Share This Article:

Adaptive Lifting Transform for Classification of Hyperspectral Signatures

Abstract Full-Text HTML XML Download Download as PDF (Size:836KB) PP. 138-146
DOI: 10.4236/ars.2015.42012    3,805 Downloads   4,195 Views  

ABSTRACT

Supervised classification of hyperspectral images is a challenging task because of the higher dimensionality of a pixel signature. The conventional classifiers require large training data set; however, practically limited numbers of labeled pixels are available due to complexity and cost involved in sample collection. It is essential to have a method that can reduce such higher dimensional data into lower dimensional feature space without the loss of useful information. For classification purpose, it will be useful if such a method takes into account the nature of the underlying signal when extracting lower dimensional feature vector. The lifting framework provides the required flexibility. This article proposes the adaptive lifting wavelet transform to extract the lower dimensional feature vectors for the classification of hyperspectral signatures. The proposed adaptive update step allows the decomposition filter to adapt to the input signal so as to retain the desired characteristics of the signal. A three-layer feed forward neural network is used as a supervised classifier to classify the extracted features. The effectiveness of the proposed method is tested on two hyperspectral data sets (HYDICE & ROSIS sensors). The performance of the proposed method is compared with first generation discrete wavelet transform (DWT) based feature extraction method and previous studies that use the same data. The indices used for measuring performance are overall classification accuracy and Kappa value. The experimental results show that the proposed adaptive lifting scheme (ALS) has excellent results with a small size training set.

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

Agrawal, R. and Bawane, N. (2015) Adaptive Lifting Transform for Classification of Hyperspectral Signatures. Advances in Remote Sensing, 4, 138-146. doi: 10.4236/ars.2015.42012.

