一种基于新型符号函数的小波阈值图像去噪算法

doi:10.11959/j.issn.1000-0801.2017012

电信科学 ›› 2017, Vol. 33 ›› Issue (1): 45-52.doi: 10.11959/j.issn.1000-0801.2017012

一种基于新型符号函数的小波阈值图像去噪算法

崔金鸽¹,陈炳权^1,²(),徐庆¹,邓波¹

¹ 吉首大学物理与机电工程学院，湖南吉首 416000
² 吉首大学信息科学与工程学院，湖南吉首 416000

修回日期:2017-01-04 出版日期:2017-01-01 发布日期:2017-06-04
作者简介:崔金鸽（1991-），男，吉首大学物理与机电工程学院硕士生，主要研究方向为信号处理技术。|陈炳权（1972-），男，博士，吉首大学物理与机电工程学院副教授，主要研究方向为图像处理与智能控制。|徐庆（1988-），男，吉首大学物理与机电工程学院硕士生，主要研究方向为图像处理技术。|邓波（1990-），男，吉首大学物理与机电工程学院硕士生，主要研究方向为图像编码压缩感知。
基金资助:
湖南省自然科学基金资助项目(2016JJ4074);湖南省教育厅科学研究项目(14C0920);吉首大学课题资助项目(Jdy16023);吉首大学课题资助项目(15JDY032)

A wavelet threshold image denoising algorithm based on a new kind of sign function

Jinge CUI¹,Bingquan CHEN^1,²(),Qing XU¹,Bo DENG¹

¹ College of Physics and Electromechanical Engineering,Jishou University,Jishou 416000,China
² College of Information Science and Engineering,Jishou University,Jishou 416000,China

Revised:2017-01-04 Online:2017-01-01 Published:2017-06-04
Supported by:
Hunan Provincial Natural Science Foundation of China(2016JJ4074);Project of Hunan Provincial Education Department of China(14C0920);Project of Jishou University Subject(Jdy16023);Project of Jishou University Subject(15JDY032)

摘要/Abstract

摘要：

在现有阈值去噪算法的基础上提出了一种基于新型符号函数的小波阈值图像去噪算法，该算法提出的新阈值函数具有连续可导、小波系数偏差小、阈值自适应性强等优势。不仅保留了分解后的低频小波系数，还有效滤除了高频系数中的噪声系数，使得重构后的图像更接近原始图像。对高斯白噪声的Bridge图像、Lena图像及含“斑点噪声”的B超Fetus图像进行仿真，实验的结果表明，无论是新阈值函数的视觉效果，还是定量指标PSNR和MSE，均优于现有的阈值图像去噪算法。其边缘及细节信息能得到较好的保护，无明显振荡，图像更平滑、均匀，且在复杂噪声背景下，该方法具有较好的顽健性。

关键词: 符号函数, 小波阈值, 去噪, 顽健性

Abstract:

Based on the existing threshold denoising algorithm,a threshold denoising algorithm based on the new symbolic function was proposed.The new threshold function has advantages of continuous guidance,small deviation of wavelet coefficient,strong threshold adaptability and so on.It not only preserved the low-frequency wavelet coefficients,but also filtered the noise coefficients in the high-frequency coefficients effectively,so that the reconstructed image was closer to the original image.The simulation results of Bridge image,Lena image and B-mode Fetus image with Gaussian white noise show that the visual effect of both the new threshold function and the quantitative indicators PSNR and MSE are better than the existing threshold image denoising algorithm.The edge and detail information can be better protected,have no obvious oscillation,the image is smoother and even,and the method has good stubbornness under the background of complex noise.

Key words: sign function, wavelet threshold, denoising, robustness

中图分类号:

TP391.4

崔金鸽,陈炳权,徐庆,邓波. 一种基于新型符号函数的小波阈值图像去噪算法[J]. 电信科学, 2017, 33(1): 45-52.

