Open Access

Denoising by Sparse Approximation: Error Bounds Based on Rate-Distortion Theory

  • Alyson K Fletcher1,
  • Sundeep Rangan2,
  • Vivek K Goyal3 and
  • Kannan Ramchandran4
EURASIP Journal on Advances in Signal Processing20062006:026318

https://doi.org/10.1155/ASP/2006/26318

Received: 9 September 2004

Accepted: 30 June 2005

Published: 8 March 2006

Abstract

If a signal is known to have a sparse representation with respect to a frame, it can be estimated from a noise-corrupted observation by finding the best sparse approximation to . Removing noise in this manner depends on the frame efficiently representing the signal while it inefficiently represents the noise. The mean-squared error (MSE) of this denoising scheme and the probability that the estimate has the same sparsity pattern as the original signal are analyzed. First an MSE bound that depends on a new bound on approximating a Gaussian signal as a linear combination of elements of an overcomplete dictionary is given. Further analyses are for dictionaries generated randomly according to a spherically-symmetric distribution and signals expressible with single dictionary elements. Easily-computed approximations for the probability of selecting the correct dictionary element and the MSE are given. Asymptotic expressions reveal a critical input signal-to-noise ratio for signal recovery.

[123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354]

Authors’ Affiliations

(1)
Department of Electrical Engineering and Computer Sciences, University of California
(2)
Flarion Technologies Inc.
(3)
Department of Electrical Engineering and Computer Science and Research Laboratory of Electronics, Massachusetts Institute of Technology
(4)
Department of Electrical Engineering and Computer Sciences, College of Engineering, University of California

