Principal component analysis (PCA) is an effective tool for spectral decorrelation of hyperspectral imagery, and PCAbased spectral transforms have been employed successfully in conjunction with JPEG2000 for hyperspectral image compression. However, the computational cost of determining the data-dependent PCA transform is high because of its traditional eigendecomposition implementation which requires calculation of a covariance matrix across the data. Several strategies for reducing the computation burden of PCA are explored, including both spatial and spectral subsampling in the covariance calculation as well as an iterative algorithm that circumvents determination of the covariance matrix entirely. Experimental results investigate the impacts of such low-complexity PCA on JPEG2000 compression of hyperspectral images, focusing on rate-distortion performance as well as data-analysis performance at an anomaly-detection task.
Baldi, P.F. and Hornik, K. (1995). Learning in linear neural networks: A survey, IEEE Transactions on Neural Networks6(4): 837-857.
2.
Chang, C.-I. and Chiang, S.-S. (2002). Anomaly detection and classification for hyperspectral imagery, IEEE Transactions on Geoscience and Remote Sensing40(6): 1314- 1325.
3.
Chang, C.-I. and Du, Q. (2004). Estimation of number of spectrally distinct signal sources in hyperspectral imagery, IEEE Transactions on Geoscience and Remote Sensing42(3): 608-619.
4.
Diamantaras, K.I. and Kung, S.Y. (1996). Principal component neural networks: Theory and applications, New York, NY: John Wiley & Sons, Inc.
5.
Dremmel, J.E. (1997). Applied numerical linear algebra, Philadelphia, PA: Society for Industrial and Applied Mathematics.
6.
Du, Q. and Fowler, J.E. (2007). Hyperspectral image compression using JPEG2000 and principal component analysis, IEEE Geoscience and Remote Sensing Letters4(2): 201- 205.
7.
Fleury, M., Self, R.P., and Downton, A.C. (2004). Development of a fine-grained parallel Karhunen-Loève transform, Journal of Parallel and Distributed Computing64(4): 520-535.
8.
Fowler, J.E. and Rucker, J.T. (2007). 3D wavelet-based compression of hyperspectral imagery, In Hyperspectral data exploitation: Theory and applications , edited by C.-I Chang, Chapter 14, pp. 379-407. Hoboken, NJ: John Wiley & Sons, Inc .
9.
Haykin, S. (1999). Neural networks: A comprehensive foundation, 2nd edition, Upper Saddle River, NJ: Prentice Hall.
10.
Hirai, Y. and Nishizawa, K. (2000). Hardware implementation of a PCA learning network by an asynchronous PDM digital circuit. In Proceedings of the International Joint Conference on Neural Networks, Vol. 2, Como, Italy, pp. 65- 70.
11.
Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components, Journal of Educational Psychology24(6): 417-441.
12.
ISO/IEC ( 2004). Information technology - JPEG 2000 image coding system - Part 2: Extensions, ISO/IEC 15444-2.
13.
Kim, B.-J., Xiong, Z., and Pearlman, W.A. (2000). Low bitrate scalable video coding with 3-D set partitioning in hierarchical trees (3-D SPIHT), IEEE Transactions on Circuits and Systems for Video Technology10(8): 1374- 1387.
14.
Kulkarni, P., Bilgin, A., Marcellin, M.W., Dagher, J.C., Kasner, J.H., Flohr, T.J., and Rountree, J.C. (2006). Compression of earth science data with JPEG2000 . In Hyperspectral Image Compression, edited by G. Motta, F. Rizzo , and J. A. Storer, Chapter 12, pp. 347-378. New York: Springer.
15.
Kumar, A.P., Kamakoti, V., and Das, S. (2007). System-on-programmable-chip implementation for on-line face recognition, Pattern Recognition Letters28(3): 342-349.
16.
Makhoul, J., Roucos, S., and Gish, H. (1985). Vector quantization in speech coding, Proceedings of the IEEE73(11): 1551-1588.
17.
Murahashi, Y., Hotta, H., Doki, S., and Okuma, S. (2004). Pulsed neural networks based on delta-sigma modulation suitable for hardware implementation. In Proceedings of the International Joint Conference on Neural Networks, Vol. 4, Budapest, Hungary, pp. 2607-2612.
18.
Pearlman, W.A., Islam, A., Nagaraj, N., and Said, A. (2004). Efficient, low-complexity image coding with a set-partitioning embedded block coder, IEEE Transactions on Circuits and Systems for Video Technology14(11): 1219- 1235.
19.
Penna, B., Tillo, T., Magli, E., and Olmo, G. (2006a). A new low complexity KLT for lossy hyperspectral data compression. In Proceedings of the International Geoscience and Remote Sensing Symposium, Vol. 7, Denver, CO, pp. 3525-3528.
20.
Penna, B., Tillo, T., Magli, E., and Olmo, G. (2006b). Progressive 3-D coding of hyperspectral images based on JPEG 2000, IEEE Geoscience and Remote Sensing Letters3(1): 125-129.
21.
Pickering, M.R. and Ryan, M.J. (2006). An architecture for the compression of hyperspectral imagery. In Hyperspectral Image Compression, edited by G. Motta, F. Rizzo, and J. A. Storer, Chapter 1, pp. 1-34. New York: Springer.
22.
Prasanna, C.S.S., Sudha, N., and Kamakoti, V. (2005). A principal component neural network-based face recognition system and its ASIC implementation. In Proceedings of 18th International Conference on VLSI Design, Kolkata, India, pp. 795-798.
23.
Reed, I.S. and Yu, X. (1990). Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution, IEEE Transactions on Acoustics, Speech, and Signal Processing38(10): 1760-1770.
24.
Rucker, J.T., Fowler, J.E., and Younan, N.H. (2005). JPEG2000 coding strategies for hyperspectral data . In Proceedings of the International Geoscience and Remote Sensing Symposium, Vol. 1, Seoul, South Korea, pp. 128- 131.
25.
Said, A. and Pearlman, W.A. (1996). A new, fast, and efficient image codec based on set partitioning in hierarchical trees, IEEE Transactions on Circuits and Systems for Video Technology6(3): 243-250.
26.
Sanger, T.D. (1989). Optimal unsupervised learning in a single-layer linear feedforward neural network, Neural Networks2(6): 459-473.
27.
Schreiber, R. (1986). Solving eigenvalue and singular value problems on an undersized systolic array, SIAM Journal on Scientific and Statistical Computing7(2): 441-451.
28.
Subramanian, S., Gat, N., Ratcliff, A., and Eismann, M. (2000). Real-time hyperspectral data compression using principal components transformation. In Proceedings of the AVIRIS Earth Science & Applications Workshop, Pasadena, CA.
29.
Tang, X. and Pearlman, W.A. (2005). Scalable hyperspectral image coding. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Vol. 2, Philadelphia, PA, pp. 401-404.
30.
Taubman, D.S. and Marcellin, M.W. (2002). JPEG2000: Image compression fundamentals, standards and practice, Boston, MA: Kluwer Academic Publishers.
31.
Zhu, W. (2007). On the performance of JPEG2000 and principal component analysis in hyperspectral image compression, Master's thesis, Mississippi State University.
