非凸混合总变分图像盲复原

doi:10.3969/j.issn.1001-2400.2016.02.021

Abstract

Abstract:

A multi-regularization constraint method for imageblind restoration is proposed to recover the blurry-noisy images.First, the non-convex total variation is adoptedas the regularization constraint by taking the sparse edges in the natural image into consideration. Next, the high-order total variation is used to overcome the staircase effects in the smooth regions of the image. Then a non-convex minimization model is proposed. Finally, the augmented Lagrangian method and a new generalized p shrinkage operator are applied to solve the model. The results of numerical experiments show that the proposed method can preserve the image edges while removing the staircase effects effectively. The high quality restored image can be obtained.

Key words: image restoration, non-convex, high-order, total variation, augmented Lagrangian method, p shrinkage operator；optimization

LIU Qiaohong;LI Bin;LIN Min. Non-convex hybrid total variation method for image blind restoration[J].Journal of Xidian University, 2016, 43(2): 120-125.

References

［1］ RUDIN L I, OSHER S, FATEMI E. Nonlinear Total Variation Based Noise Removal Algorithms［J］. Physica D,1992, 60(1/4): 259-268.
［2］ CHAN T F, WONG C K. Total Variation Blind Deconvolution［J］. IEEE Transactions on Image Processing, 1998, 7(3): 370-375.
［3］ CHAMBOLLE A, LIONS P. Image Recovery via Total Variation Minimization Andrelatedproblems ［J］. Numerische Mathematik, 1997, 76(2): 167-188.
［4］ LYSAKER M, TAI X C. Iterative Image Restoration Combining Total Variation Minimizationand a Second-order Functional［J］. International Journal of Computer Vision, 2006, 66(1): 5-18.
［5］ PAPAFITSOROS K, SCHONLIEB C B. A Combined First and Second Order Variational Approach for Image Reconstruction［J］. Journal of Mathematical Imaging and Vision, 2014, 48(2): 308-338.
［6］ KRISHNAN D, FERGUS R. Fast Image Deconvolution Using Hyper-Laplacian Priors［C］//Advances in Neural Information Processing Systems. New York: Curran Associates Incorporated, 2009: 1033-1041.
［7］ NIKOLOVAM, NG M K, TAM C P. Fast Nonconvex Nonsmooth Minimizationmethods for Image Restoration and Reconstruction［J］. IEEE Transactions on Image Processing, 2010,19(12): 3073-3088.
［8］张文娟, 冯象初. 利用平衡方法的非凸图像修复［J］. 西安电子科技大学学报, 2014, 41(5): 141-147.
ZHANG Wenjuan, FENG Xiangchu. Nonconvex Image Inpainting via Balanced Regularization Approach［J］. Journal of Xidian University, 2014, 41(5): 141-147.
［9］ CHARTRAND R. Nonconvex Splitting for Regularized Low-Rank+Sparsedecomposition［J］. IEEE Transactions on Signal Processing, 2012, 60(11): 5810-5819.
［10］张文娟, 冯象初. 非凸低秩稀疏约束的图像超像素分割方法［J］. 西安电子科技大学学报, 2013, 40(5): 86-91.
ZHANG Wenjuan, FENG Xiangchu. Image Super-pixels Segmentation Method Based on the Non-convex Low-rank and Sparse Constraints［J］. Journal of Xidian University, 2013, 40(5): 86-91.
［11］ SHAN Q, JIA J, AGARWALA A. High-quality Motion Deblurring from a Single Image［J］. ACM Transactions on Graphics, 2008, 27(3): 73.
［12］ KRISHNAN D, TAY T, FERGUS R. Blind Deconvolution Using a Normalized Sparsity Measure［C］//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2011: 233-240.
［13］ XU L, JIA J Y. Two-phase Kernel Estimation for Robust Motion Deblurring［C］//Lecture Notes in Computer Science: 6311 LNCS. Heidelberg: Springer Verlag, 2010: 157-170.

[1]	LIU Xiaoxuan,ZHANG Yuming,JI Qingzhou,CAO Tianjiao. Design and realization of a high-precision and low temperature drift reference circuit [J]. Journal of Xidian University, 2019, 46(2): 41-46.
[2]	XIAO Song, CHEN Hui, NI Mengyu, NI Liuliu, ZHANG Jiajia. Algorithm for near-field source localization using the minimum redundant symmetric array [J]. Journal of Xidian University, 2018, 45(6): 123-129.
[3]	SUN Yue;FENG Xiangchu;LI Xiaoping;ZHANG Rui. Augmented Lagrangian bonding block model for contact problems [J]. Journal of Xidian University, 2017, 44(4): 34-39.
[4]	WANG Shuzhen;XIE Kun;LI Li;ZHANG Jingang. Improved RLTV algorithm used to radio image reconstruction [J]. Journal of Xidian University, 2017, 44(3): 72-76.
[5]	YANG Siyan;CAO Wencan;LI Shiping. Second-order graph model ant and colony optimization based image matching [J]. Journal of Xidian University, 2017, 44(1): 159-164.
[6]	LV Qian;SU Tao;WU Kai;ZHANG Jiancheng. ISAR imaging algorithm for targets with the complex motion based on the high-order ambiguity function-Lv's distribution [J]. Journal of Xidian University, 2016, 43(5): 24-30.
[7]	FENG Xiangchu;WANG Siqi;LI Xiaoping. Low-rank and dual approximation method for image inpainting problems [J]. Journal of Xidian University, 2016, 43(4): 172-177.
[8]	HUO Leigang;FENG Xiangchu;WANG Xudong;HUO Chunlei. Higherorder singular value decomposition- and total variation- regularized multiplicative noise removal model [J]. Journal of Xidian University, 2016, 43(3): 78-84.
[9]	WANG Yong;FENG Tangzhi;CHEN Chuchu;QIAO Qianqian;YANG Xiaoyu;WANG Guodong. Adaptive sparse representation and total variation constraint based image reconstruction [J]. J4, 2016, 43(1): 12-17+109.
[10]	LI Zhenyu;YANG Jun;LIANG Yi;XING Mengdao. New method for azimuth-dependent correction of highly squint missile-borne SAR subaperture imaging [J]. J4, 2015, 42(4): 88-94+197.
[11]	KUANG Tao;HUANG Liyu;ZHONG Yufang;LI Chao. Improved compressive sensing algorithm for CT image reconstruction with incomplete projection data [J]. J4, 2015, 42(4): 95-99+113.
[12]	WU Wei;ZHENG Chenglin;ZHANG Yingying;ZHOU Shouhuan. Image super-resolution using generalized nonlocal mean and self-similarity [J]. J4, 2014, 41(4): 100-107.
[13]	LI Quanhe;ZHA Yufei;XIONG Lei;BI Duyan. Novel method for haze degraded image scene rendition [J]. J4, 2013, 40(5): 99-106.
[14]	ZHANG Wenjuan;FENG Xiangchu. Image super-pixels segmentation method based on the non-convex low-rank and sparse constraints [J]. J4, 2013, 40(5): 86-91.
[15]	BAI Jian;FENG Xiangchu. Model based on the integro-differential equation for multiplicative noise removal [J]. J4, 2013, 40(3): 132-138.

Non-convex hybrid total variation method for image blind restoration

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 10