非局部的变分正则化图像放大算法

doi:10.3724/SP.J.1087.2012.00725

计算机应用 ›› 2012, Vol. 32 ›› Issue (03): 725-728.DOI: 10.3724/SP.J.1087.2012.00725

非局部的变分正则化图像放大算法

姜东焕,徐光宝,东野长磊

山东科技大学信息科学与工程学院,山东青岛 266590

收稿日期:2011-08-12 修回日期:2011-11-21 发布日期:2012-03-01 出版日期:2012-03-01
通讯作者: 姜东焕
作者简介:姜东焕(1981-),女,山东聊城人,讲师,博士,主要研究方向:偏微分方程图像处理、小波分析;徐光宝(1980-),男,山东阳谷人,讲师,硕士,主要研究方向:图像处理、信息安全;东野长磊(1978-),男,山东平邑人,讲师,博士研究生,主要研究方向:图像处理、模式识别。
基金资助:
山东省自然科学基金资助项目(Y2008G11);山东省优秀中青年科学家科研奖励基金资助项目(BS2010DX026);山东省高等学校科技计划项目(J10LG24);山东科技大学春蕾计划项目(2009AZZ162)。

Variational image zooming based on nonlocal total variation

JIANG Dong-huan, XU Guang-bao, DONGYE Chang-lei

College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao Shandong 266590, China

Received:2011-08-12 Revised:2011-11-21 Online:2012-03-01 Published:2012-03-01
Contact: DongHuan Jiang

摘要/Abstract

摘要： 针对Chambolle图像放大模型存在分块效应,提出一种非局部的变分正则化图像放大算法。该算法的思想是构造一个适用于图像放大的变分泛函,该泛函由正则项和数据保真项构成,其中图像的正则项是用非局部全变差范数进行估计,进而用迭代投影方法求泛函的最小解,即为放大后的图像。与传统的图像插值方法不同,该算法是用变分的思想进行图像放大,非局部全变差的引入更使得该算法不只是利用图像的单个像素点,或某一邻域内的灰度和梯度信息进行放大,而是更大范围地利用了图像本身的信息,这将更有效地保留图像特征,避免了Chambolle方法在图像放大时出现的分块效应。实验结果表明,该算法能更好地保留边缘和细节信息,放大图像的清晰度比Chambolle图像放大方法和样条插值的效果要好。

关键词: 图像放大, 变分泛函, 非局部全变差

Abstract: A regularized image zooming model based on nonlocal total variation was proposed, with regard to that the Chambolle image zooming model has blocky effects. It consisted of regular term and fidelity term. The zoomed image was obtained by minimizing the variational function which used the nonlocal total variation norm to measure the regularity of the image. Unlike the traditional image zooming by interpolation, the variational model was incorporated in the new zooming algorithm and the use of nonlocal operator made the algorithm not just use a single pixel of the image, or gray and gradient information in a neighborhood to amplify, but use the information of image content itself widely that will avoid blocky effects of Chambolle's model. The experimental results show that the new algorithm can preserve better the border and details. It achieves better effect than Chambolle's method and the interpolation by using spline.

Key words: image zooming, variational function, nonlocal total variation

中图分类号:

姜东焕徐光宝东野长磊. 非局部的变分正则化图像放大算法[J]. 计算机应用, 2012, 32(03): 725-728.

JIANG Dong-huan XU Guang-bao DONGYE Chang-lei. Variational image zooming based on nonlocal total variation[J]. Journal of Computer Applications, 2012, 32(03): 725-728.

参考文献

[1]朱宁,吴静, 王忠谦.图像放大的偏微分方程方法[J].计算机辅助设计与图形学学报,2005,17(9):1941-1945.

[2]谢美华,王正明.基于边缘定向扩散的图像增强方法[J].光子学报,2005,34(9):1420-1424.

[3]GUICHARD F, MALGOUYRES F. Edge direction preserving image zooming: a mathematical and numerical analysis[J]. SIAM Journal of Numerical Analysis, 2001, 39(1): 1-37.

