Abstract
Independent component analysis (ICA) finds a linear representation of non-Gaussian data so that the components are statistically independent, or as independent as possible. It has been successfully applied to many problems, such as blind source separation. We apply ICA to high-resolution remote sensing images to obtain an efficient representation of color information. The three independent components are in opponent-color model by which the responses of R, G and B cones are combined in opponent fashions. This is consistent with the principle of many color systems. The interesting point is that there is no summation component that responds to the luminance channel in other transformations such as principal component analysis (PCA). The spectral independent components are then used for classification of high-resolution remote sensing images. The classification map of the independent components exhibits somewhat spatial consistency, which indicates that reduction of spectral correlation may lead to increase of spatial correlation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barlow, H.: Sensory Communication. MIT Press, Boston (1961)
Bell, A., Sejnowski, T.J.: An information-maximasation approach to blind separation and blind deconvolution. Neural Computation 7, 1129–1159 (1995)
Bell, A., Sejnowski, T.J.: The “Independent Components” of natural scenes are edge filters. Vision Res. 37(23), 3327–3338 (1997)
Buchsbaum, G., Gottschalk, A.: Trichromacy, opponent colours coding and optimum colour information transmission in the retina. Proceedings of the Royal Society London, B 220, 89–113 (1983)
Chang, C.I., Chiang, S.-S., Smith, J.A., Ginsberg, I.W.: Linear spectral random mixture analysis for hyperspectral imagery. IEEE Trans. on Geoscience and Remote Sensing 40(2), 375–392 (2002)
Coates, A., Ng, A.Y.: Learning feature representations with K-means. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 561–580. Springer, Heidelberg (2012)
Comon, P.: Independent component analysis- a new concept? Signal Processing 36, 287–314 (1994)
Deco, G., Obradovic, D.: Independent Component Analysis: General Formulation and Linear Case, An Information-theoretic Approach to Neural Computing. Springer, New York (1996)
Ding, C., He, X.: K-means clustering via principal component analysis. In: Proceedings of International Conference on Machine Learning, pp. 225–232 (2004)
Du, Q., Kopriva, I., Szu, H.: Independent-component analysis for hyperspectral remote sensing imagery classification. Opt. Eng. 45(1), 1–13 (2006)
Dubuisson-Jolly, M.P., Gupta, A.: Color and texture fusion: application to aerial image segmentation and GIS updating. Image and Vision Computing 18, 823–832 (2000)
Duda, R., Hart, P.: Pattern Classification and Scene Analysis. Join Wiley and Sons, Inc., New York (1973)
Herault, J., Jutten, C.: Space or time adaptive signal processing by neural network models. In: Denker, J.S. (ed.) Neural Network for Computing. In: Proceedings of AIP Conference, pp. 206–211. American Institute of Physics, New York (1985)
Hyvärinen, A.: Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. on Neural Networks 10(3), 626–634 (1999)
Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and application. Neural Networks 13(4-5), 411–430 (2000)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiely and Sons, Inc., New York (2001)
Klein, U., Sester, M., Strunz, G.: Segmentation of remotely sensed image based on the uncertainty of multispectral classification. IAPRS, GIS-between Vision and Applications, Stuttgart. 32(4), 299–305 (1998)
Lee, T.W., Achtler, T., Sejnowski, T.J.: The spectral independent components of natural scenes. Institute for Neural Computation at UCSD Technical Report Series No. INC-9901, San Diego (1999)
Murai, H., Omatsu, S., OE, S.: Principal component analysis for remotely sensed data classified by kohonens feature mapping preprocessor and multi-layered neural network classifier. IEICE Trans. Commun. E78-B (12), 1604-1610 (1995)
Ruderman, D.L.: Statistics of cone responses to natural images: implications for visual coding. J. Opt. Soc. Am. 15(8), 2036–2045 (1998)
Schiewe, J.: Segmentation of high-resolution remotely sensed data-concept, application and problem. In: Proceedings of Symposium on Geospatial Theory, Processing and Applications, Ottawa (2002)
Settle, J.J., Drake, N.A.: Linear mixing and estimation of ground cover proportions. Int. J. Remote Sensing 14, 1159–1177 (1993)
Tailor, D.R., Finkel, L.H., Buchsbaum, G.: Color-opponent receptive fields derived from independent component analysis of natural images. Vision Res. 40(19), 2671–2676 (2000)
Tu, T.: Unsupervised signature extraction and separation in hyperspectral images: a noise-adjusted independent component analysis approach. Opt. Eng. 39(4), 897–906 (2000)
Villa, A., Chanussot, J., Benediktsson, J.A., Jutten, C., Dambreville, R.: Unsupervised methods for the classification of hyperspectral images with low spatial resolution. Pattern Recognition 46(6), 1556–1568 (2013)
Wyszecki, G., Stiles, W.S.: Color Science: Concepts and Methods, Quantitative Data and Formula, 2nd edn. Wiley, New York (1982)
Zhang, X., Chen, C.H.: New independent component analysis method using higher order statistics with application to remote sensing images. Opt. Eng. 41(7), 1717–1728 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Zeng, XY., Chen, YW. (2014). Independent Component Analysis and Its Application to Classification of High-resolution Remote Sensing Images. In: Chen, YW., C. Jain, L. (eds) Subspace Methods for Pattern Recognition in Intelligent Environment. Studies in Computational Intelligence, vol 552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54851-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-54851-2_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54850-5
Online ISBN: 978-3-642-54851-2
eBook Packages: EngineeringEngineering (R0)