基于Demons算法改进的图像去噪模型研究

周先春; 汪美玲; 周林锋; 吴琴

doi:10.7498/aps.64.024205

摘要

在Demons算法的基础上, 将扩散过程看作图像配准, 建立一种新的基于图像配准的Demons 去噪模型. 实验表明, 该模型去噪效果优于经典的Perona-Malik模型, 排除了模型的病态性. 考虑到新模型在图像去噪过程中仅靠梯度信息表示图像的局部特征还不完善, 故将水平集曲率作为控制图像结构的驱动力因素引入到此模型中, 提出了一种新的梯度和曲率双重驱动力的图像去噪模型. 分析和仿真结果表明, 两种新模型都可有效抑制噪声, 清晰度也有明显的提高, 其中双重驱动力的图像去噪模型去噪效果更具优越性.

关键词:

Abstract

According to image registration, we build a new Demons model of image denoising, in which the diffusion access is regarded as image registration. The experimental results indicate that the performance of the model is better than that of the Perona-Malik model: the ill-condition of the model is removed. It is not enough to describe local characteristics only by using the gradient information in the access of image denoising, so a level set curvature which is the driving force of image structure controlling is introduced into the denoising model. Therefore we propose a new model of image denoising based on two driving forces of gradient and curvature. The simulation results show that the two improved models can both suppress noise effectively, their definitions are enhanced obviously, the performance of image denoising model of two driving forces is more greatly improved.

Keywords:

作者及机构信息

1.
南京信息工程大学电子与信息工程学院, 南京 210044;

2.
南京信息工程大学气象传感网技术工程中心, 南京 210044;

3.
南京信息工程大学, 江苏省气象探测与信息处理重点实验室, 南京 210044

基金项目: 国家自然科学基金(批准号: 11202106, 61302188)、教育部高等学校博士学科点专项科研基金(批准号: 20123228120005)、江苏省“信息与通信工程”优势学科建设项目、江苏省自然科学基金(批准号: BK20131005)和江苏省高校自然科学研究项目(批准号: 13KJB170016)资助的课题.

Authors and contacts

1.
College of Electronic and Information Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China;

2.
Jiangsu Technology and Engineering Center for Meteorological Sensor Network, Nanjing University of Information Science and Technology, Nanjing 210044, China;

3.
Jiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing 210044, China

Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11202106, 61302188), the Specialized Research Fund for the Doctoral Program of Higher Education, China (Grant No. 20123228120005), the Jiangsu Information and Communication Engineering Preponderant Discipline Platform, China, the Natural Science Foundation of Jiangsu Province, China (Grant No. BK20131005), and the Natural Sciences Fundation from the Universities of Jiangsu Province of China (Grant No. 13KJB170016).

参考文献

[1]	Gonzalez R C, Woods R E (translated by Ruan Q Q, Ruan Y Z) 2010 Digital Image Processing (3rd Edition) (Beijing: Publishing House of Electronics Industry) pp197-213 (in Chinese) [冈萨雷斯R C, 伍兹 R E 著 (阮秋琦, 阮宇智译) 2010(第三版)数字图像处理(北京: 电子工业出版社) 第197–213页]
[2]	Liu P, Fang H, Li G Q, Liu Z W 2012 IEEE Geosci. Remote Sens. 9 358
[3]	Bumsub H, Dongbo M, Kwanghoon S 2013 IEEE Trans. Image Process. 22 1096
[4]	Sofou A, Evangelopoulos G, Maragos P 2005 IEEE Geosci. Remote Sens. 3 94
[5]	Li Z B, Liu Z Z, Shi W Z 2014 IEEE Geosci. Remote Sens. 11 743
[6]	Shi L F, Mo J Q 2013 Acta Phys. Sin. 62 040203 (in Chinese) [石兰芳, 莫嘉琪 2013 62 040203]
[7]	Zhou X C, Lin W T, Lin Y H, Mo J Q 2012 Acta Phys. Sin. 61 240202 (in Chinese) [周先春, 林万涛, 林一骅, 莫嘉琪 2012 61 240202]
[8]	Wang Z, Huang X, Li Y X, Song X N 2013 Chin. Phys. B 22 010504
[9]	Wang Z, Huang X, Li Y X, Song X N 2012 Chin. Phys. B 21 050506
[10]	Sun Z G, Han C Z 2010 Acta Phys. Sin. 59 3210 (in Chinese) [孙增国, 韩崇昭 2010 59 3210]
[11]	Sun Z G, Han C Z 2007 Acta Phys. Sin. 56 4565 (in Chinese) [孙增国, 韩崇昭 2007 56 4565]
[12]	Perona P, Malik J 1990 IEEE Trans. Pattern Anal. Mach. Intell. 12 629
[13]	Catte F, Lions P L, Morel J M 1992 SIMA J. Numer. Anal. 29 182
[14]	Li Y Y, Kaveh M 2000 IEEE Trans. Image Process. 9 1723
[15]	Gilboa G, Sochen N, Zeevi Y Y 2002 IEEE Trans. Image Process. 11 689
[16]	Zhang Y H, Ding Y, Wang L H 2011 Proced. Engineer. 15 2778
[17]	Li J C, Ma Z H, Peng Y X, Huang B 2013 Acta Phys. Sin. 62 099501 (in Chinese) [李金才, 马自辉, 彭宇行, 黄斌 2013 62 099501]
[18]	Thirion J P 1988 Med. Image Anal. 2 243
[19]	Wang D K, Hou Y Q, Peng J Y 2008 Partial Differential Equation Method of Image Processing (Beijing: Science Press) pp13-17 (in Chinese) [王大凯,侯愉青,彭进业 2008 图像处理的偏微分方程方法(北京:科学出版社) 第13–17页]
[20]	Weickert J, Bary H R, Max A V 1998 IEEE Trans. Image Process. 7 398

