Abstract
The high dimensions of hyperspectral imagery have caused burden for further processing. A new Fast Independent Component Analysis (FastICA) approach to dimensionality reduction for hyperspectral imagery is presented. The virtual dimensionality is introduced to determine the number of dimensions needed to be preserved. Since there is no prioritization among independent components generated by the FastICA, the mixing matrix of FastICA is initialized by endmembers, which were extracted by using unsupervised maximum distance method. Minimum Noise Fraction (MNF) is used for preprocessing of original data, which can reduce the computational complexity of FastICA significantly. Finally, FastICA is performed on the selected principal components acquired by MNF to generate the expected independent components in accordance with the order of endmembers. Experimental results demonstrate that the proposed method outperforms second-order statistics-based transforms such as principle components analysis.
Similar content being viewed by others
References
B. Penna, T. Tillo, E. Magli, et al.. Transform coding techniques for lossy hyperspectral data compression. IEEE Transactions on Geoscience and Remote Sensing, 45(2007)5, 1408–1421.
B. Penna, T. tillo, E. Magli, et al.. Hyperspectral image compression employing a model of anomalous pixels. IEEE Geoscience and Remote Sensing Letters, 4(2007)4, 664–668.
Q. Du, and J. E. Fowler. Hyperspectral image compression using JPEG2000 and principal component analysis. IEEE Geoscience and Remote Sensing Letters, 4(2007)2, 201–205.
Z. T. Zhou, G. H. Dong, X. Xu, et al.. Independent Components Analysis. Beijing, Publishing House of Electronics Industry, 2007, 108–111 (in Chinese). 周宗潭, 董国华, 徐昕, 等. 独立成分分析. 北京. 电 子工业出版社, 2007, 108–111.
Y. Feng, M. Y. He, J. H. Song, et al.. ICA-based dimensionality reduction and compression of hyper spectral images. Journal of Electronics & Information Technology, 29(2007)12, 2871–2875 (in Chinese). 冯燕, 何明一, 宋江红, 等. 基于独立成分分析的高光 谱图像数据降维及压缩. 电子与信息学报, 29(2007)12, 2871–2875
B. Ramakrishna, J. Wang, C. -I Chang, et al.. Spectral/spatial hyperspectral image compression in conjunction with virtual dimensionality. Proceedings of SPIE, Boston, USA, 5806(2005), 772–781.
J. Wang and C. -I Chang. Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis. IEEE Transactions on Geoscience and Remote Sensing, 44(2006)6, 1586–1600.
J. Wang and C. -I. Chang. Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 44(2006)9, 1586–1600.
A. Hyvarinen and E. Oja. A fast fixed-point algorithm for independent component analysis. Neural Computation, 9(1997)7, 1483–1492.
C. -I Chang and Q. Du. Estimation of number of spectrally distinct signal sources in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 42(2004)3, 608–619.
X. R. Geng. Research on target detection and classification of hyperspectral remotesensing [Ph.D. Dissertation]. Beijing, Institute of Remote Sensing Applications in the Chinese Academy of Sciences, 2005.
A. A. Green, M. Berman, P. Switzer, et al.. A transformation for ordering multispectral data in terms of image quality with implications for noise removal. IEEE Transactions on Geoscience and Remote Sensing, 26(1988)1, 65–74.
Q. Du, I. Kopriva, and H. Szu. Classifying hyperspectral remote sensing imagery with independent component analysis. Proceedings of SPIE, Boston, USA, 5818(2005), 50–58.
G. Motta, F. Rozzo, and J. A. Storer. Hyperspectral Data Compression. New York, US, Springer, 2006, 314–317.
J. M. P. Nascimento and J. M. B. Dias. Does independent component analysis play a role in unmixing hyperspectral data. IEEE Transactions on Geoscience and Remote Sensing, 43(2006)1, 175–187.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (No. 60572135).
Communication author: Xin Qin, born in 1973, male, Ph.D., associate professor.
About this article
Cite this article
Xin, Q., Nian, Y., Li, X. et al. Dimensionality reduction for hyperspectral imagery based on fastica. J. Electron.(China) 26, 831–835 (2009). https://doi.org/10.1007/s11767-009-0023-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-009-0023-5