激光与光电子学进展, 2017, 54 (5): 051005, 网络出版: 2017-05-03   

各向异性全变分引导滤波及其Split Bregman方法 下载: 733次

Anisotropic Total Variation Guided Filtering and Its Split Bregman Algorithm
作者单位
河南理工大学计算机科学与技术学院, 河南 焦作 454000
摘要
引导滤波(GF)去噪的关键是选取一幅包含清晰结构信息的引导图像。为提高GF的去噪效果, 提出一种由各向异性全变分(ATV)引导的滤波方法。首先利用ATV模型对噪声图像进行光滑处理, 生成包含良好结构信息的引导图像, 然后利用GF进行处理。为提高算法的稳健性, 对上述过程进行迭代处理。由于计算全变分模型的传统迭代方法速度较慢, 因此采用Split Bregman迭代方法进行加速处理。实验结果表明:该算法不仅在峰值信噪比、归一化均方误差和结构相似性等客观指标上具有优势, 而且计算速度比传统迭代方法提高了约30倍。该算法可以较好地快速去除噪声, 并能较好地保持图像中的结构和边缘特征等细节信息。
Abstract
An ideal guided image with good structure is the key to guided filtering (GF) denoising. In order to improve the denoising effect of the GF, an anisotropic total variation (ATV) based on the GF is proposed. First, the noisy image is smoothed by the ATV model to obtain a good structure information image. Then the image is served as the guided image in the GF algorithm. And an iterative processing is used for improving the algorithm robustness. Considering that the traditional iterative method for the total variation model is time consuming, the Split Bregman iterative method is introduced to speed up the whole process. The experimental results indicate that the proposed method not only has certain advantages in peak signal noise ratio, normalized mean square error and structural similarity, but also increases the computation speed by nearly 30 times compared with the related traditional iterative method. It can effectively remove the noises while preserving more structure and edge details.
参考文献

[1] 杨永发, 李 琦. 双边滤波算法的太赫兹共焦扫描图像去噪应用[J]. 激光与光电子学进展, 2015, 52(12): 121101.

    Yang Yongfa, Li Qi. Application of bilateral filtering algorithm on terahertz confocal scanning image denoising[J]. Laser & Optoelectronics Progress, 2015, 52(12): 121101.

[2] He K M, Sun J, Tang X. Guided image filtering[J]. IEEE Transactions on Software Engineering, 2013, 35(6): 1397-1409.

[3] 王卫星, 肖 翔, 陈良琴. 结合最小滤波和引导滤波的暗原色去雾[J]. 光学 精密工程, 2015, 23(7): 2100-2108.

    Wang Weixing, Xiao Xiang, Chen Liangqin. Image dark channel prior haze removal based on minimum filtering and guidedfiltering[J]. Optics and Precision Engineering, 2015, 23(7): 2100-2108.

[4] 肖创柏, 赵宏宇, 禹 晶. 基于引导滤波的Retinex快速夜间彩色图像增强技术[J]. 北京工业大学报, 2013, 39(12): 1868-1873.

    Xiao Chuangbo, Zhao Hongyu, Yu Jing. Rapid retinex algorithm for night color image enhancement based on guided filtering[J]. Journal of Beijing University of Technology, 2013, 39(12): 1868-1873.

[5] 高陈强, 陈 佩. 引导滤波和三维块匹配结合的红外图像去噪[J]. 重庆邮电大学学报(自然科学版), 2016, 28(2): 150-155.

    Gao Chenqiang, Chen Pei. Infrared image denoising based on three-dimensional block matching[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science), 2016, 28(2): 150-155.

[6] 芦碧波, 王建龙, 郑艳梅. 全变分引导图像去噪[J]. 计算机工程与应用, 2016, 52(8): 207-210.

    Lu Bibo, Wang Jianlong, Zheng Yanmei. Total variation guided filtering method for image denoising[J]. Computer Engineering and Applications, 2016, 52(8): 207-210.

[7] Rudin L I, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms[J]. Physica D: Nonlinear Phenomena, 1992, 60(1-4): 259-268.