施引文献

[1]	Gonzalez R C, Woods R E (translated by Ruan Q Q, Ruan Y Z) 2010 Digital Image Processing (3rd Edition) (Beijing: Publishing House of Electronics Industry) pp197-213 (in Chinese) [冈萨雷斯R C, 伍兹 R E 著 (阮秋琦, 阮宇智译) 2010(第三版)数字图像处理(北京: 电子工业出版社) 第197–213页]
[2]	Liu P, Fang H, Li G Q, Liu Z W 2012 IEEE Geosci. Remote Sens. 9 358
[3]	Bumsub H, Dongbo M, Kwanghoon S 2013 IEEE Trans. Image Process. 22 1096
[4]	Sofou A, Evangelopoulos G, Maragos P 2005 IEEE Geosci. Remote Sens. 3 94
[5]	Li Z B, Liu Z Z, Shi W Z 2014 IEEE Geosci. Remote Sens. 11 743
[6]	Shi L F, Mo J Q 2013 Acta Phys. Sin. 62 040203 (in Chinese) [石兰芳, 莫嘉琪 2013 62 040203]
[7]	Zhou X C, Lin W T, Lin Y H, Mo J Q 2012 Acta Phys. Sin. 61 240202 (in Chinese) [周先春, 林万涛, 林一骅, 莫嘉琪 2012 61 240202]
[8]	Wang Z, Huang X, Li Y X, Song X N 2013 Chin. Phys. B 22 010504
[9]	Wang Z, Huang X, Li Y X, Song X N 2012 Chin. Phys. B 21 050506
[10]	Sun Z G, Han C Z 2010 Acta Phys. Sin. 59 3210 (in Chinese) [孙增国, 韩崇昭 2010 59 3210]
[11]	Sun Z G, Han C Z 2007 Acta Phys. Sin. 56 4565 (in Chinese) [孙增国, 韩崇昭 2007 56 4565]
[12]	Perona P, Malik J 1990 IEEE Trans. Pattern Anal. Mach. Intell. 12 629
[13]	Catte F, Lions P L, Morel J M 1992 SIMA J. Numer. Anal. 29 182
[14]	Li Y Y, Kaveh M 2000 IEEE Trans. Image Process. 9 1723
[15]	Gilboa G, Sochen N, Zeevi Y Y 2002 IEEE Trans. Image Process. 11 689
[16]	Zhang Y H, Ding Y, Wang L H 2011 Proced. Engineer. 15 2778
[17]	Li J C, Ma Z H, Peng Y X, Huang B 2013 Acta Phys. Sin. 62 099501 (in Chinese) [李金才, 马自辉, 彭宇行, 黄斌 2013 62 099501]
[18]	Thirion J P 1988 Med. Image Anal. 2 243
[19]	Wang D K, Hou Y Q, Peng J Y 2008 Partial Differential Equation Method of Image Processing (Beijing: Science Press) pp13-17 (in Chinese) [王大凯,侯愉青,彭进业 2008 图像处理的偏微分方程方法(北京:科学出版社) 第13–17页]
[20]	Weickert J, Bary H R, Max A V 1998 IEEE Trans. Image Process. 7 398

