Sparsity regularized image super-resolution model via forward-backward operator splitting method

被引：1
作者：
Sun Y.-B. [1 ,2 ]
Fei X. [1 ]
Wei Z.-H. [1 ]
Xiao L. [1 ]
机构：
[1] Department of Pattern Recognition and Artificial Intelligence, School of Computer Science and Technology, Nanjing University of Science and Technology
[2] Laboratory of Three Dimensional Simulation, 60th Research Institute of General Staff Department, Chinese People's Liberation Army
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2010年 / 36卷 / 09期
关键词：
Forward-backward splitting; Proximal operator; Sparse representation; Super-resolution; Threshold shrinkage;
D O I：
10.3724/SP.J.1004.2010.01232
中图分类号：
学科分类号：
摘要：
A convex variational model is proposed for multi-frame image super-resolution with sparse representation regularization. The regularization term constrains the underlying image to have a sparse representation in a proper frame. The fidelity term restricts the consistency with the measured image in terms of the data degradation model. The characters of the optimal solution to the model are analyzed. Furthermore, a fixed-point numerical iteration algorithm is proposed to solve this convex variational problem based on the proximal forward-backward splitting method for monotone operator. At every iteration, the forward (explicit) gradient step for the fidelity term and the backward (implicit) step for regularization term are activated separately, thus complexity is decreased rapidly. The convergence of the numerical algorithm is studied and a continuation strategy is exploited to accelerate the convergence speed. Numerical results for optics and infrared images are presented to demonstrate that our super-resolution model and numerical algorithm are both effective. Copyright © 2010 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：1232 / 1238
页数：6
相关论文
共 13 条
  • [1] Ng M.K., Bose N.K., Mathematical analysis of super-resolution methodology, IEEE Signal Processing Magazine, 20, 3, pp. 62-74, (2003)
  • [2] Rudin L.I., Osher S., Fatemi E., Nonlinear total variation based noise removal algorithms, Physica D: Nonlinear Phenomena, 60, 1-4, pp. 259-268, (1992)
  • [3] Capel D., Zisserman A., Super-resolution enhancement of text image sequences, Proceedings of the 15th International Conference on Pattern Recognition, pp. 600-605, (2000)
  • [4] Ng M.K., Shen H.F., Lam E.Y., Zhang L.P., A total variation regularization based super-resolution reconstruction algorithm for digital video, EURASIP Journal on Applied in Signal Processing, 2007, pp. 1-16, (2007)
  • [5] Protter M., Elad M., Image sequence denoising via sparse and redundant representations, IEEE Transactions on Image Processing, 18, 1, pp. 27-35, (2009)
  • [6] Chaux C., Combettes P.L., Pesquet J.C., Wajs V.R., A variational formulation for frame-based inverse problems, Inverse Problems, 23, 6, pp. 1495-1518, (2007)
  • [7] Lian Q.-S., Chen S.-Z., Image reconstruction for compressed sensing based on the combined sparse image representation, Acta Automatica Sinica, 36, 3, pp. 385-391, (2010)
  • [8] Combettes P.L., Wajs V.R., Signal recovery by proximal forward-backward splitting, Multiscale Modeling and Simulation, 4, 4, pp. 1168-1200, (2006)
  • [9] Candcs E.J., Donoho D.L., New tight frames of curvelets and optimal representation of objects with piecewise C<sup>2</sup> singularities, Communications on Pure and Applied Mathematics, 57, 2, pp. 219-266, (2004)
  • [10] Elad M., Hel-Or Y., A fast super-resolution reconstruction algorithm for pure translational motion and common spaceimvariant blur, IEEE Transactions on Image Processing, 10, 8, pp. 1187-1193, (2001)
12