[8] 陈华松, 宋 旸, 张正军, 等. 基于各向异性总变分的运动模糊盲复原方法[J]. 光电子·激光, 2015, 26(6): 1206-1214.

    Chen Huasong, Song Yang, Zhang Zhengjun, et al. Motion blind deblurring method by using anisotropic total variation[J]. Journal of Optoelectronics·Laser, 2015, 26(6): 1206-1214.

[9] 白俊奇, 陈 钱. 基于各向异性扩散的红外图像噪声滤波算法[J]. 光学学报, 2008, 28(5): 866-869.

    Bai Junqi, Chen Qian. Algorithm for infrared image noise filtering based on anisotropic diffusion[J]. Acta Optica Sinica, 2008, 28(5): 866-869.

[10] Chen Z Q, Jin X, Li L, et al. A limited-angle CT reconstruction method based on anisotropic TV minimization[J]. Physics in Medicine and Biology, 2013, 58(7): 2119-2141.

[11] Goldstein T, Osher S.The Split Bregman method for L1-regularized problems[J]. Siam Journal on Imaging Sciences, 2009, 2(2): 323-343.

[12] 谢爱敏, 周光华, 冯象初. 一种基于Split Bregman方法的快速曲率驱动图像修补算法[J]. 激光与光电子学进展, 2010, 47(8): 081002.

    Xie Aimin, Zhou Guanghua, Feng Xiangchu. Image inpainting algorithm of curvature driven diffusions based on Split Bregman method[J]. Laser & Optoelectronics Progress, 2010, 47(8): 081002.

[13] Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining,inference and prediction[M]. California: Springer, 2001: 192-192.

[14] Bregman L M. The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming[J]. Ussr Computational Mathematics & Mathematical Physics, 1967, 7(3): 200-217.

[15] Wang Y, Yin W, Zhang Y. A fast algorithm for image deblurring with total variation regularization[R]. CAAM, 2007: 1-19.

[16] Vogel C R, Oman M E.Iterative methods for total variation denoising[J]. Siam Journal on Scientific Computing, 1997, 17(1): 227-238.

[17] 高露露, 刘建军, 任 鑫, 等. 基于结构相似度的全景相机立体像对图像质量评价[J]. 激光与光电子学进展, 2014, 51(7): 071004.

    Gao Lulu, Liu Jianjun, Ren Xin, et al. Image quality evaluation of panoramic camera steropair based on structural similarity[J]. Laser & Optoelectronics Progress, 2014, 51(7): 071004.

[18] 逄浩辰, 朱 明, 郭立强. 彩色图像融合客观评价指标[J]. 光学 精密工程, 2013, 21(9): 2348-2353.

    Pang Haochen, Zhu Ming, Guo Liqiang. Objective color image fusion performance index[J]. Optics and Precision Engineering, 2013, 21(9): 2348-2353.

[19] 李珊珊, 王 琦, 冯兴乐. 基于亮度和对比度模型的图像融合质量评估标准[J]. 激光与光电子学进展, 2011, 48(6): 061001.

    Li Shanshan, Wang Qi, Feng Xingle. A novel quality metric based on luminance and contrast model for image fusion[J]. Laser & Optoelectronics Progress, 2011, 48(6): 061001.

[20] Chaudhury K N, Rithwik K. Image denoising using optimally weighted bilateral filters: a sure and fast approach[J]. International Conference on Image Processing, 2015: 108-112.

[21] Zhang M, Gunturk B K. Multiresolution bilateral filtering for image denoising[J]. IEEE Transactions on Image Processing, 2008, 17(12): 2324-2333.

芦碧波, 王乐蓉, 王永茂, 郑艳梅. 各向异性全变分引导滤波及其Split Bregman方法[J]. 激光与光电子学进展, 2017, 54(5): 051005. Lu Bibo, Wang Lerong, Wang Yongmao, Zheng Yanmei. Anisotropic Total Variation Guided Filtering and Its Split Bregman Algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(5): 051005.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!