Abstract
In this paper a quasi-Newton projection method for image deblurring is presented. The image restoration problem is mathematically formulated as a nonnegatively constrained minimization problem where the objective function is the sum of the Kullback–Leibler divergence, used to express fidelity to the data in the presence of Poisson noise, and of a Tikhonov regularization term. The Hessian of the objective function is approximated so that the Newton system can be efficiently solved by using Fast Fourier Transforms. The numerical results show the potential of the proposed method both in terms of relative error reduction and computational efficiency.
Similar content being viewed by others
References
Anconelli, B., Bertero, M., Boccacci, P., Carbillet, M., Lanteri, H.: Iterative methods for the reconstruction of astronomical images with high dynamic range. J. Comput. Appl. Math. 198, 321–331 (2007)
Bardsley, J., N’djekornom, L.: Tikhonov regularized poisson likelihood estimation: theoretical justification and a computational method. Inverse Probl. Sci. Eng. 16(2), 199–215 (2008)
Bardsley, J., N’djekornom, L.: An analysis of regularization by diffusion for ill-posed poisson likelihood estimation. Inverse Probl. Sci. Eng. 17(4), 537–550 (2009)
Bardsley, J.M., Vogel, C.R.: A nonnegatively constrained convex programming method for image reconstruction. SIAM J. Sci. Comput. 25, 1326–1343 (2003)
Bertsekas, D.: Constrained Optimization and Lagrange Multiplier Methods. Academic, New York (1982)
Bertsekas, D.: Projected Newton methods for optimization problem with simple constraints. SIAM J. Control Optim. 20(2), 221–245 (1982)
Bertsekas, D.: Nonlinear Programming, 2nd ed. Athena Scientific, Belmont, Massachusetts (1999)
Conchello, J.A., McNally, J.G.: Fast regularization technique for expectation maximization algorithm for optical sectioning microscopy. Proc. SPIE 2655, 199–208 (1996)
Gafni, E.M., Bertsekas, D.P.: Two-metric projection methods for constrained optimization. SIAM J. Control. Optim. 22, 936–964 (1984)
Green, P.J.: Bayesian reconstructions from emission tomography data using a modified EM algorithm. IEEE Trans. Med. Imag. 9, 84–93 (1990)
Hanke, M., Nagy, J.G., Vogel, C.: Quasi Newton approach to nonnegative image restorations. Linear Algebra Appl. 316, 222–333 (2000)
Hansen, P.C., Nagy, J.G., O’Leary, D.P.: Deblurring images: matrices, spectra and filtering. SIAM, Philadelphia (2006)
Kelley, C.T.: Iterative Methods for Optimization. SIAM, Philadelphia (1999)
Landi, G., Loli Piccolomini, E.: A projected Newton-CG method for nonnegative astronomical image deblurring. Numer. Algorithms 48, 279–300 (2008)
Lant’eri, H., Roche, M., Aime, C.: Penalized maximum likelihood image restoration with positivity constraints: multiplicative algorithms. Inverse Probl. 18, 1397–1419 (2002)
Bertero, M, Boccacci, P., Desiderà, G., Vicidomini, G.: Image deblurring with Poisson data: from cells to galaxies. Inverse Probl. 25, 123006 (2009)
Lanteri, H., Bertero, M., Zanni, L.: Iterative image reconstruction: a point of view. In: Mathematical Methods in Biomedical Imaging and Intensity-Modulated Radiation Therapy (IMRT) (CRM Series, vol. 7), pp. 37–63 (2008)
Markham, J., Conchello, J.A.: Fast maximum-likelihood image-restoration algorithms for threedimensional fluorescence microscopy. J. Opt. Soc. Am. A 18, 1062–1071 (2001).
Nocedal, J., Wright, S.J.: Numerical Optimization. Springer, New York (1999)
Shepp, L.A., Vardi, Y.: Maximum likelihood reconstruction for emission tomography. IEEE Trans. Med. Imag. 1, 113–122 (1982)
Vogel, C.R.: Computational Methods for Inverse Problems. SIAM, Philadelphia (2002)
Vogel, C.R., Oman, M.E.: Fast, robust total variation–based reconstruction of noisy, blurred images. IEEE Trans. Image Process. 7, 813–824 (1998)
Wang, Z., Bovik, A.C.: Mean squared error: love it or leave it? IEEE Signal Process. Mag. 98, 98–117 (2009)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Landi, G., Loli Piccolomini, E. An improved Newton projection method for nonnegative deblurring of Poisson-corrupted images with Tikhonov regularization. Numer Algor 60, 169–188 (2012). https://doi.org/10.1007/s11075-011-9517-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11075-011-9517-y