基于图像分割的非局部均值去噪算法

doi:10.11772/j.issn.1001-9081.2017.07.2078

计算机应用 ›› 2017, Vol. 37 ›› Issue (7): 2078-2083.DOI: 10.11772/j.issn.1001-9081.2017.07.2078

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于图像分割的非局部均值去噪算法

徐苏^1,2, 周颖玥^1,2

1. 西南科技大学信息工程学院, 四川绵阳 621010;
2. 特殊环境机器人技术四川省重点实验室(西南科技大学), 四川绵阳 621010

收稿日期:2016-12-19 修回日期:2017-03-08 出版日期:2017-07-10 发布日期:2017-07-18
通讯作者: 徐苏
作者简介:徐苏(1983-),女,四川绵阳人,讲师,博士,主要研究方向:图像处理与分析、模式识别、深度学习;周颖玥(1983-),女,四川马尔康人,副研究员,博士,主要研究方向:图像处理与分析、深度学习。
基金资助:
国家自然科学基金资助项目（61401379）；西南科技大学博士基金资助项目（11zx7134）。

Non-local means denoising algorithm based on image segmentation

XU Su^1,2, ZHOU Yingyue^1,2

1. School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China;
2. State Key Laboratory of Robot Technology Used for Special Environment(Southwest University of Science and Technology), Mianyang Sichuan 621010, China

Received:2016-12-19 Revised:2017-03-08 Online:2017-07-10 Published:2017-07-18
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61401379), the Doctoral Fund of Southwest University of Science and Technology (11zx7134).

摘要/Abstract

摘要： 针对传统非局部均值（NLM）算法的滤波参数非自适应及去噪后边缘易模糊的缺点，提出一种基于图像分割的非局部均值去噪算法。该算法分为两个阶段：第一阶段根据噪声大小及图像纹理自适应确定滤波参数的值，并采用传统非局部均值算法得到去噪结果图；第二阶段根据像素点方差的不同，将该去噪结果图分为细节区域和背景区域，再对属于不同区域的图像块分别去噪，同时为了更有效地去除噪声，还采用了反向投影的方式，充分利用了第一阶段方法噪声中残留的结构信息。实验结果表明，与传统非局部均值算法及其三种改进算法相比，所提算法的峰值信噪比（PSNR）及结构相似性（SSIM）更高，纹理细节和边缘结构更完整，图像更清晰，本真信息保留更完整。

关键词: 图像去噪, 非局部均值, 图像分割, 噪声标准差, 相似性度量

Abstract: Focusing on the problems of non-adaption of filtering parameters and edge blur of Non-Local Means (NLM) algorithm, an improved NLM denoising algorithm based on image segmentation was proposed. The proposed algorithm is composed of two phases. In the first phase, the filtering parameter was determined according to the noise level and image structure, and traditional NLM algorithm was used to remove the noise and generate the rough clean image. In the second phase, the estimated clean image was divided into detailed region and background region based on pixel variance, and the image patches belonged to different regions were denoised separately. To effectively remove the noise, the back projection was utilized to make full use of the residual structure from the method noise of the first phase. The experimental results show that compared with traditional NLM and three NLM-improved algorithms, the proposed algorithm achieves higher Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM), while maintaining more structure details and edges, making the denoised image clear and retaining the complete real information.

Key words: image denoising, Non-Local Mean (NLM), image segmentation, noise standard deviation, similarity measurement

中图分类号:

TP391.413

徐苏, 周颖玥. 基于图像分割的非局部均值去噪算法[J]. 计算机应用, 2017, 37(7): 2078-2083.

XU Su, ZHOU Yingyue. Non-local means denoising algorithm based on image segmentation[J]. Journal of Computer Applications, 2017, 37(7): 2078-2083.

