Abstract
Image restoration is an ill-posed problem that requires regularization to solve. Many existing regularization terms in the literature are the convex function. However, nonconvex nonsmooth regularization has advantages over convex regularization for restoring images, but its practical interest used to be limited by the difficulty of the computational stage which requires a nonconvex nonsmooth minimization. In this paper, an adaptive nonconvex nonsmooth regularization is proposed for image restoration by using the spatial information indicator. Moreover, an efficient numerical algorithm for solving the resulting minimization problem is provided by applying the variable splitting and the penalty techniques. Finally, its advantages are shown in deblurring edges and restoring fines of image simultaneously in experiments.
Similar content being viewed by others
References
J.F. Cai, H. Ji, C.Q. Liu, Z.W. Shen, Framelet-based blind motion deblurring from a single image. IEEE Trans. Image Process. 21, 562–572 (2012)
J.F. Cai, S. Osher, Z. Shen, Linearized Bregman iterations for frame-based image deblurring. SIAM J. Imag. Sci. 2, 226–252 (2009)
P. Campisi, K. Egiazarian (eds.), Blind image deconvolution: theory and applications (CRC, Boca Raton, 2007)
R.A. Carmona, S.F. Zhong, Adaptive smoothing respecting feature directions. IEEE Trans. Image Process. 7, 353–358 (1998)
D.Q. Chen, L.Z. Cheng, Alternative minimisation algorithm for non-local total variational image deblurring. IET Image Process. 4, 353–364 (2010)
X.J. Chen, M.K. Ng, C. Zhang, Non-Lipschitz \(l^p\)-regularization and box constrained model for image restoration. IEEE Trans. Image Process. 21, 4709–4721 (2012)
H.Z. Fang, L.X. Yan, H. Liu, Y. Chang, Blind Poissonian images deconvolution with framelet regularization. Opt. Lett. 38, 389–391 (2013)
R. Fergus, B. Singh, A. Hertzmann, S.T. Roweis, W.T. Freeman, Removing camera shake from a single photograph. Proc. ACM SIGGRAPH 25, 787–794 (2006)
S. Fu, Q. Ruan, W. Wang, F. Gao, H. Cheng, A feature-dependent fuzzy bidirectional flow for adaptive image sharpening. Neurocomputing 70, 883–895 (2007)
S. Fu, C. Zhang, Adaptive non-convex total variation regularisation for image restoration. Electron. Lett. 46, 907–908 (2010)
G.H. Golub, P.C. Hansen, D.P. O’Leary, Tikhonov regularization and total least squares. SIAM J. Matrix Anal. 21, 185–194 (1999)
T. Goldstein, S. Osher, The split bregman method for L1 regularized problems. SIAM J. Imag. Sci. 2, 323–343 (2009)
H.Y. Hong, L.C. Li, I.K. Park, T.X. Zhang, Universal deblurring method for real images using transition region. Opt. Eng. 51, 047006 (2012)
H.Y. Hong, L.C. Li, T.X. Zhang, Blind restoration of real turbulence-degraded image with complicated backgrounds using anisotropic regularization. Opt. Commun. 285, 4977–4986 (2012)
H.Y. Hong, T.X. Zhang, Fast restoration approach for rotational motion blurred image based on deconvolution along the blurring paths. Opt. Eng. 42, 3471–3486 (2003)
H.Y. Hong, T.X. Zhang, G.L. Yu, Regularized restoration algorithm of astronautcal turbulence-degraded images using maximum-likelihood estimation. J. Infrared Millim. W. 2, 130–134 (2005)
Y. Huang, M.K. Ng, Y. Wen, A fast total variation minimization method for image restoration. SIAM J. Multiscale Model. Sim. 7, 774–795 (2008)
N. Joshi, R. Szeliski, D.J. Kriegman, PSF estimation using sharp edge prediction, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8, 2008
D. Krishnan, T. Tay, R. Fergus, Blind deconvolution using a normalized sparsity measure, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 233–240, 2011
A. Levin, Y. Weiss, F. Durand, W.T. Freeman, Understanding and evaluating blind deconvolution algorithms, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1964–1971, 2009
A. Liu, W. Lin, M. Narwaria, Image quality assessment based on gradient similarity. IEEE Trans. Image Process. 21, 1500–1512 (2012)
