[1]张俊峰,罗立民,舒华忠,等.基于先验信息的全变分图像复原算法[J].东南大学学报(自然科学版),2016,46(6):1132-1136.[doi:10.3969/j.issn.1001-0505.2016.06.004]
 Zhang Junfeng,Luo Limin,Shu Huazhong,et al.Total variation image restoration algorithm based on prior information[J].Journal of Southeast University (Natural Science Edition),2016,46(6):1132-1136.[doi:10.3969/j.issn.1001-0505.2016.06.004]
点击复制

基于先验信息的全变分图像复原算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
46
期数:
2016年第6期
页码:
1132-1136
栏目:
计算机科学与工程
出版日期:
2016-11-20

文章信息/Info

Title:
Total variation image restoration algorithm based on prior information
作者:
张俊峰罗立民舒华忠伍家松
东南大学计算机科学与工程学院, 南京210096; 东南大学计算机网络和信息集成教育部重点实验室, 南京211189; 东南大学中法生物医学信息研究中心, 南京210096
Author(s):
Zhang Junfeng Luo Limin Shu Huazhong Wu Jiasong
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China
Key Laboratory of Computer Network and Information Integration of Ministry of Education, Southeast University, Nanjing 211189, China
Centre de Recherche en Information Biomédicale Sino-Francais, Southeast University, Nanjing 210096, China
关键词:
图像复原 先验信息 全变分 非局部均值 分裂Bregman
Keywords:
image restoration prior information total variation nonlocal mean split Bregman
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2016.06.004
摘要:
为了提高全变分模型的图像复原效果,提出一种基于先验信息的全变分图像复原算法.首先,采用能够有效保护滤波后图像结构信息的非局部均值算法对模糊退化图像进行滤波以减少其中所含噪声,获取滤波后的先验图像信息.然后,构建基于该先验信息的全变分图像复原模型,该模型不仅保留了全变分模型对复原图像边界信息的保护优势,也保留了非局部均值的结构信息保护优势.最后,采用分裂 Bregman交替方向乘子迭代算法对所提模型进行优化,得到复原后的图像.实验结果表明,无论从主观视觉效果方面,还是从峰值信噪比与结构相似性客观量化指标方面对所复原图像进行评价, 与其他算法相比,所提算法均能取得较好的复原效果.
Abstract:
In order to improve the performance of image restoration of the total variation(TV)model, an improved TV image restoration algorithm based on prior information is proposed. First, the nonlocal means(NLM)filtering algorithm, which can effectively protect the structural information of the filtered image, is employed to reduce the noise within the image to restore. Thus, the filtered prior image information is obtained. Then, an improved total variation restoration model based on the obtained prior information is established. The proposed model can not only maintain the TV model’ advantage of protecting the boundary information of restorated image, but also maintain the NLM model’ advantage of protecting the structure information. Finally, the proposed model is optimized by the split Bregman alternating direction multiplier iteration algorithm and the restored image is obtained. The experimental results show that compared with other algorithms, the proposed algorithm achieves better restoration effect in terms of the subjective visual effect and the objective quantitative indices such as peak signal to noise ratio(PSNR)and structural similarity(SSIM).

参考文献/References:

[1] Sonka M, Hlavac V, Boyle R. Image processing, analysis, and machine vision [M]. 4th ed. Stanford, CA, USA: Cengage Learning, 2014:161-165.
[2] Averbuch A, Neittaanmäki P, Zheludev V. Periodic spline-based frames for image restoration [J]. Inverse Problems and Imaging, 2015, 9(3): 661-707.
[3] Huang C, Ding X, Fang C, et al. Robust image restoration via adaptive low-rank approximation and joint kernel regression [J]. IEEE Transactions on Image Processing, 2014, 23(12): 5284-5297. DOI:10.1109/TIP.2014.2363734.
[4] Dong W, Zhang L, Shi G, et al. Nonlocally centralized sparse representation for image restoration [J]. IEEE Transactions on Image Processing, 2013, 22(4): 1620-1630. DOI:10.1109/TIP.2012.2235847.
[5] Rudin L I, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms [J]. Physica D, 1992, 60(1): 259-268. DOI:10.1016/0167-2789(92)90242-f.
[6] Beck A, Teboulle M. Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems [J]. IEEE Transactions on Image Processing, 2009, 18(11): 2419-2434. DOI:10.1109/TIP.2009.2028250.
[7] Liu X. Weighted total generalised variation scheme for image restoration [J]. IET Image Processing, 2016, 10(1): 80-88. DOI:10.1049/iet-ipr.2015.0013.[8] Lü X G, Song Y Z, Wang S X, et al. Image restoration with a high-order total variation minimization method[J]. Applied Mathematical Modelling, 2013, 37(16): 8210-8224. DOI:10.1016/j.apm.2013.03.028.
[9] Buades A, Coll B, Morel J M. A review of image denoising algorithms, with a new one [J]. Multiscale Modeling & Simulation, 2005, 4(2): 490-530. DOI:10.1137/040616024.
[10] Lou Y, Zhang X, Osher S, et al. Image recovery via nonlocal operators [J]. Journal of Scientific Computing,2010, 42(2): 185-197. DOI:10.1007/s10915-009-9320-2.
[11] Chen H, Wang C, Song Y, et al. Split Bregmanized anisotropic total variation model for image deblurring [J]. Journal of Visual Communication and Image Representation, 2015, 31: 282-293. DOI:10.1016/j.jvcir.2015.07.004.
[12] Chambolle A, De Vore R A, Lee N Y, et al. Nonlinear wavelet image processing: Variational problems, compression, and noise removal through wavelet shrinkage [J]. IEEE Transactions on Image Processing, 1998, 7(3): 319-335. DOI:10.1109/83.661182.
[13] Gonzalez R C, Woods R E, Eddins S L. Digital image processing using Matlab [M]. Bergen County, NJ, USA: Pearson Education, 2004:141-193.
[14] Hansen P C, Nagy J G, O’Leary D P. Deblurring images: Matrices, spectra, and filtering [M]. Philadelphia, PA, USA: Society for Industrial and Applied Mathematics, 2006:21-29.

备注/Memo

备注/Memo:
收稿日期: 2016-04-05.
作者简介: 张俊峰(1985—),男,博士生;罗立民(联系人),男,博士,教授,博士生导师, luo.list@seu.edu.cn.
基金项目: 国家重点基础研究发展计划(973计划)资助项目(2010CB732503)、国家自然科学基金资助项目(61201344).
引用本文: 张俊峰,罗立民,舒华忠,等.基于先验信息的全变分图像复原算法[J].东南大学学报(自然科学版),2016,46(6):1132-1136. DOI:10.3969/j.issn.1001-0505.2016.06.004.
更新日期/Last Update: 2016-11-20