References

[1] Chang, C.I. (2003) Hyperspectral Imaging: Techniques for Spectral Detection and Classification. Kluwer, New York.
http://dx.doi.org/10.1007/978-1-4419-9170-6
[2] Donoho, D.L. (2000) High-Dimensional Data Analysis: The Curses and Blessing of Dimensionality. AMS Math-Ematical Challenges of the 21st Century.
[3] Serpico, S.B. and Moser, G. (2007) Extraction of Spectral Channels From Hyperspectral Images for Classification Purposes. IEEE Transactions on Geoscience and Remote Sensing, 45, 484-495.
http://dx.doi.org/10.1109/TGRS.2006.886177
[4] Mallat, S.G. (1989) A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 674-693.
http://dx.doi.org/10.1109/34.192463
[5] Selesnick, I.W., Baraniuk, R.G. and Kingsbury, N.G. (2005) The Dual-Tree Complex Wavelet Transform. IEEE Signal Processing Magazine, 22, 123-151.
http://dx.doi.org/10.1109/MSP.2005.1550194
[6] Hsu, P.-H., Tseng, Y.-H. and Gong, P. (2006) Spectral Feature Extraction of Hyperspectral Images Using Wavelet Transform. Journal of Photogrammetry and Remote Sensing, 11, 93-109.
[7] Bruce, L.M., Koger, C.H. and Li, J. (2002) Dimensionality Reduction of Hyperspectral Data Using Discrete Wavelet Transform Feature Extraction. IEEE Transactions on Geoscience and Remote Sensing, 40, 2331-2338.
[8] Choi, H., Romberg, J., Baraniuk, R. and Kingsbury, N. (2000) Hidden Markov Tree Modeling of Complex Wavelet Transforms. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1, 133-136.
[9] Sweldens, W. (1995) The Lifting Scheme: A New Philosophy in Biorthogonal Wavelet Constructions. In: Proceedings of SPIE 2569: Wavelet Applications in Signal and Image Processing III, SIPE Press, San Diego, 68-79.
[10] Claypoole, R.L., Baraniuk, R.G. and Nowak, R.D. (1998) Adaptive Wavelet Transforms via Lifting. Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, 3, 1513-1516.
http://dx.doi.org/10.1109/icassp.1998.681737
[11] Claypoole, R.L., Davis, G.M., Sweldens, W. and Baraniuk, R.G. (2003) Nonlinear Wavelet Transforms for Image Coding via Lifting. IEEE Transactions on Image Processing, 12, 1449-1459.
http://dx.doi.org/10.1109/TIP.2003.817237
[12] Piella, G. and Heijmans, H.J.A.M. (2002) Adaptive Lifting Schemes with Perfect Reconstruction. IEEE Transactions on Signal Processing, 50, 1620-1630.
http://dx.doi.org/10.1109/TSP.2002.1011203
[13] Heijmas, H.J.A.M., Pesquet-Popescu, B. and Piella, G. (2005) Building Nonredundant Adaptive Wavelets by Update Lifting. Applied and Computational Harmonic Analysis, 18, 252-281.
http://dx.doi.org/10.1016/j.acha.2004.11.006
[14] Piella, G. and Pesquet-Popescu, B. (2007) A Three-Step Nonlinear Lifting Scheme for Lossless Image Compression. Proceedings of the IEEE International Conference on Image Processing, San Antonio, 16 September-19 October 2007, 453-456.
[15] Tomic, M. and Sersic, D. (2013) Point-Wise Adaptive Wavelet Transform for Signal Denoising. INFORMATICA, 24, 637-656.
[16] Subasi, A. and Ercelebi, E. (2005) Classification of EEG Signals Using Neural Network and Logistic Regression. Computer Methods and Programs in Biomedicine, 78, 87-99.
http://dx.doi.org/10.1016/j.cmpb.2004.10.009
[17] Ding, X.W. and Huang, W.G. (2007) SAR Image De-Noising by Wavelet Transform Based on Lifting Scheme. Proceedings of SPIE—The International Society for Optical Engineering, 67-87.
http://dx.doi.org/10.1117/12.748762
[18] Gouze, A., Antonini, M., Barlaud, M. and Macq, B. (2004) Design of Signal-Adapted Multidimensional Lifting Scheme for Lossy Coding. IEEE Transactions on Image Processing, 13, 1589-1603.
[19] Benazza-Benyahia, A., Pesquet, J.-C., Hattay, J. and Masmoudi, H. (2007) Block-Based Adaptive Vector Lifting Schemes for Multichannel Image Coding. EURASIP Journal on Image and Video Processing, 2007, Article ID: 013421.
[20] Landgrebe, D.A. (2003) Signal Theory Methods in Multispectral Remote Sensing. John Wiley and Sons, New York.
http://dx.doi.org/10.1002/0471723800
[21] https://engineering.purdue.edu/biehl/MultiSpec/hyperspectral
[22] Gamba, P. University of Pavia.
http://eecs.unipv.it/teaching-staff/paolo-gamba/
[23] Haykin, S. (1997) Neural Networks: A Comprehensive Foundation. Prentice Hall, England.
[24] Richards, J.A. and Jia, X. (1999) Remote Sensing Digital Image Analysis: An Introduction. Springer, New York.
http://dx.doi.org/10.1007/978-3-662-03978-6
[25] Kuo, B.-C. and Landgrebe, D.A. (2004) Hyperspectral Data Classification Using Nonparametric Weighted Feature Extraction. IEEE Transactions on Geoscience and Remote Sensing, 42, 1096-1105.
http://dx.doi.org/10.1109/TGRS.2004.825578
[26] Plaza, A., Benediktsson, J.A., Boardman, J.W., Braziled, J., Bruzzonee, L., Camps-Valls, G., et al. (2009) Recent Advances in Techniques for Hyperspectral Image Processing. Remote Sensing of Environment, 113, S110-S122.
[27] Tarabalka, Y., Chanussot, J. and Benediktsson, J.A. (2010) Segmentation and Classification of Hyperspectral Images Using Watershed Transformation. Pattern Recognition, 43, 2367-2379.
http://dx.doi.org/10.1016/j.patcog.2010.01.016

  
comments powered by Disqus

Copyright © 2018 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.