Y.F. Lou, X.Q. Zhang, S. Osher, A. Bertozzi, Image recovery via nonlocal operators. J. Sci. Comput. 42, 185–197 (2009)
C.W. Lu, Image restoration and decomposition using non-convex non-smooth regularisation and negative Hilbert–Sobolev norm. IET Image Process. 6, 706–716 (2012)
M. Nikolova, M.K. Ng, C.P. Tam, Fast non-convex non-smooth minimization methods for image restoration and reconstruction. IEEE Trans. Image Process. 19, 3073–3088 (2010)
M. Nikolova, M.K. Ng, C.P. Tam, On \(l^1\) data fitting and concave regularization for image recovery. SIAM J. Sci. Comput. 35, 397–430 (2013)
M. Nikolova, M.K. Ng, S. Zhang, W.K. Ching, Efficient reconstruction of piecewise constant images using nonsmooth nonconvex minimization. SIAM J. Imaging Sci. 1, 2–25 (2008)
J. Nocedal, S. Wright, Numer. Opt. (Springer, New York, 2006)
L. Rudin, S. Osher, E. Fatemi, Total variation based image restoration with free local constraints, in The 1th IEEE International Conference on Image Processing, Austin, USA, pp. 31–35, 1994
Q. Shan, J.Y. Jia, A. Agarwala, High-quality motion deblurring from a single image. Proc. ACM SIGGRAPH 25, 1–10 (2008)
Y.Y. Shi, Q.S. Chang, New time dependent model for image restoration. Appl. Math. Comput. 179, 121–134 (2006)
H.Y. Tian, H.M. Cai, J.H. Lai, X.Y. Xu, Effective image noise removal based on difference eigenvalue, in The 18th IEEE International Conference on Image Processing, pp. 3357–3360, 2011
A.N. Tikhonov, V.Y. Arsenin, Solutions of Ill-Posed Problems (Wiley, New York, 1977)
J. Weickert, Anisotropic Diffusion in Image Processing (B. G. Teubner, Stuttgart, 1998)
Z. Wang, A. Bovik, Mean squared error: love it or leave it?—a new look at signal fidelity measures. IEEE Signal Process. Mag. 26, 98–117 (2009)
Z. Wang, A. Bovik, H. Sheikh, Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600–612 (2004)
L.X. Yan, H.Z. Fang, S. Zhong, Blind image deconvolution with spatially adaptive total variation regularization. Opt. Lett. 37, 2778–2780 (2012)
L.X. Yan, M.Z. Jin, H.Z. Fang, H. Liu, T.X. Zhang, Atmospheric-turbulence- degraded astronomical image restoration by minimizing second-order central moment. IEEE Geosci. Remote Sens. Lett. 9, 672–676 (2012)
T.X. Zhang, Automated Recognition of Imaged Targets (Hubei Science and Technology, Wuhan, 2003)
X.Q. Zhang, M. Burger, X. Bresson, S. Osher, Bregmanized nonlocal regularization for deconvolution and sparse reconstruction. SIAM J. Imag. Sci. 3, 253–276 (2010)
Z.Y. Zuo, X. Lan, G. Zhou, X. Liu, A time dependent model via non-local operator for image restoration, in The 7th International Conference on Intelligent Systems and Knowledge Engineering, 2012
Z.Y. Zuo, L. Liu, J. Hu, X. Lan, Adaptive non-convex non-smooth regularization for image restoration based on spatial information, in The 6th international Congress on Image and Signal Processing, 2013
Z.Y. Zuo, T.X. Zhang, X. Lan, L.X. Yan, An adaptive non-local total variation blind deconvolution employing split Bregman iteration. Circ. Syst. Signal Process. 32, 2407–2421 (2013)
Acknowledgments
The authors would like to thank the editors and the anonymous reviewers for their valuable suggestions. We also would like to thank Anmin Liu, Houzhang Fang, and Professor Mila Nikolova for supplying the Matlab implementation of their algorithm. This work was supported by the Project of the key National Natural Science Foundation of China under Grant No. 60736010, No. 60902060, No. 61227007, Innovation Research Fund Committee of HUST (2011QN073), and Innovation Fund of CASC (CASC 201104).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zuo, Z., Yang, W., Lan, X. et al. Adaptive Nonconvex Nonsmooth Regularization for Image Restoration Based on Spatial Information. Circuits Syst Signal Process 33, 2549–2564 (2014). https://doi.org/10.1007/s00034-014-9760-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-014-9760-2