Jinge CUI,Bingquan CHEN,Qing XU,Bo DENG. A wavelet threshold image denoising algorithm based on a new kind of sign function[J]. Telecommunications Science, 2017, 33(1): 45-52.

图/表 9

图1

图2

图3

图4

图5

图6

表1

表2

图7

参考文献 19

[1]	谢杰成，张大力，徐文立 . 小波图像去噪综述[J]. 中国图象图形学报， 2002,7(3): 209-217.
	XIE J C , ZHANG D L , XU W L . Overview on wavelet image denoising[J]. Journal of Image and Graphics, 2002,7(3): 209-217.
[2]	DONOHO D L , JOHNSTONE I M . Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika, 1994,81(3):425-455.
[3]	DONOHO D L , JOHNSTONE I M , KERKYACHARIAN G , et al. Wavelet shrinkage:asymptopia[J]. Journal of Royal Statistics Society Series(B), 1995(57):301-369.
[4]	BRUCE A G , GAO H Y . Understanding WaveShrink:variance and biasestimation[J]. Biometrika, 1996,83(4):727-745.
[5]	GUNAWAN D . Denoising images using wavelet transform[C]//1999 IEEE Pacific Rim Conference on Communications,Computers and Signal Processing,Aug 22-24,1999,Victoria,BC,Canada. New Jersey: IEEE Press, 1999:83-85.
[6]	SHARK L K , YU C . Denoising by optimal fuzzy thresholding in wavelet domain[J]. Electronics Letters, 2000,36(6):581-582.
[7]	MUKHOPADHYAY S , MANDALJ K . Wavelet based denoising of medical images using sub-band adaptive thresholding through genetic algorithm[J]. Procedia Technology, 2013,10(2):680-689.
[8]	GUPTA D K , PAWARV S , JAIN Y K . Wavelet based multilevel sub-band adaptive thresholding for image denoising using modified PSO algorithm[J]. International Advanced Research Journal in Science, 2015,12(2):24-30.
[9]	张遵伟，罗晓辉，张德胜，等. 阈值改进算法在小波去噪中的应用[J]. 西华大学学报(自然科学版)， 2010,29(5): 43-45.
	ZHANG Z W , LUO X H , ZHANG D S , et al. An improved thresholding denosing algorithm and its application in wavelet denoising[J]. Journal of Xihua University(Natural Science Edition), 2010,29(5): 43-45.
[10]	杨鑫蕊 . 改进的小波阈值去噪算法研究[D]. 哈尔滨：哈尔滨理工大学， 2014.
	YANG X R . Research on improved wavelet threshold denoising algorithm[D]. Harbin: Harbin University of Science and Technology, 2014.
[11]	王琪，程彬，杜娟，等. 一种改进的小波阈值图像去噪方法[J]. 计算机与现代化， 2015(4): 65-69.
	WANG Q , CHENG B , DU J , et al. An improved method for denoising of wavelet threshold images[J]. Modern Electronics Technique, 2015(4): 65-69.
[12]	谢家林，李根强，谢家丽，等. 改进阈值函数在图像去噪中的应用[J]. 空军工程大学学报(自然科学版)， 2016,17(1): 72-76.
	XIE J L , LI G Q , XIE J L , et al. Research on the application of the improved threshold function to image denoising[J]. Journal of Air Force Engineering University(Natural Science Edition), 2016,17(1): 72-76.
[13]	JITHA C R . Image denoising by modified overcomplete wavelet representation utilizing adaptive thresholding algorithm[J]. International Journal of Scientific ＆ Engineering Research, 2015,4(6): 802-813.
[14]	BHANDARI A K , KUMAR A , SINGH G , et al. Performance study of evolutionary algorithm for different wavelet filters for satellite image denoising using sub-band adaptive threshold[J]. Journal of Experimental ＆ Theoretical Artificial Intelligence, 2015,28(1-2):71-95.
[15]	杜春 . 运动模糊图像恢复和小波阈值去噪算法研究[D]. 长沙：国防科学技术大学， 2008.
	DU C . Motion blurred image restoration and wavelet threshold denoising algorithm analysis[D]. Changsha: National University of Defense Technology, 2008.
[16]	袁开明，舒乃秋，孙云莲，等. 基于阈值寻优法的小波去噪分析[J]. 武汉大学学报(工学版)， 2015,48(1): 74-80.
	YUAN K M , SHU N Q , SUN Y L , et al. Wavelet denoising based on threshold optimization method[J]. Engineering Journal of Wuhan University, 2015,48(1): 74-80.
[17]	VERMA S , KHARE N . Denoising of computed tomography images using wavelet transform[J]. International Journal for Innovative Research in Science ＆ Technology, 2015,1(8):21-29.
[18]	侯宏花，陈树越，郭保全 . 医学B超图像降噪处理的三种方法比较[J]. 测试技术学报， 2003,17(3): 262-264.
	HOU H H , CHEN S Y , GUO B Q , et al. Comparison of three methods in decreasing noise of medical B model ultrasonic images[J]. Journal of Test and Measurement Technology, 2003,17(3): 262-264.
[19]	张聚，王陈，程芸 . 小波与双边滤波的医学超声图像去噪[J]. 中国图象图形学报， 2014,19(1): 126-132.