References

  1. Duffin RJ, Schaeffer AC: A class of nonharmonic Fourier series. Transactions of the American Mathematical Society March 1952, 72: 341-366. 10.1090/S0002-9947-1952-0047179-6MathSciNetView ArticleMATHGoogle Scholar
  2. Daubechies I: Ten Lectures on Wavelets. SIAM, Philadelphia, Pa, USA; 1992.View ArticleMATHGoogle Scholar
  3. Demmel JW: Applied Numerical Linear Algebra. SIAM, Philadelphia, Pa, USA; 1997.View ArticleMATHGoogle Scholar
  4. Donoho DL, Vetterli M, DeVore RA, Daubechies I: Data compression and harmonic analysis. IEEE Transactions on Information Theory 1998, 44(6):2435-2476. 10.1109/18.720544MathSciNetView ArticleMATHGoogle Scholar
  5. Gorodnitsky IF, Rao BD: Sparse signal reconstruction from limited data using FOCUSS: A re-weighted minimum norm algorithm. IEEE Transactions on Signal Processing 1997, 45(3):600-616. 10.1109/78.558475View ArticleGoogle Scholar
  6. Malioutov D, Çetin M, Willsky AS: A sparse signal reconstruction perspective for source localization with sensor arrays. IEEE Transactions on Signal Processing 2005, 53(8, Part 2):3010-3022.MathSciNetView ArticleGoogle Scholar
  7. Donoho DL, Elad M, Temlyakov V: Stable recovery of sparse overcomplete representations in the presence of noise. IEEE Transactions on Information Theory 2006, 52(1):6-18.MathSciNetView ArticleMATHGoogle Scholar
  8. Elad M, Bruckstein AM: A generalized uncertainty principle and sparse representation in pairs of bases. IEEE Transactions on Information Theory 2002, 48(9):2558-2567. 10.1109/TIT.2002.801410MathSciNetView ArticleMATHGoogle Scholar
  9. Donoho DL, Elad M:Optimally sparse representation in general (nonorthogonal) dictionaries via minimization. Proceedings of the National Academy of Sciences 2003, 100(5):2197-2202. 10.1073/pnas.0437847100MathSciNetView ArticleMATHGoogle Scholar
  10. Gribonval R, Nielsen M: Sparse representations in unions of bases. IEEE Transactions on Information Theory 2003, 49(12):3320-3325. 10.1109/TIT.2003.820031MathSciNetView ArticleMATHGoogle Scholar
  11. Fuchs J-J: On sparse representations in arbitrary redundant bases. IEEE Transactions on Information Theory 2004, 50(6):1341-1344. 10.1109/TIT.2004.828141View ArticleMathSciNetMATHGoogle Scholar
  12. Tropp JA: Greed is good: Algorithmic results for sparse approximation. IEEE Transactions on Information Theory 2004, 50(10):2231-2242. 10.1109/TIT.2004.834793MathSciNetView ArticleMATHGoogle Scholar
  13. Donoho DL, Elad M: On the stability of basis pursuit in the presence of noise. submitted to EURASIP Journal on Applied Signal Processing, October 2004MATHGoogle Scholar
  14. Tropp JA: Just relax: Convex programming methods for subset selection and sparse approximation. In ICES Report 0404. University of Texas at Austin, Austin, Tex, USA; February 2004.Google Scholar
  15. Candès EJ, Romberg J, Tao T: Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on Information Theory 2006, 52(2):489-509.View ArticleMathSciNetMATHGoogle Scholar
  16. Candès EJ, Tao T: Near optimal signal recovery from random projections: Universal encoding strategies? submitted to IEEE Transactions on Information Theory, October 2004Google Scholar
  17. Candès EJ, Romberg J, Tao T: Stable signal recovery from incomplete and inaccurate measurements. In Comput. & Appl. Math. Report 05-12. University of California, Los Angeles, Calif, USA; March 2005.Google Scholar
  18. Fletcher AK, Ramchandran K: Estimation error bounds for frame denoising. Wavelets: Applications in Signal and Image Processing X, August 2003, San Diego, Calif, USA, Proceedings of SPIE 5207: 40-46.Google Scholar
  19. Fletcher AK, Rangan S, Goyal VK, Ramchandran K: Denoising by sparse approximation: Error bounds based on rate-distortion theory. In Electron. Res. Lab. Memo M05/5. University of California, Berkeley, Calif, USA; September 2004.Google Scholar
  20. Fletcher AK: Estimation via sparse approximation: Error bounds and random frame analysis, M.A. thesis. University of California, Berkeley, Calif, USA; May 2005.Google Scholar
  21. Elad M, Zibulevsky M: A probabilistic study of the average performance of basis pursuit. sumitted to in IEEE Transactions on Information Theory, December 2004Google Scholar
  22. Cohen A, D'Ales J-P: Nonlinear approximation of random functions. SIAM Journal on Applied Mathematics 1997, 57(2):518-540. 10.1137/S0036139994279153MathSciNetView ArticleMATHGoogle Scholar
  23. DeVore RA: Nonlinear approximation. Acta Numerica 1998, 7: 51-150.MathSciNetView ArticleMATHGoogle Scholar
  24. Goodwin MM: Adaptive Signal Models: Theory, Algorithms, and Audio Applications. Kluwer Academic, Boston, Mass, USA; 1998.View ArticleGoogle Scholar
  25. Engan K, Aase SO, Husoy JH: Designing frames for matching pursuit algorithms. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '98), May 1998, Seattle, Wash, USA 3: 1817-1820.Google Scholar
  26. Tropp JA, Dhillon IS, Heath RW Jr., Strohmer T: Designing structured tight frames via an alternating projection method. IEEE Transactions on Information Theory 2005, 51(1):188-209.MathSciNetView ArticleMATHGoogle Scholar
  27. Davis G: Adaptive nonlinear approximations, M.S. thesis. New York University, New York, NY, USA; September 1994.Google Scholar
  28. Natarajan BK: Sparse approximate solutions to linear systems. SIAM Journal on Computing 1995, 24(2):227-234. 10.1137/S0097539792240406MathSciNetView ArticleMATHGoogle Scholar
