Abstract
The total variation model proposed by Rudin, Osher and Fatemi for image denoising is considered to be one of the best denoising models. In this paper, we propose, analyze and test a dual based method to solve the total variation model. This method minimizes a quadratic function with separable constraints, and we make projections onto a feasible set so that it is easy to compute. Under some mild conditions, global convergence of the proposed method is established. The proposed approach could be easily implemented. Preliminary results are reported to demonstrate its performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Suppose that \(0<\tau <1/8\), then \(\frac{1}{\mu }\nabla \cdot w_k\) converges to \(\pi _{\frac{1}{\mu }\mathcal {K}}(-f)\) as \(k\rightarrow \infty \), where \(\pi _{\frac{1}{\mu }\mathcal {K}}(\cdot )\) is the orthogonal projection onto a convex set \(\frac{1}{\mu }\mathcal {K}\) with \(\mathcal {K}:=\{\nabla \cdot w: |w_{i,j} \le 1|, \forall i, j=1,2,\cdots ,n\}\).
- 2.
Some experiments show that a better convergence can be obtained when \(\tau =0.248\).
- 3.
References
Barzilai, J., Borwein, J.M.: Two point step size gradient methods. IMA J. Numer. Anal. 8, 141–148 (1998)
Birgin, E.G., Martinez, J.M., Raydan, M.: Nonmonotone spectral projected gradient methods on convex sets. SIAM J. Optim. 10, 1196–1211 (2000)
Carter, J.L.: Dual methods for total variation-based image restoration. Ph.D. thesis, University of California at Los Angeles (Advisor: T.F. Chan) (2001)
Chambolle, A.: An algorithm for total variation minimization and applications. J. Math. Imaging Vis. 20, 89–97 (2004)
Chambolle, A.: Total variation minimization and a class of binary mrf models. In: Rangarajan, A., Vemuri, B., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 136–152. Springer, Heidelberg (2005). doi:10.1007/11585978_10
Chan, T.F., Golub, G.H., Mulet, P.: A nonlinear primal-dual method for total variation-based image restoration. SIAM J. Sci. Comput. 20, 1964–1977 (1999). VPL
Dahl, J., Hansen, P.C., Jensen, S.H., Jensen, T.L.: Algorithms and software for total variation image reconstruction via first-order methods. Numer. Algorithms 53, 67–92 (2010)
Dai, Y.H., Fletcher, R.: Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming. Numer. Math. 100, 21–47 (2005)
Dai, Y.H., Liao, L.Z.: R-Linear Convergence of the Barzilai and Borwein gradient method. IMA J. Numer. Anal. 22, 1–10 (2002)
Ekeland, I., T\(\acute{e}\)mam, R.: Convex Analysis and Variational Problems: Classics in Applied Mathematics. SIAM, Philadelphia (1999)
Grippo, L., Lampariello, F., Lucidi, S.: A truncated Newton method with nonmonotone line search for unconstrained optimization. J. Optim. Theor. Appl. 60, 401–419 (1989)
Goldfarb, D., Yin, W.: Second-order cone programming methods for total variation-based image restoration. SIAM J. Sci. Comput. 27, 622–645 (2005)
Goldstein, T., Osher, S.: The Split Bregman method for L1 regularized problems. SIAM J. Imaging Sci. 2, 323–343 (2009)
Hintermuller, M., Stadler, G.: An infeasible primal-dual algorithm for tv-based infconvolution-type image restoration. SIAM J. Sci. Comput. 28, 1–23 (2006)
Nesterov, Y.: Smooth minimization of non-smooth functions. Math. Program. Ser. A 103, 127–152 (2005)
Raydan, M.: The Barzilai and Borwein gradient method for the large scale unconstrained minimization problem. SIAM J. Optim. 7, 26–33 (1997)
Rudin, L., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D Nonlinear Phenom. 60, 259–268 (1992)
Shi, Z.J., Shen, J.: New inexact line search method for unconstrained optimization. J. Optim. Theor. Appl. 127, 425–446 (2005)
Toint, P.L.: An assessment of non-monotone line search techniques for unconstrained optimization. SIAM J. Sci. Comput. 17, 725–739 (1996)
Vogel, C.R., Oman, M.E.: Iterative methods for total variation denoising. SIAM J. Sci. Comput. 17, 227–238 (1996)
Wu, C., Zhang, J., Tai, X.C.: Augmented Lagrangian method for total variation restoration with non-quadratic fidelity. UCLA CAM Report 09–82 (2009)
Xiao, Y.H., Song, H.N.: An inexact alternating directions algorithm for constrained total variation regularized compressive sensing problems. J. Math. Imaging Vis. 44, 114–127 (2012)
Yu, G.H.: Nonmonotone spectral gradient-type methods for large-scaleunconstrained optimization and nonlinear systems of equations. Pac. J. Optim. 7, 387–404 (2011)
Yu, G.H., Qi, L.Q., Dai, Y.H.: On nonmonotone chambolle gradient projection algorithms for total variation image restoration. J. Math. Imaging Vis. 35, 143–154 (2009)
Zhang, H.C., Hager, W.W.: A nonmonotone line search technique and its application to unconstrained optimization. SIAM J. Optim. 14, 1043–1056 (2004)
Zhou, B., Gao, L., Dai, Y.H.: Gradient methods with adaptive stepsizes. Comput. Optim. Appl. 35, 69–86 (2006)
Zhu, M., Chan, T.F.: An efficient primal-dual hybrid gradient algorithm for total variation image restoration. UCLA CAM Report 08–34 (2008)
Zhu, M.Q., Wright, S.J., Chan, T.F.: Duality-based algorithms for total-variation-regularized image restoration. Comput. Optim. Appl. 47, 377–400 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liao, Y., Hua, J., Xue, W. (2016). A Dual-Based Adaptive Gradient Method for TV Image Denoising. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds) Pattern Recognition. CCPR 2016. Communications in Computer and Information Science, vol 663. Springer, Singapore. https://doi.org/10.1007/978-981-10-3005-5_20
Download citation
DOI: https://doi.org/10.1007/978-981-10-3005-5_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3004-8
Online ISBN: 978-981-10-3005-5
eBook Packages: Computer ScienceComputer Science (R0)