去噪方法		Bridge			Lena			Fetus		结论
去噪方法	MSE		PSNR/dB	MSE		PSNR/dB	MSE		PSNR/dB	结论
硬阈值法	62.164 2		30.483 2	161.592 1		26.146 5	11.887 9		36.235 6	局部有振荡
软阈值法	77.923 5		29.110 1	220.769 7		25.384 2	25.870 3		35.032 8	边缘出现模糊
参考文献[4]方法	61.739 8		30.314 5	157.227 0		26.139 9	12.159 8		37.412 0	局部过于平滑
参考文献[9]方法	67.772 1		29.923 3	177.684 2		25.723 1	17.247 8		36.221 5	部分细节信息缺失
参考文献[11]方法	62.499 2		30.203 6	158.771 2		26.112 5	15.113 0		36.645 8	景深突变处出现失真
本文方法	52.423 6		30.978 4	136.002 1		26.849 5	8.547 9		38.993 1	效果较好

k		Bridge			Lena			Fetus
k	MSE		PSNR/dB	MSE		PSNR/dB	MSE		PSNR/dB
0	61.873 2		30.446 5	160.851 7		26.223 6	15.012 2		36.597 0
1	52.423 6		30.978 4	136.002 1		26.849 5	8.547 9		38.993 1
2	55.001 5		30.932 7	136.855 3		26.861 0	9.230 4		38.777 6
3	56.328 9		30.749 0	138.130 6		26.728 4	9.603 1		38.289 9

一种基于新型符号函数的小波阈值图像去噪算法

A wavelet threshold image denoising algorithm based on a new kind of sign function

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 19

相关文章 5

Metrics

推荐阅读 0

[1]	杨帅, 王瑞琴, 马辉. 基于多通道的边学习图卷积网络[J]. 电信科学, 2022, 38(9): 95-104.
[2]	康凯凯,刘兆霆,姚英彪. 传感器网络分布式顽健RLS估计算法[J]. 电信科学, 2019, 35(1): 37-43.
[3]	李丹,王慧倩,柏桐,林金朝,庞宇,姜小明,蒋宇皓. 基于双树复小波变换和形态学的脉搏信号去噪[J]. 电信科学, 2016, 32(12): 93-98.
[4]	姜海涛,李斌,王祥,陈锦铭,郭雅娟. 智能电子设备顽健性测试方法[J]. 电信科学, 2015, 31(Z1): 125-131.
[5]	胡荣贻,彭木根,张洪岩,李远. LTE-Advanced系统中的移动顽健性优化技术研究[J]. 电信科学, 2013, 29(5): 84-89.