Blurred Image Restoration Method Based on Second-order Total Generalized Variation Regularization
-
摘要: 针对图像去模糊问题, 采用二阶广义全变差作为修复图像的正则项构建恢复模型, 并针对重建模型的高阶与非光滑特性, 给出了基于分裂Bregman 迭代的快速算法. 实验结果表明, 该模型和数值算法能够较好地恢复被噪声和模糊污染的图像, 同时可以很好地保留图像的纹理和细节信息.
-
关键词:
- 二阶广义全变差 /
- 图像恢复 /
- 去模糊 /
- 分裂Bregman迭代
Abstract: For the blurred image restoration problem, we adopt the second-order total generalized variation as the regularization term to construct an image restoration model. For the high order and non-smooth feature of the restoration model, a fast algorithm based on the split Bregman iterative algorithm is also proposed. Experimental results show that the model and the numerical algorithm can effectively restore the images polluted by noise and blur, and they can preserve image texture and details effectively. -
[1] Lucy B. An iterative technique for the rectification of observed distributions. Astronomical Journal, 1974, 79(6): 745-754 [2] [2] Richardson W H. Bayesian-based iterative method of image restoration. Journal of the Optical Society of America, 1972, 62(1): 55-59 [3] [3] Krishnan D, Fergus R. Fast image deconvolution using hyper-Laplacian priors. In: Proceedings of the 2009 Advances in Neural Information Processing Systems. Vancouver, British Columbia: Curran Associates, Inc., 2009. 1033- 1041 [4] [4] Galatsanos N P, Katsaggelos A K. Methods for choosing the regularization parameter and estimating the noise variance in image restoration and their relation. IEEE Transactions on Image Processing, 1992, 1(3): 322-336 [5] [5] Wang W L, Yang J F, Yin W T, Zhang Y. A new alternating minimization algorithm for total variation image reconstruction. SIAM Journal on Imaging Sciences, 2008, 1(3): 248- 272 [6] [6] Babacan S D, Molina R, Katsaggelos A K. Variational Bayesian blind deconvolution using a total variation prior. IEEE Transactions on Image Processing, 2009, 18(1): 12- 26 [7] He Chuan, Hu Chang-Hua, Zhang Wei, Shi Biao. Box-constrained total-variation image restoration with automatic parameter estimation. Acta Automatica Sinica, 2014, 40(8): 1804-1811(何川, 胡昌华, 张伟, 师彪. 区间约束的全变差图像复原和自动参数估计. 自动化学报, 2014, 40(8): 1804-1811) [8] [8] Bioucas-Dias J M. Bayesian wavelet-based image deconvolution: a GEM algorithm exploiting a class of heavy-tailed priors. IEEE Transactions on Image Processing, 2006, 15(4): 937-951 [9] [9] Zhang H, Zhang Y N. Sparse representation based iterative incremental image deblurring. In: Proceedings of the 16th IEEE International Conference on Image Processing (ICIP). Cairo, Egypt: IEEE, 2009. 1293-1296 [10] Rudin L, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Physica D, 1992, 60(1-4): 259- 268 [11] Kristian B, Karl K, Thomas P. Total generalized variation. SIAM Journal on Imaging Sciences, 2010, 3(3): 492-526 [12] Knoll1 F, Bredies K, Pock T, Stollberger R. Second order total generalized variation (TGV) for MRI. Magnetic Resonance in Medicine, 2011, 65(2): 480-491 [13] Yin W T, Osher S, Goldfarb D, Darbon J. Bregman iterative algorithms for l1-minimization with applications to compressed sensing. SIAM Journal on Imaging Sciences, 2008, 1(1): 143-168 [14] Goldstein T, Osher S. The split Bregman method for L1-regularized problems. SIAM Journal on Imaging Sciences, 2009, 2(2): 323-343 [15] Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202 [16] Puig A T, Wiesel A, Fleury G, Hero A O. Multidimensional shrinkage-thresholding operator and group LASSO penalties. IEEE Signal Processing Letters, 2011, 18(6): 363-366 [17] Oliveira J P, Bioucas-Dias J M, Figueiredo M A T. Adaptive total variation image deblurring: a majorization-minimization approach. Signal Processing, 2009, 89(9): 1683-1693
点击查看大图
计量
- 文章访问数: 2379
- HTML全文浏览量: 105
- PDF下载量: 1589
- 被引次数: 0