Abstract
This paper presents an original research for hyperspectral satellite image compression using a fully neural system with the following processing stages: (1) a Hebbian network performing the principal component selection; (2) a system of “k” circular self-organizing maps for vector quantization of the previously extracted components. The software implementation of the above system has been trained and tested for a hyperspectral image segment of type AVIRIS with 16 bits/pixel/band (b/p/b). One obtains the peak-signal-to-quantization noise ratio of about 50 dB, for a bit rate of 0.07 b/p/b (a compression ratio of 228:1). We also extend the previous model for removal of the spectral redundancy (between the R, G, B channels) of color images as a particular case of multispectral image compression; we consider both the case of color still images and that of color image sequences.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Abousleman, G. P., Marcellin, M. W., Hunt, B. R.: Compression of Hyperspectral Imagery Using the 3-D DCT and Hybrid DPCM/DCT. IEEE Trans. Geosci. Remote Sensing. 33 (1995) 26–34
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, New York (1995)
Chan, Y.-L., Siu, W.-C.: Variable Temporal — Length 3-D Discrete Cosine Transform Coding. IEEE Trans. Image Proc. 6 (1997) 758–763
Cramer, C., Gelenbe, E., Bakircioglu, H.: Low Bit-Rate Video Compression with Neural Networks and Temporal Subsampling. Proceedings IEEE. 84 (1996) 1529–1543
Hertz, J., Krogh, A., Palmer, R.: Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company, Redwood City California (1990)
Jain, A.K.: Fundamentals of Digital Image Processing, Prentice-Hall, Englewood Cliffs NJ (1989)
Kohonen, T.: The Self-Organizing Map. Proceedings IEEE. 78 1461–1480 (1990)
Li, H., Lundmark, A., Forchheimer, R.: Image Sequence Coding at Very Low Bit Rates: A Review. IEEE Trans. Image Proc. 3 (1994) 589–608
Nasrabadi, N.M., King, R.: Image Coding Using Vector Quantization: A Review. IEEE Trans. Commun. COM-36 (1998) 957–971
Neagoe, V.-E.: Predictive Ordering Technique and Feedback Transform Coding for Data Compression of Still Pictures. IEEE Trans Commun. COM-40 (1992) 386–396
Neagoe, V.-E.: A Circular Kohonen Network for Image Vector Quantization, In: D’Hollander, E.H., Joubert, G. R. Peters, F. J., Trystram, D. (eds.): Advances in Parallel Computing, Vol. 11. Elsevier, Amsterdam New York (1996) 677–680
Neagoe, V.-E., Szabo, F., Fratila, I.: A Fully Neural Approach to Color Image Compression. Proceedings of the International Symposium on Communications’96. Bucharest (1996) 476–481
Neagoe, V.-E., Georgescu, B.: A Neural Vector Quantization for Image Sequence Compression. In: Reusch, B., Dascalu, D. (eds.): Real World Applications of Intelligent Technologies. Part II. printed by National Institute for Research and Development in Microtechnologies, Bucharest (1998) 86–90
Neagoe, V.-E., Stanasila, O.: Recunoasterea formelor si retele neurale — algoritmi fundamentali (Pattern Recognition and Neural Networks-Fundamental Algorithms). Ed. Matrix Rom, Bucharest (1999)
Neagoe, V.-E.: A Neural Vector Quantization of 4-D Orthogonally Transformed Color Image Sequences. In: Borcoci, E., Dini, P., Vladeanu, C., Serbanescu, A. (eds.): Proceedings of the IEEE International Conference on Telecommunications, 4–7 June 2001, Bucharest, Romania, Vol. Special Sessions. Printed by Geoma, Bucharest (2001) 247–251
Oja, E.: A Simplified Neuron Model as a Principal Component Analyzer. Math. Biol. 15, 267–273 (1982) 267-273
Ryan, M. J. Arnold, J. F.: The Lossless Compression of AVIRIS Images by Vector Quantization. IEEE Trans. Geosci. Remote Sensing. 35 (1997) 546–550
Sanger, T. D.: Optimal Unsupervised Learning in a Single Layer Linear Feedforward Neural Network. Neural Networks. 2 (1989) 459–473
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neagoe, V. (2001). A Neural Approach to Compression of Hyperspectral Remote Sensing Imagery. In: Reusch, B. (eds) Computational Intelligence. Theory and Applications. Fuzzy Days 2001. Lecture Notes in Computer Science, vol 2206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45493-4_45
Download citation
DOI: https://doi.org/10.1007/3-540-45493-4_45
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42732-2
Online ISBN: 978-3-540-45493-9
eBook Packages: Springer Book Archive