Second and higher order whitening image in reconstruction

• Autorzy: Bose N. K. , Srinivas U. , Culver R. L.

Warianty tytułu

PL

Metoda redukcji nadmiarowości w strumieniu danych sekwencji obrazów

• Języki publikacji: EN

Abstrakty

EN

In natural vision, the information in the natural environment, tends to be acquired with minimum redundancy for subsequent handling aldu to the technical problems aaid solutions encountered during the direct or indirect acquisition of compressed or decorrelated (whitened) multidimensional data, their transmission and processing. Considerable challenges are faced when the restrictions of Gausedanity in the signal and noise distributions, and linearity in processing are lifted. We improve recent results in vision research on the concept of higher order whitening of higher order statistics (HOS) based data. This is achieved by modifying the design of the falter and its inverse so that the processed image is of better quality than what is possible by direct implementation of a related scheme. Besides the modified higher order \vhitener and its complete analysis, the restriction of rotational symmetry in the power spectrum is eliminated in the two-dimensional derivation.

PL

Sekwencje obrazów zawierają w sposób naturalny dużo strukturalnych powiązań (korelacji), co wiąże się ze znaczną nadmiarowością zawartych w nich informacji. Dla szybkiego przetwarzania i transmisji danych cyfrowych o takich sekwencjach konieczna jest redukcja w nich tych zbytecznych nadmiarowości. W artykule została zaproponowana i dogłębnie przebadana metoda służąca temu celowi. Jest ona, jak pokazano, efektywna. Od strony teoretycznej bazuje na zaproponowanych ulepszeniach, w wielu aspektach, technik dotychczas stosowanych.

Słowa kluczowe

EN

whitening; higher-order whitening; power law for images

PL

metody redukcji nadmiarowości w strumieniu danych sekwencji obrazów

• Wydawca: Wydawnictwa Uczelniane Politechniki Bydgoskiej im. Jana i Jędrzeja Śniadeckich
• Czasopismo: Zeszyty Naukowe. Telekomunikacja i Elektronika / Uniwersytet Technologiczno-Przyrodniczy w Bydgoszczy
• Rocznik: 2009
• Tom: z. 12
• Strony: 21--42
• Opis fizyczny: Bibliogr. 19 poz.

Twórcy

autor

Bose N. K.

autor

Srinivas U.

autor

Culver R. L.

• Department of Electrical Engineering, The Pennsylvania State University University Park, PA 16802, USA,

Bibliografia

• [1] A. M. Monk, M. Davis, L. B. Milstein, and C. W. Helstrom, "A noise whitening approadi to multiple access noise rejection part I: theory and background;' IEEE Journal on Selected Areas in Communications, vol. 12, no. 5, Jime 1994,
• [2] J. J. Alick and A. N. Redlich, "What does the retina know about natural scenes?" Neural Computations, vol. 4, pp. 196-210, 1992.
• [3] S. Buzzi, B. Conte, A. D, Maio, and M, Lops, ''Optimum diversity detection over fading dispersive channels with non-Gaussian noise," IEEE Trans. Signal Process., vol. 49, 110. 4, pp. 767-776. April 2001.
• [4] H,-F. Clien, X.-R. Cao, H.-T, Fang, and J. Zhu, "Nonlinear adaptive blind whitening for MIMO channel," IEEE Trans. Signal Process., vol. 53, no. 8. pp. 2635-2647. August, 2005.
• [5] S. Buzzi, E. Conte. arid M. Lops, ''Optimum detection over Rayleigh-fading, dispersive channels. with non-Gaussian noise,1' IEEE Trans. Comm., vol. -15, no. 9, pp. 1001-1069, September 1997.
• [6] A. Hyvarinen, J. Karhunen, and E. Oja, Independent Component Analysis. Wiley Intersdenee, 2001 .
• [7] F. Vriiis and M. Yerleysen, "SWM: A claws of convex contrasts for source separation," in Proc. IEEE Int. Con/. Aco-usL, Speech, and Signal Process., Philadelphia, US, 2005,
• [8] R. M. Balboa, C. W. Tyler, and N. M. Grzywacz, "'Occlusions contribute to scaling in natural images," Vis-ion Research, vol. 4.1, pp. 955-964, 2001.
• [9] N. M. GrzywM-z. R. M. Balboa, and. C. W. Tyler, "A reply to a letter to the editor by Rudennan," Vision Research,, vol. 42; pp. 2803-2805, 2002,
• [10] D. L. Kuderman, "Origins of scaling in natural images," Vision Research. vol. 37, no. 23, pp. 3385-3398, 1907.
• [11] J. Gluckman, "Higher order wliitening of natural images,7' Proc. of the IEEE Conference on Computer V'-mon and Pattern Recognition., vol. 2, no. 12, pp. 354-360, -Time 2005.
• [12] B. OLdhausen. [Online]. Available: http;//redwood.berkeley,edu/bruno/npb261b/lab2/lab2.htinl
• [13] D. J. Field, "Relations between the statistics of natural images and. the response profiles of cortical cells," Journal of the Optical Society of America A. pp. 2379-2394, 1987.
• [14] L.-Z, Liao, S.-W. Luo, and M, Tian, "Whitenedfaces recognition with PCA mid ICA," IEEE Signal Processing Letters, vol. 14, no. 12, pp. 1008-1011, December 2007,
• [15] J. H. van Hat-eren and A. van der Scliaiif, "Iridopendent component filters of natural images compared with simple cells in primary visual cortex,'' Proc. of the Royal Statistical Society of London (B), vol. 205, pp. 359-366, 1998.
• [16] N. -3. W. Morris. S. Avid an, W. Matusik. and H. PfibMa:, ^Statistics of infrared images;' Proceedings of the. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2007.
• [17] A. vail der Schaaf arid J. H. van Hatereu, "Modelling the power spectra of natural images: statistics and information."' Vision Research-, vol. 36, pp. 2759-2770, 199G.
• [18] M. S. Langer, "Large-scale failures of / "a scaling in natural image spectra," Journal of the Optical Society of America A, \ol. 17, no. 1, pp. 28-33-, 2000.
• [19] N. K. Bose, U. Srinivas, and R.. L. Culver. "Wavelength diversity based infrared super-resolution and condition-based maintenance,'' Insight, vol. 50, no. 8, pp. 423-428, August 2008,