  29. Golub GH, Van Loan CF: Matrix Computations. 2nd edition. Johns Hopkins University Press, Baltimore, Md, USA; 1989.MATHGoogle Scholar
  30. Mallat SG, Zhang Z: Matching pursuits with time-frequency dictionaries. IEEE Transactions on Signal Processing 1993, 41(12):3397-3415. 10.1109/78.258082View ArticleMATHGoogle Scholar
  31. Chen SS, Donoho DL, Saunders MA: Atomic decomposition by basis pursuit. SIAM Review 2001, 43(1):129-159. 10.1137/S003614450037906XMathSciNetView ArticleMATHGoogle Scholar
  32. Gribonval R, Nielsen M: Highly sparse representations from dictionaries are unique and independent of the sparseness measure. In Tech. Rep. R-2003-16. Department of Mathematical Sciences, Aalborg University, Aalborg, Denmark; October 2003.Google Scholar
  33. Gribonval R, Vandergheynst P: On the exponential convergence of matching pursuits in quasi-incoherent dictionaries. In Tech. Rep. 1619. Institut de Recherche en Informatique et Systèmes Aléatoires, Rennes, France; April 2004.Google Scholar
  34. Gribonval R, Nielsen M:Beyond sparsity: Recovering structured representations by minimization and greedy algorithms—Application to the analysis of sparse underdetermined ICA. In Tech. Rep. 1684. Institut de Recherche en Informatique et Systèmes Aléatoires, Rennes, France; January 2005.Google Scholar
  35. Saito N: Simultaneous noise suppression and signal compression using a library of orthonormal bases and the minimum description length criterion. In Wavelets in Geophysics. Edited by: Foufoula-Georgiou E, Kumar P. Academic Press, San Diego, Calif, USA; 1994:299-324. chapter XIView ArticleGoogle Scholar
  36. Natarajan BK: Filtering random noise from deterministic signals via data compression. IEEE Transactions on Signal Processing 1995, 43(11):2595-2605. 10.1109/78.482110View ArticleGoogle Scholar
  37. Krim H, Tucker D, Mallat S, Donoho DL: On denoising and best signal representation. IEEE Transactions on Information Theory 1999, 45(7):2225-2238. 10.1109/18.796365MathSciNetView ArticleMATHGoogle Scholar
  38. Chang SG, Yu B, Vetterli M: Adaptive wavelet thresholding for image denoising and compression. IEEE Transactions on Image Processing 2000, 9(9):1532-1546. 10.1109/83.862633MathSciNetView ArticleMATHGoogle Scholar
  39. Liu J, Moulin P: Complexity-regularized image denoising. IEEE Transactions on Image Processing 2001, 10(6):841-851. 10.1109/83.923281MathSciNetView ArticleMATHGoogle Scholar
  40. Bergeaud F, Mallat S: Matching pursuit of images. Proceedings of International Conference on Image Processing (ICIP '95), October 1995, Washington, DC, USA 1: 53-56.View ArticleMATHGoogle Scholar
  41. Neff R, Zakhor A: Very low bit-rate video coding based on matching pursuits. IEEE Transactions on Circuits and Systems for Video Technology 1997, 7(1):158-171. 10.1109/76.554427View ArticleGoogle Scholar
  42. Goyal VK, Vetterli M, Thao NT:Quantized overcomplete expansions in : Analysis, synthesis, and algorithms. IEEE Transactions on Information Theory 1998, 44(1):16-31. 10.1109/18.650985MathSciNetView ArticleMATHGoogle Scholar
  43. Al-Shaykh OK, Miloslavsky E, Nomura T, Neff R, Zakhor A: Video compression using matching pursuits. IEEE Transactions on Circuits and Systems for Video Technology 1999, 9(1):123-143. 10.1109/76.744280View ArticleGoogle Scholar
  44. Moschetti F, Granai L, Vandergheynst P, Frossard P: New dictionary and fast atom searching method for matching pursuit representation of displaced frame difference. Proceedings of International Conference on Image Processing (ICIP '02), September 2002, Rochester, NY, USA 3: 685-688.Google Scholar
  45. Conway JH, Hardin RH, Sloane NJA: Packing lines, planes, etc.: Packings in Grassmannian spaces. Experimental Mathematics 1996, 5(2):139-159.MathSciNetView ArticleMATHGoogle Scholar
  46. Strohmer T, Heath RW Jr.: Grassmannian frames with applications to coding and communication. Applied and Computational Harmonic Analysis 2003, 14(3):257-275. 10.1016/S1063-5203(03)00023-XMathSciNetView ArticleMATHGoogle Scholar
  47. Sloane NJA, Hardin RH, Smith WD, et al.: A library of putatively optimal spherical codes, together with other arrangements which may not be optimal but are especially interesting for some reason. http://www.research.att.com/~njas/packings
  48. Gallager RG: Information Theory and Reliable Communication. John Wiley & Sons, New York, NY, USA; 1968.MATHGoogle Scholar
  49. Andrews GE, Askey R, Roy R: Special Functions, Encyclopedia of Mathematics and Its Applications. Volume 71. Cambridge University Press, Cambridge, Mass, USA; 1999.Google Scholar
  50. Berger T: Rate Distortion Theory: A Mathematical Basis for Data Compression, Information and System Sciences Series. Prentice-Hall, Englewood Cliffs, NJ, USA; 1971.Google Scholar
  51. Cover TM, Thomas JA: Elements of Information Theory. John Wiley & Sons, New York, NY, USA; 1991.View ArticleMATHGoogle Scholar
  52. Gray RM: Source Coding Theory. Kluwer Academic, Boston, Mass, USA; 1990.MATHGoogle Scholar
  53. Grimmett GR, Stirzaker DR: Probability and Random Processes. 2nd edition. Oxford University Press, Oxford, UK; 1992.MATHGoogle Scholar
  54. Conway JH, Hardin RH, Sloane NJA: Packing lines, planes, etc.: Packings in Grassmannian spaces. Experimental Mathematics 1997, 6(2):175. editors' noteMathSciNetView ArticleMATHGoogle Scholar

Copyright

© Alyson K. Fletcher et al. 2006

This article is published under license to BioMed Central Ltd. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.