参考文献

[1] LEVIN A, NADLER B. Natural image denoising:optimality and inherent bounds[C]//CVPR 2011:Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2011:2833-2840.
[2] BUADES A, COLL B, MOREL J M. A review of image denoising algorithms, with a new one[J]. Multiscale Modeling and Simulation, 2005, 4(2):490-530.
[3] CHAUDHURY K N, SINGER A. Non-local Euclidean medians[J]. IEEE Signal Processing Letters, 2012, 19(11):745-748.
[4] 黄智,付兴武,刘万军.混合相似性权重的非局部均值去噪算法[J].计算机应用,2016,36(2):556-562.(HUANG Z, FU X W, LIU W J. Non-local means denoising algorithm with hybrid similarity weight[J]. Journal of Computer Applications, 2016, 36(2):556-562.)
[5] 蔡斌,刘卫,郑重,等.一种改进的非局部均值去噪算法[J].模式识别与人工智能,2016,29(1):1-10.(CAI B, LIU W, ZHENG Z, et al. An improved non-local means denoising algorithm[J]. Pattern Recognition and Artificial Intelligence, 2016, 29(1):1-10.)
[6] 许光宇,檀结庆.带结构检测的非局部均值图像去噪算法[J].计算机应用,2011,31(3):749-752.(XU G Y, TAN J Q. Enhanced non-local means image denoising algorithm using structure detection[J]. Journal of Computer Applications, 2011, 31(3):749-752.)
[7] GAN K, TAN J, HE L. Non-local means image denoising algorithm based on edge detection[C]//ICDH 2014:Proceedings of the 2014 International Conference on Digital Home. Piscataway, NJ:IEEE, 2014:117-121.
[8] LAN R, ZHOU Y, TANG Y Y, et al. Image denoising using non-local fuzzy means[C]//China SIP 2015:Proceedings of the 2015 IEEE China Summit and International Conference on Signal and Information Processing. Piscataway, NJ:IEEE, 2015:196-200.
[9] 李新春,于抒平,王波.一种改进的非局部均值算法[J].计算机工程与应用,2016,52(5):185-189.(LI X C, YU S P, WANG B. Improved non-local means algorithm[J]. Computer Engineering and Applications, 2016, 52(5):185-189.
[10] HEMALATE B, SUBHASIS C. Novel speed-up strategies for non-local means denoising with patch and edge patch based dictionaries[J]. IEEE Transactions on Image Processing, 2014, 23(1):356-365.
[11] WU Y, TRACEY B, NATARAJAN P, et al. Probabilistic non-local means[J]. IEEE Signal Processing Letters, 2013, 20(8):763-766.
[12] LI H, SUEN C Y. A novel Non-local means image denoising method based on grey theory[J]. Pattern Recognition, 2015, 49:237-248.
[13] DELEDALLE C A, DUVAL V, SALMON J. Non-local Methods with Shape-Adaptive Patches (NLM-SAP)[J]. Journal of Mathematical Imaging and Vision, 2012, 43(2):103-120.
[14] DONG W, ZHANG L, SHI G, et al. Nonlocal back-projection for adaptive image enlargement[C]//ICIP 2009:Proceedings of the 2009 IEEE International Conference on Image Processing. Piscataway, NJ:IEEE, 2009:349-352.
[15] 李彦丽,金东瀚,焦秉立.几种典型的感知视频质量评价模型[J].计算机工程与应用,2002,38(13):66-68.(LI Y L, JIN D H, JIAO B L. Several typical perceptual video quality assessment models[J]. Computer Engineering and Applications, 2002, 38(13):66-68.)
[16] RAMPONI G. A rational edge-preserving smoother[C]//ICIP 1995:Proceedings of the 1995 IEEE International Conference on Image Processing. Piscataway, NJ:IEEE, 1995:151-154.
[17] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[18] SALMON J. On two parameters for denoising with non-local means[J]. IEEE Signal Processing Letters, 2010, 17(3):269-272.
[19] VAN DE VILLE D, KOCHER M. SURE-based non-local means[J]. IEEE Signal Processing Letters, 2009, 16(11):973-976.

基于图像分割的非局部均值去噪算法

Non-local means denoising algorithm based on image segmentation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[2]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[3]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.
[4]	杨蒙蒙, 张爱华. 基于灰度共生矩阵和同步正交匹配追踪的分形图像压缩[J]. 计算机应用, 2021, 41(5): 1445-1449.
[5]	罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183.
[6]	董阳, 潘海为, 崔倩娜, 边晓菲, 滕腾, 王邦菊. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054.
[7]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[8]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[9]	胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516.
[10]	周玉彬, 肖红, 王涛, 姜文超, 熊梦, 贺忠堂. 基于动作周期退化相似性度量的机械轴健康指标构建与剩余寿命预测[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3192-3199.
[11]	原泉, 王艳, 李玉先. 距离保持水平集演化模型的快速实现算法[J]. 计算机应用, 2020, 40(9): 2743-2747.
[12]	高海军, 曾祥银, 潘大志, 郑伯川. 基于U-Net改进模型的直肠肿瘤分割方法[J]. 计算机应用, 2020, 40(8): 2392-2397.
[13]	吴崇数, 林霖, 薛蕴菁, 时鹏. 基于自监督学习的病理图像层次分割[J]. 计算机应用, 2020, 40(6): 1856-1862.
[14]	曾招鑫, 刘俊. 基于深度学习的秀丽隐杆线虫显微图像分割方法[J]. 计算机应用, 2020, 40(5): 1453-1459.
[15]	张一飞, 李新福, 田学东. 基于图像分割的立体匹配算法[J]. 计算机应用, 2020, 40(5): 1415-1420.