy corals based on cluster analysis, principal components analysis, and derivative spectroscopy", Remote Sens. Environ., vol. 65, pp. 217-224, 1998.
[26]
T.H. Demetriades-Shah, M.D. Steven, and J.A. Clark, "High resolution derivative spectra in remote sensing", Remote Sens. Environ., vol. 33, pp. 55-64, 1990.
[http://dx.doi.org/10.1016/0034-4257(90)90055-Q]
[27]
F. Tsai, and W. Philpot, Derivative analysis of hyperspectral data for detecting spectral features Geosci. Remote Sens., 1997. IGARSS’97. Remote Sensing-A Scientific Vision for Sustainable Development, IEEE International, 1997, pp. 1243-1245..
[http://dx.doi.org/10.1109/IGARSS.1997.606410]
[28]
Y. Li, "Hyperspectral derivative on Clifford manifold", Information Technol. J., vol. 11, pp. 904-909, 2012.
[http://dx.doi.org/10.3923/itj.2012.904.909]
[29]
B. Rasti, J.R. Sveinsson, M.O. Ulfarsson, and J.A. Benediktsson, "Hyperspectral image denoising using 3D wavelets Geoscience and Remote Sensing Symposium (IGARSS), IEEE International, 2012, pp. 1349-1352",
[30]
R. Maini, and H. Aggarwal, “Study and comparison of various image edge detection techniques”, Int. J. image process., vol. Vol. 3. IJIP, 2009, pp. 1-11.
[31]
C. Zhu, and X. Yang, Study of remote sensing image texture analysis and classification using wavelet nt. J. Remote Sens., Taylor & Francis, vol. 19, pp. 3197-3203, 1998., .
[http://dx.doi.org/10.1080/014311698214262]
[32]
D.A. Yocky, "Image merging and data fusion by means of the discrete two-dimensional wavelet transform, JOSA A", Optic. Soc. America, vol. 12, pp. 1834-1841, 1995.
[http://dx.doi.org/10.1364/JOSAA.12.001834]
[33]
Q. Du, and J.E. Fowler, "“Hyperspectral image compression using JPEG2000 and principal component analysis”, IEEE Geosci. Remote sens", Let.vol. 4, 2007, pp. 201-205. [IEEE
[34]
A. Karami, M. Yazdi, and G. Mercier, “Compression of hyperspectral images using discerete wavelet transform and tucker decomposition”, IEEE J. select. topics appl. earth observ. remote sens., vol. 5. IEEE, 2012, pp. 444-450.
[35]
S.G. Mallat, A theory for multiresolution signal decomposition: the wavelet representation, IEEE transactions on pattern analysis and machine intelligence.IEEE, vol. 11, pp. 674-693., 1989..
[36]
P-H. Hsu, Y-H. Tseng, and P. Gong, Dimension reduction of hyperspectral images for classification applications Geograph. Info. Sci., Taylor & Francis, vol. 8, pp. 1-8, 2002..
[http://dx.doi.org/10.1080/10824000209480567]
[37]
C. Tao, Y. Tang, C. Fan, and Z. Zou, Hyperspectral imagery classification based on rotation-invariant spectral–spatial feature.IEEE Geosci. Remote Sens. LetIEEE, vol. 11, pp. 980-984, 2014.
[http://dx.doi.org/10.1109/LGRS.2013.2284007]
[38]
C.M. Reddy, J.S. Arey, J.S. Seewald, S.P. Sylva, K.L. Lemkau, R.K. Nelson, C.A. Carmichael, C.P. McIntyre, J. Fenwick, and G.T. Ventura, "Composition and fate of gas and oil released to the water column during the Deepwater Horizon oil spill", Proceedings of the National Academy of Sciences, National Academy Sciences, vol. 109, pp. 20229-20234, .2012,
[http://dx.doi.org/10.1073/pnas.1101242108]
[39]
F. Module, "Atmospheric correction module: Quac and flaash users guide", Version, vol. 4, p. 44, 2009.
[40]
J. Gruninger, and S. Adler-Golden, Process for finding endmembers in a data set. US Patent 7680337-B2, 2010..
[41]
X. Ma, H. Wang, and J. Geng, “Spectral–spatial classification of hyperspectral image based on deep auto-encoder”, IEEE J.Select. Topics Appl. Earth Observ. Remote Sens.EEE, vol. 9, pp. 4073-4085, 2016..
[http://dx.doi.org/10.1109/JSTARS.2016.2517204]
[42]
B.L. Davis, T.F. Rodriguez, and G.B. Rhoads, inventors; Digimarc Corporation, assignee. Longitudinal dermoscopic study employing smartphone-based image registration.US Patent US 14/288,890. 2014 Oct 23..
[43]
L. Xiaoqiang, Y. Yuan, and Z. Xiangtao, Transfer learning-based hyperspectral image super-resolution method CN Patent CN107301372A , 2017.

Rights & Permissions Print Cite
Article Metrics
6
1
© 2024 Bentham Science Publishers | Privacy Policy