[4]CHAMBOLLE A. An algorithm for total variation minimization and applications[J]. Journal of Mathematical Imaging and Vision, 2004, 20(1/2): 89-97.

[5]石澄贤,吴建成,夏德深.各向异性扩散方程和一种图像放大方法[J].南京大学学报:数学半年刊,2005, 22(1): 153-160.

[6]郝彬彬,冯象初. 一种基于小波和矩阵型扩散的图像放大[J]. 光子学报, 2008,37(11):2365-2368.

[7]冯象初,姜东焕,徐光宝.基于变分和小波变换的图像放大算法[J].计算机学报,2008,31(2):340-345.

[8]JIANG DONG-HUAN, XU GUANG-BAO. Image zooming based on cartoon and texture decomposition [C]// International Conference on Information Systems and Computational Intelligence. Washington, DC: IEEE Computer Society, 2011:119-122.

[9]BAUDES A, COLL B, MOREL J M. A non-local algorithm for image denoising [C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2005: 60-65.

[10]BAUDES A, COLL B, MOREL J M. On image denoising method[J]. SIAM Multiscale Modeling and Simulation, 2005,4(2):490-530.

[11]SINGER A, SHKOLNISKY Y, NADLER B. Diffusion interpretation of non-local neighborhood filters for signal denoising[J]. SIAM Journal on Imaging Sciences, 2009, 2(1):118-139.

[12]GILBOA G, OSHER S. Nonlocal linear image regularization and supervised segmentation[J]. SIAM Multiscale Modeling and Simulation, 2007,6(2): 595-630.

[13]GILBOA G, OSHER S. Nonlocal operators with applications to image processing[J]. SIAM Multiscale Modeling and Simulation, 2008, 7(3):1005-1028.

[14]孙伟峰,彭玉华.一种改进的非局部平均去噪方法[J].电子学报, 2010, 38(4):923-928.

[15]徐大宏,王润生. 基于非局部正则化的图像去噪[J].计算机应用研究, 2009, 26(12): 4830-4832.

[16]王卫卫,韩雨,冯象初. 基于非局部扩散的图像去噪[J]. 光学学报, 2010,30(2):373-375.

[17]吴晓明, 陈斌, 阮波, 等. 基于非局部算法的序列图像超分辨率重构[J].计算机应用,2009, 29(1):95-96.

[18]GILBOA G, OSHER S. Nonlocal operators with applications to image processing[J]. SIAM Multiscale Modeling and Simulation, 2008, 7(3):1005-1028.

[19]GILBOA G, DARBON J, OSHER S, et al. Nonlocal convex functionals for image regularization[R]. [S.l.]:UCLA,2006.

非局部的变分正则化图像放大算法

Variational image zooming based on nonlocal total variation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	海涛, 张雷, 刘旭焱, 张新刚. 基于改进复扩散自适应耦合非局部变换域模型的图像放大[J]. 计算机应用, 2018, 38(4): 1151-1156.
[2]	海涛, 席志红. 各向异性四阶偏微分方程耦合二阶偏微分方程的图像放大[J]. 计算机应用, 2015, 35(4): 1084-1088.
[3]	张巍贺星霍颖翔滕少华滕毅李日贵. 基于并行运算的双层图像锐化方法[J]. 计算机应用, 2013, 33(08): 2325-2329.
[4]	袁野田中旭. 新的保持边缘的图像放大算法[J]. 计算机应用, 2012, 32(11): 3182-3184.
[5]	杨鹤猛黄战华. 基于梯度的快速图像插值算法[J]. 计算机应用, 2012, 32(10): 2821-2823.
[6]	孔繁庭刘俊华. 基于边界程度的图像插值算法[J]. 计算机应用, 2011, 31(06): 1585-1587.
[7]	冯杰飞韩慧健. 基于非均匀B样条插值算法的图像放大[J]. 计算机应用, 2010, 30(1): 82-84.
[8]	杨立志;顾耀林. 一种基于有理二次样条曲线的图像放大方法[J]. 计算机应用, 2006, 26(5): 1053-1054.