[1]	林丹樱, 龚振权, 黄黎琳, 聂梦娇, 于斌, 屈军乐. 用于多通道单分子定位的高精度图像配准方法. , 2024, 73(6): 068701. doi: 10.7498/aps.73.20231695
[2]	汪书潮, 苏秀琴, 朱文华, 陈松懋, 张振扬, 徐伟豪, 王定杰. 基于弹性变分模态提取的时间相关单光子计数信号去噪. , 2021, 70(17): 174304. doi: 10.7498/aps.70.20210149
[3]	苏博, 陶芬, 李可, 杜国浩, 张玲, 李中亮, 邓彪, 谢红兰, 肖体乔. 同步辐射纳米CT图像配准方法研究. , 2021, 70(16): 160704. doi: 10.7498/aps.70.20210156
[4]	郎利影, 陆佳磊, 于娜娜, 席思星, 王雪光, 张雷, 焦小雪. 基于深度学习的联合变换相关器光学图像加密系统去噪方法. , 2020, 69(24): 244204. doi: 10.7498/aps.69.20200805
[5]	李静和, 何展翔, 杨俊, 孟淑君, 李文杰, 廖小倩. 曲波域统计量自适应阈值探地雷达数据去噪技术. , 2019, 68(9): 090501. doi: 10.7498/aps.68.20182061
[6]	程志远, 李治国, 折文集, 夏爱利. 激光相干场成像散斑噪声复合去噪方法. , 2019, 68(5): 054206. doi: 10.7498/aps.68.20181578
[7]	王梦蛟, 周泽权, 李志军, 曾以成. 混沌信号自适应协同滤波去噪. , 2018, 67(6): 060501. doi: 10.7498/aps.67.20172470
[8]	刘柏年, 皇群博, 张卫民, 任开军, 曹小群, 赵军. 集合背景误差方差中小波阈值去噪方法研究及试验. , 2017, 66(2): 020505. doi: 10.7498/aps.66.020505
[9]	范虹, 韦文瑾, 朱艳春. 基于二维集合经验模式分解的距离正则化水平集磁共振图像分割. , 2016, 65(16): 168701. doi: 10.7498/aps.65.168701
[10]	王梦蛟, 吴中堂, 冯久超. 一种参数优化的混沌信号自适应去噪算法. , 2015, 64(4): 040503. doi: 10.7498/aps.64.040503
[11]	尹艳玲, 乔钢, 刘凇佐, 周锋. 基于基追踪去噪的水声正交频分复用稀疏信道估计. , 2015, 64(6): 064301. doi: 10.7498/aps.64.064301
[12]	赵辽英, 吕步云, 厉小润, 陈淑涵. 基于尺度不变特征变换和区域互信息优化的多源遥感图像配准. , 2015, 64(12): 124204. doi: 10.7498/aps.64.124204
[13]	李广明, 吕善翔. 混沌信号的压缩感知去噪. , 2015, 64(16): 160502. doi: 10.7498/aps.64.160502
[14]	周先春, 汪美玲, 石兰芳, 周林锋, 吴琴. 基于梯度与曲率相结合的图像平滑模型的研究. , 2015, 64(4): 044201. doi: 10.7498/aps.64.044201
[15]	范虹, 朱艳春, 王芳梅, 张旭梅. 多分辨率水平集算法的乳腺MR图像分割. , 2014, 63(11): 118701. doi: 10.7498/aps.63.118701
[16]	吕善翔, 冯久超. 一种混沌映射的相空间去噪方法. , 2013, 62(23): 230503. doi: 10.7498/aps.62.230503
[17]	计时鸣, 翁晓星, 谭大鹏. 基于水平集方法二维模型的软性磨粒两相流流场特性分析方法. , 2012, 61(1): 010205. doi: 10.7498/aps.61.010205
[18]	何文平, 吴琼, 成海英, 张文. 不同滤波方法在去趋势波动分析中去噪的应用比较. , 2011, 60(2): 029203. doi: 10.7498/aps.60.029203
[19]	侯威, 廉毅, 封国林. 基于搜索平均法的气象观测数据的非线性去噪. , 2007, 56(1): 589-596. doi: 10.7498/aps.56.589
[20]	梁艳梅, 翟宏琛, 母国光. 模糊集理论在彩色图像检索中的应用. , 2002, 51(12): 2671-2675. doi: 10.7498/aps.51.2671

计量

文章访问数: 6323
PDF下载量: 503
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板