Constrained and SNR-Based Solutions for TV-Hilbert Space Image Denoising
- 249 Downloads
We examine the general regularization model which is based on total-variation for the structural part and a Hilbert-space norm for the oscillatory part. This framework generalizes the Rudin-Osher-Fatemi and the Osher-Sole-Vese models and opens way for new denoising or decomposition methods with tunable norms, which are adapted to the nature of the noise or textures of the image. We give sufficient conditions and prove the convergence of an iterative numerical implementation, following Chambolle’s projection algorithm.
In this paper we focus on the denoising problem. In order to provide an automatic solution, a systematic method for choosing the weight between the energies is imperative. The classical method for selecting the weight parameter according to the noise variance is reformulated in a Hilbert space sense. Moreover, we generalize a recent study of Gilboa-Sochen-Zeevi where the weight parameter is selected such that the denoised result is close to optimal, in the SNR sense. A broader definition of SNR, which is frequency weighted, is formulated in the context of inner products. A necessary condition for maximal SNR is provided. Lower and upper bounds on the SNR performance of the classical and optimal strategies are established, under quite general assumptions.
Keywordsimage restoration BV H−1 hilbert space SNR projection total-variation denoising
Unable to display preview. Download preview PDF.
- 1.A. Almansa, V. Caselles, G. Haro, and B. Rouge, “Restoration and zoom of irregularly sampled, blurred and noisy images by accurate total variation minimization with local constraints,” accepted in SIAM Journal on Multiscale Modelling and Simulation.Google Scholar
- 3.G. Aubert and P. Kornprobst, “Mathematical Problems in Image Processing, Vol. 47, of Applied Mathematical Sciences,” Springer-Verlag, 2002.Google Scholar
- 6.J.F. Aujol and G. Gilboa, “Implementation and parameter selection for BV-Hilbert space regularizations,” UCLA CAM Report 04-66, ftp://ftp.math.ucla.edu/pub/camreport/cam04-66.pdf, 2004.
- 7.J.F. Aujol, G. Gilboa, T. Chan, and S. Osher, “Structure-texture decomposition by a TV-Gabor model,” In VLSM 05, 2005.Google Scholar
- 8.J.F. Aujol, G. Gilboa, T. Chan, and S. Osher, “Structure-texture image decomposition — modeling, algorithms, and parameter selection,” UCLA CAM Report 05-10, ftp://ftp.math.ucla.edu/pub/camreport/cam05-10.pdf, International Journal of Computer Vision, Vol. 67, No. 1, pp. 111–136, April 2006.
- 9.J. Bect, G. Aubert, L. Blanc-Féraud, and A. Chambolle, “A l 1 unified variational framwork for image restoration,” In ECCV 2004, May 2004.Google Scholar
- 11.J.L. Carter, “Dual methods for total variation-based image restoration,” PhD thesis, UCLA, Advisor: T.F. Chan, 2001.Google Scholar
- 14.T. Chan and S. Esedoglu, “Aspects of total variation regularized l 1 function approximation,” CAM report 04-07, to appear in SIAM Journal on Applied Mathematics, 2004.Google Scholar
- 16.P.G. Ciarlet, “Introduction à l’analyse numérique matricelle et à l’optimisation,” Mathématiques appliquées pour la maitrise. Masson, 1982.Google Scholar
- 20.P.L. Combettes and V. R. Wajs, “Signal recovery by proximal forward-backward splitting,” SIAM Journal on Multiscale Modeling and Simulation, Vol. 4, 2005.Google Scholar
- 22.Y. Dodge, “Statistical Data Analysis based on L1-norm and Related Methods,” North-Holland, Amsterdam, 1987.Google Scholar
- 25.G. Gilboa, N. Sochen, and Y.Y. Zeevi, “Estimation of optimal PDE-based denoising in the SNR sense,” To appear in IEEE Transactions on Image Processing, 2006.Google Scholar
- 26.G. Gilboa, N. Sochen, and Y.Y. Zeevi, “Variational denoising of partly-textured images by spatially varying constraints,” To appear in IEEE Transactions on Image Processing, 2006.Google Scholar
- 27.G. Gilboa, N. Sochen, and Y.Y. Zeevi, “Texture preserving variational denoising using an adaptive fidelity term,” In Proc. VLSM 2003, Nice, France, pp. 137–144, 2003.Google Scholar
- 28.G. Gilboa, N. Sochen, and Y.Y. Zeevi, “Estimation of optimal PDE-based denoising in the SNR sense,” CCIT report No. 499, Technion, August, see http://www.math.ucla.edu/∼gilboa/. 2004.
- 29.G. Gilboa, N. Sochen, and Y.Y. Zeevi, “Estimation of the optimal variational parameter via SNR analysis,” In Scale-Space, of Lecture Notes in Computer Science, Vol. 3459, pp. 230–241, April 2005.Google Scholar
- 30.A. Haddad and Y. Meyer, “Variational methods in image processing,” UCLA CAM report, 04-52, 2004.Google Scholar
- 31.J.B. Hiriart-Urruty and C. Lemarechal, “Convex Analysis ans Minimisation Algorithms I, of Grundlehren der mathematischen Wissenschaften,” Springer-Verlag, Vol. 305, 1993.Google Scholar
- 32.Yves Meyer, “Oscillating patterns in image processing and in some nonlinear evolution equations,” The Fifteenth Dean Jacquelines B. Lewis Memorial Lectures, March 2001.Google Scholar
- 35.A. Obereder, S. Osher, and O. Sherzer, “On the use of dual norms in bounded variation type regularization,” UCLA CAM report 04-35, 2004.Google Scholar
- 37.S. Osher and O. Sherzer, “G-norm properties of bounded variation regularization,” UCLA CAM report 04-23, 2004.Google Scholar
- 39.M. Navara P. Mrázek, “Selection of optimal stopping time for nonlinear diffusion filtering,” IJCV, Vol. 52, No. 2/3, pp. 189–203, 2003.Google Scholar
- 40.P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” PAMI, Vol. 12, No. 7, pp. 629–639, 1990.Google Scholar
- 41.T. Rockafellar, “Convex Analysis, of Grundlehren der mathematischen Wissenschaften,” Princeton University Press, second edition, Vol. 224, 1983.Google Scholar
- 42.L. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Physica D, Vol 60, pp. 259–268, 1992.Google Scholar
- 43.Alon Spira, Ron Kimmel, and Nir Sochen, “Efficient Beltrami flow using a short time kernel,” In Scale-Space, of Lecture Notes in Computer Science, Vol. 2695, pp. 511–522, January 2003.Google Scholar
- 45.A.N. Tikhnonv and V.Y. Arsenin, “Solutions of Ill-posed problems, W.H. Winston,” Washington D.C, 1977.Google Scholar
- 49.Wotao Yin, Donald Goldfarb, and Stanley Osher, “Total variation based image cartoon-texture decomposition,” UCLA CAM Report 05-27, 2005.Google Scholar